CN109086277B - Method, system, mobile terminal and storage medium for constructing map in overlapping area - Google Patents
Method, system, mobile terminal and storage medium for constructing map in overlapping area Download PDFInfo
- Publication number
- CN109086277B CN109086277B CN201710440699.7A CN201710440699A CN109086277B CN 109086277 B CN109086277 B CN 109086277B CN 201710440699 A CN201710440699 A CN 201710440699A CN 109086277 B CN109086277 B CN 109086277B
- Authority
- CN
- China
- Prior art keywords
- map
- vehicle
- information
- constructed
- landmark
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000010276 construction Methods 0.000 claims abstract description 39
- 230000008447 perception Effects 0.000 claims abstract description 19
- 230000033001 locomotion Effects 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 17
- 230000000007 visual effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010034719 Personality change Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Navigation (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a map construction method and system for an overlapping area, a mobile terminal and a storage medium. In the map construction mode, information perception data of a vehicle are obtained, landmark information is extracted from the information perception data, and a landmark map and a vehicle running track are generated according to the motion gesture of the vehicle and the landmark information based on a SLAM algorithm; the map constructed in times is compared with the similarity of the overlapped areas, and the map is spliced after successful matching; and circularly performing a map construction process to form a local or global map. And matching the map constructed in multiple times according to the landmark information, so that the accuracy of constructing the map is continuously improved, and meanwhile, the functions of comparing with the vehicle-mounted map and downloading in the cloud are supported.
Description
Technical Field
The present invention relates to the field of computer communications and network security, and in particular, to a method, a system, a mobile terminal, and a storage medium for constructing a map in an overlapping area.
Background
The increase of the automobile storage quantity promotes the development of large-scale parking lots, and in twenty-first century, the large-scale parking lots are more and more, and the increasing of the scale of the parking lots brings a series of problems of parking and taking vehicles, so that the large-scale parking lots become the social problems generally faced by each large-scale and medium-scale city worldwide.
First, as urban vehicles increase and traffic congestion increases, the difficulty of parking in the city increases greatly. Many drivers feel it difficult to drive the parking technology. Secondly, on one hand, the vehicle owner faces a gradually increased tour path due to parking space searching when parking, and on the other hand, the walking distance of the vehicle owner when the vehicle owner walks out of the parking lot is increased, so that the physical strength, time and energy cost of the vehicle owner are increased; meanwhile, the parking spaces of the large-scale parking lot are numerous and the indication is not clear enough, and the vehicle searching is greatly plagued by the parking spaces in the case of being in the vast.
Today, the development of vehicles is more and more developed, the intellectualization of vehicles is a great trend of the future development of vehicles, and how to make the vehicles acquire the map of a parking lot and position the vehicles in the parking lot is a technical problem which needs to be solved urgently in the process of realizing autonomous parking of the vehicles.
The outdoor map of the vehicle is mainly satellite positioning (including difference), and the satellite positioning mainly comprises a GPS system, a Beidou system, a GLONASS system and a Galileo system. The satellite positioning has the disadvantage of being easily affected by tall buildings and trees, and cannot achieve ideal accuracy in many scenes. The construction of the map of the vehicle interior space is performed by using INS signals (readings from accelerometers, gyroscopes, compasses, pressure sensors, etc.), or by using navigation systems that combine inertial navigation signals with satellite systems. SLAM techniques (Simultaneous Localization and Mapping instant localization and mapping) are sometimes employed.
At present, a concrete scheme for constructing an indoor map by adopting SLAM technology is as follows: the patent literature of the map construction method, the system, the mobile terminal and the storage medium adopts the following technical scheme: "when any one of the vehicles is in the map construction mode, acquiring a motion posture of the vehicle and a vehicle surrounding image and extracting landmark information from the vehicle surrounding image; generating a landmark map and a vehicle running track according to the motion gesture of the vehicle and the landmark information based on the SLAM algorithm; detecting a drivable region and generating a grid map according to the vehicle travel track and the detected drivable region; and when the vehicle runs in different areas of the parking lot, the map construction process is circularly carried out to form a local or global constructed map. In this case, the vehicle motion posture and the vehicle surrounding image need not be acquired by the acquisition vehicle, but by a single user vehicle on which the vehicle-mounted system is mounted.
Disclosure of Invention
In order to solve the above and other potential technical problems, the present invention provides a map construction method, system, mobile terminal and storage medium for an overlap region, firstly, when in a map construction mode, a map is generated according to the constructed map overlap region, information sensing data of the overlap region is based on keyframes, a relative transformation relationship between a plurality of nodes is established, maintenance of the key nodes is continuously performed, capacity of the data is ensured, and calculation amount is reduced while accuracy is ensured. Secondly, the system automatically generates the grid map and the landmark map, does not depend on a design drawing as a basic map, and automates the map generation process, so that manual intervention is reduced. Thirdly, the information sensing data of the overlapping area acquired by the system is processed in a unified way according to the data types, the time stamps and the coordinate systems of different types of sensors, the data is compared with a model of the same coordinate point or coordinate range of a map in a support library, if the information sensing data is inconsistent with the data in the support library, the system reports errors, and then whether the data need to be changed is identified according to a deep learning network. Fourth, the SLAM algorithms presented herein include, but are not limited to, PTAM, monoSLAM, ORB-SLAM, RGBD-SLAM, RTAB-SLAM, LSD-SLAM. Fifth, the system has two modes of operation: and constructing a mode and a positioning mode, and comprehensively judging the two modes according to the instruction received by the system and the information perception data. Sixth, 2D and/or 3D maps and driving tracks can be displayed on the vehicle-mounted screen and the mobile phone.
The method for constructing and updating the map according to the overlapping area comprises the following steps:
s01: when any vehicle is in a map building mode, acquiring information perception data of the vehicle and extracting landmark information from the information perception data;
s02: based on the SLAM algorithm, generating a landmark map and a vehicle running track according to the motion gesture of the vehicle and the landmark information;
s03: comparing the similarity of the overlapping areas for the map constructed in the step S02 in a number of times, and splicing after successful matching;
s04: and circularly performing a map construction process to form a local or global map.
In this embodiment, in step S03, when comparing the similarity of the overlapping areas 100, the information sensing data of the map boundaries constructed in batches may be extracted, the absolute position of the landmark information 110 included in the information sensing data of the map boundaries is determined according to the position, size and angle of the landmark information in the image, and two or more constructed maps are matched and spliced according to the absolute position of one or more landmark information 110 until the global map is obtained.
Further, when two or more maps constructed in batches are matched and spliced according to the absolute positions of the landmark information 110, if a 2D map is built, matching and splicing are preferably performed according to the absolute positions of the three landmark information 110, and preferably the three landmark information 110 are not on the same straight line. When the absolute positions of the three landmark information 110 are spliced, the degree of freedom of the spliced map can be limited, and the map can be prevented from rotating and shaking. The coordinate information in the overlapping area 100 in the above two embodiments may be one coordinate point 101 or a region with a coordinate range.
Further, if the 3D map is created, matching and stitching are preferably performed according to the absolute positions of the four landmark information 110, and preferably three landmark information 110 are located in one dimension, and another landmark information 110 and the remaining three landmark information are located in different dimensions. Such absolute position concatenation of the four landmark information 110 can limit the degree of freedom of the spliced map.
Further, the building map can be compared with the vehicle-mounted map, and when the building map is updated, updated contents are sent to a cloud server of the vehicle-mounted map, so that the building map is updated and displayed in the vehicle-mounted map.
Further, S011 in the above two embodiments: the information sensing data of the overlapping area 100 acquired by the system are processed uniformly according to the data types of different types of sensors, the time stamp 12 and the coordinate system 13; s012: comparing the data with the region 102 model of the same coordinate point 101 or coordinate range of the map in the support library; s013: if the information sensing data is inconsistent with the data in the support library, the system reports errors; s014: then learn the network according to the depth it is identified whether a change is required.
Further, the embodiment of the invention also provides a map construction system, which comprises an acquisition processing module, a map construction module and a map construction module, wherein the acquisition processing module is used for acquiring information perception data of a vehicle and extracting landmark information from the information perception data when any vehicle is in a map construction mode; a landmark map module for mapping the map data based on SLAM algorithm, generating a landmark map and a vehicle running track according to the information sensing data of the vehicle; and the comparison matching module is used for comparing the similarity of the overlapping areas, and matching the map constructed in batches through landmark information coordinates of the overlapping areas to form a local or global constructed map.
Further, the vehicle driving system further comprises a grid map module, wherein the grid map module is used for detecting a driving area according to the movement gesture of the driving area and generating a grid map according to the driving track of the vehicle and the detected driving area; when the vehicle runs in different areas of the parking lot, the grid map and the landmark map are circularly constructed, and a local or global construction map is formed.
Further, the vehicle-mounted map updating system further comprises a map data updating unit, wherein the map data updating unit is used for comparing the constructed map with the vehicle-mounted map, and when the constructed map is updated, updated contents are sent to a cloud server of the vehicle-mounted map, so that the constructed map is updated and displayed in the vehicle-mounted map. The map data updating unit can also upload the updated result to the cloud end so as to be convenient for other users to download. From the above, the map construction of the embodiment can realize the instant map construction.
Further, when the vehicle runs in different areas of the parking lot, the grid map and the landmark map are circularly constructed, and a local or global construction map is formed.
The embodiment of the invention also provides a mobile terminal which comprises the map building system. The above description of the map construction system has been described in detail, and will not be repeated here. The mobile terminal may be, for example, a mobile phone, a PAD, a computer, a server, or the like.
In another embodiment, a mobile terminal comprises a processor and a memory, the memory storing program instructions that execute the steps in the method as described above. The mobile terminal is, for example, a smart phone, a vehicle-mounted terminal or the like.
Embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps in the method as described above.
As described above, the present invention has the following advantageous effects:
in the map construction mode, the system collects information perception data of the overlapping area between vehicles and generates a map based on the information perception data of the overlapping area, a relative transformation relation between a plurality of nodes is established based on a keyframe (key frame), the key nodes are maintained continuously, the capacity of the data is guaranteed, and the calculated amount is reduced while the accuracy is guaranteed. The system automatically generates the grid map and the landmark map without depending on a design drawing as a basic map, and the map generation process is automated, so that manual intervention is reduced. The information sensing data of the overlapping area acquired by the system is processed in a unified way according to the data types, the time stamps and the coordinate systems of different types of sensors, the data is compared with a model of the same coordinate point or coordinate range of a map in a support library, if the information sensing data is inconsistent with the data in the support library, the system reports errors, and then whether the data need to be changed is identified according to a deep learning network. The system can display the 2D plane map and the driving track on the vehicle-mounted screen and the mobile phone.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic flow chart of the present invention.
Fig. 2 is a schematic view of an overlapping region according to an embodiment of the present invention.
Fig. 3 shows a schematic view of an overlapping region according to another embodiment of the present invention.
Fig. 4 shows a schematic view of an overlapping region according to another embodiment of the present invention.
Fig. 5 shows a schematic view of an overlapping region according to another embodiment of the present invention.
Fig. 6 shows a flow chart comparing a build map of the present invention with a known on-board map.
Fig. 7 is a diagram showing a frame of information-aware data according to the present invention.
Fig. 8 shows a flowchart for landmark information loop detection when building a map.
FIG. 9 is a flow chart of landmark information loop detection in building a map according to another embodiment.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or otherwise, used in the practice of the invention, are not intended to be critical to the essential characteristics of the invention, but are intended to fall within the spirit and scope of the invention. Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
The map construction method, the map construction system, the mobile terminal and the storage medium are applied to indoor and outdoor single-layer or multi-layer parking lots.
The map construction method provided in this embodiment uses a SLAM algorithm, and the map construction part may be completed by different vehicles or devices.
Referring to fig. 1, the method for constructing and updating a map according to an overlapping area includes the following steps:
s01: when any vehicle is in a map building mode, acquiring information perception data of the vehicle and extracting landmark information from the information perception data;
s02: generating a landmark map and a vehicle running track according to the motion gesture of the vehicle and the landmark information based on the SLAM algorithm;
s03: comparing the similarity of the overlapping areas for the map constructed in the step S02 in a number of times, and splicing after successful matching;
s04: and circularly performing a map construction process to form a local or global map.
Referring to fig. 2 to 5, in the present embodiment, when comparing the similarity of the overlapping areas 100 in step S03, the information sensing data of the map boundaries constructed in batches may be extracted, the absolute position of the landmark information 110 included in the information sensing data of the map boundaries may be determined according to the position, size and angle of the landmark information in the image, and two or more maps constructed in batches may be matched and spliced according to the absolute position of one or more landmark information 110 until a global map is obtained. Further, when two or more maps constructed in batches are matched and spliced according to the absolute positions of the landmark information 110, if a 2D map is built, matching and splicing are preferably performed according to the absolute positions of the three landmark information 110, and preferably the three landmark information 110 are not on the same straight line. When the absolute positions of the three landmark information 110 are spliced, the degree of freedom of the spliced map can be limited, and the map can be prevented from rotating and shaking. The coordinate information in the overlapping area 100 in the above two embodiments may be one coordinate point 101 or a region with a coordinate range. If a 3D map is created, matching and stitching are preferably performed according to the absolute positions of the four landmark information 110, and preferably three landmark information 110 are in one dimension, and another landmark information 110 and the remaining three landmark information are in different dimensions. Such absolute position concatenation of the four landmark information 110 can limit the degree of freedom of the spliced map.
Referring to fig. 6, in this embodiment, a build map may also be compared with the vehicle-mounted map, and when the build map is updated, updated content is sent to a cloud server of the vehicle-mounted map, so that the build map is updated and displayed in the vehicle-mounted map. When a known map is used for positioning, SLAM can be used for constructing the map at the same time. The map is compared with the known vehicle-mounted map, so that whether the current environment is changed compared with the map construction can be found. The updated results may be uploaded to the cloud for download by other users. In the present embodiment, S011 in the above two embodiments: the information sensing data of the overlapping area 100 acquired by the system are processed uniformly according to the data types of different types of sensors, the time stamp 12 and the coordinate system 13; s012: comparing the data with the region 102 model of the same coordinate point 101 or coordinate range of the map in the support library; s013: if the information sensing data is inconsistent with the data in the support library, the system reports errors; s014 the method comprises the following steps: and then identifying whether the change is needed according to the deep learning network.
Referring to fig. 7, in the present embodiment, the information sensing data in the above two embodiments includes, but is not limited to, a data packet 11 of a different type of sensor, a time stamp 12, and a coordinate system 13. In the present embodiment, the data packets 11 of the different types of sensors in the above two embodiments are data packets of signals collected by any one or more of the visual navigation sensor 11a, the light reflection navigation sensor 11b, and the ultrasonic navigation sensor 11 c. The system uses the data packet of the visual navigation sensor 11a as information sensing data, and the visual navigation sensor 11a includes an image sensor and a motion posture sensor of the vehicle, and compresses the image information and the motion posture information.
In this embodiment, the data packet of the light reflection navigation sensor 11b is used as information sensing data by the system in the above two embodiments, and the light reflection navigation sensor 11b may be a laser sensor or an infrared sensor, so as to compress the distance information between the laser sensor or the infrared sensor and the external object.
In the present embodiment, the system in the above two embodiments uses the data packet of the ultrasonic navigation sensor 11c as the information sensing data, the ultrasonic navigation sensor 11c is an ultrasonic transmitter and an ultrasonic receiver, and the distance information generated by the ultrasonic transmitter and the ultrasonic receiver is compressed.
In this embodiment, the motion gesture of the vehicle includes position information and heading angle. The motion attitude of the vehicle can be estimated by an odometer, the odometer comprises four-wheel rotation pulses and steering wheel rotation angles, and the relative transportation attitude change of the vehicle can be estimated. In particular, the motion pose of the vehicle is obtained from steering wheel angle, wheel pulse, speed parameters (e.g., acceleration, angular velocity) of a vehicle Inertial Measurement Unit (IMU), and GPS. Position information of the vehicle is acquired by using GPS, and heading angle of the vehicle is acquired by using steering wheel rotation angle, wheel pulse and speed parameters (such as acceleration and angular speed) of an Inertial Measurement Unit (IMU) of the vehicle. The course angle can be calculated by using an angular velocity meter, can also be calculated by using a vehicle four-wheel rotation pulse and a steering wheel rotation angle, can also be calculated by using Visual SLAM, and can also be fused with the data sources. In this way predictions of position and heading angle can be obtained. Since the acquisition of heading angle is well known to those skilled in the art, it is not described in detail herein. In the SLAM process, the result perceived by the camera is combined, and the position and the course angle are updated. Prediction and updating are constantly iterative processes. The landmark information includes, but is not limited to, corner coordinates of a parking space, a column edge in a parking lot, a column projection, and a bumper edge. The information of these landmarks in the map refers specifically to the coordinates (x, y) on the ground, and may also include the directions (x, y, theta) of the landmarks. The extraction of the specified landmark information from the images around the vehicle is a mature technology in the field of image processing, and will not be described herein.
In this embodiment, the proposed SLAM algorithm includes, but is not limited to, PTAM, monoSLAM, ORB-SLAM, RGBD-SLAM, RTAB-SLAM, LSD-SLAM, EXF family, particle filtering (FastSLAM), graph optimization. Most vision-based SLAM techniques select landmark information such as SIFT, FAST. But these landmark information are subject to large environmental changes. The time invariance is bad. So it cannot be saved in the map. In the embodiment, when the map is constructed by utilizing the SLAM algorithm, the selected landmark information comprises the fixed point of the parking space, the edge of the upright post, the projection of the upright post on the ground and the like. The detection of the corner coordinates of the parking space can refer to any detection means in the prior art, and is a relatively mature technology in the field. In this embodiment, the edge detection of the upright post adopts landmark information in Visual SLAM, and the characteristics that most upright posts of the parking lot have yellow-black interval anti-collision strips are utilized to extract the characteristics that the same 2D coordinates are provided, but the heights are equal in interval, so as to detect the edge.
Referring to fig. 8 to fig. 9, in this embodiment, the map construction method further includes loop detection of landmark information, and specifically includes: s021: narrowing the detection range of landmark information by utilizing the grid map in a scanning matching mode; s022: and further detecting landmark information by using the landmark map. The map construction method further comprises a step of loop detection of landmark information, and because landmark information in a parking lot is repeated, loop detection based on the landmark information is prone to generating matching errors.
In another embodiment, the loop detection may specifically include: s031: and narrowing the detection range of landmark information by utilizing the grid map in a scanning matching mode. And detecting the loop in a large-scale space in a scanning matching mode according to the network map. S032: and further detecting landmark information by using the landmark map. And (3) narrowing the searching range of the landmark information, and performing global optimization on the map through landmark information loop detection. S033: and comparing the constructed map with the vehicle-mounted map, and when the constructed map is updated, sending updated contents to a cloud server of the vehicle-mounted map, so that the constructed map is updated and displayed in the vehicle-mounted map. Because landmark information is repeated in a parking lot, loop detection based on landmark information is prone to matching errors. The loop detection module specifically comprises: the first-stage detection unit is used for narrowing the detection range of landmark information by utilizing the grid map in a scanning matching mode, and detecting a loop in a large-scale space according to the network map in the scanning matching mode. And the second-stage detection unit is used for further detecting landmark information by using the landmark map. And (3) narrowing the searching range of the landmark information, and performing global optimization on the map through landmark information loop detection.
The embodiment of the invention also provides a map construction system, which comprises an acquisition processing module, a map construction module and a map construction module, wherein the acquisition processing module is used for acquiring information perception data of a vehicle and extracting landmark information from the information perception data when any vehicle is in a map construction mode; the landmark map module is used for generating a landmark map and a vehicle running track according to information perception data of the vehicle based on the SLAM algorithm; and the comparison matching module is used for comparing the similarity of the overlapping areas, and matching the map constructed in batches through landmark information coordinates of the overlapping areas to form a local or global constructed map.
In this embodiment, the system further comprises a grid map module, detecting a travelable region for a travelable region motion gesture and generating a grid map according to the vehicle travel track and the detected travelable region; when the vehicle runs in different areas of the parking lot, the grid map and the landmark map are circularly constructed, and a local or global construction map is formed.
In this embodiment, the vehicle-mounted map updating system further includes a map data updating unit, configured to compare the constructed map with the vehicle-mounted map, and send updated content to a cloud server of the vehicle-mounted map when the constructed map is updated, so that the constructed map is updated and displayed in the vehicle-mounted map. The map data updating unit can also upload the updated result to the cloud end so as to be convenient for other users to download. From the above, the map construction of the embodiment can realize the instant map construction.
In this embodiment, when the vehicle travels in different areas of the parking lot, the grid map and the landmark map are circularly constructed to form a local or global construction map.
The embodiment of the invention also provides a mobile terminal which comprises the map building system. The above description of the map construction system has been described in detail, and will not be repeated here. The mobile terminal may be, for example, a mobile phone, a PAD, a computer, a server, or the like. In another embodiment, a mobile terminal comprises a processor and a memory, the memory storing program instructions that execute the steps in the method as described above. The mobile terminal is, for example, a smart phone, a vehicle-mounted terminal or the like.
Embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps in the method as described above.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims of this invention, which are within the skill of those skilled in the art, be included within the spirit and scope of this invention.
Claims (9)
1. The method for constructing and updating the map in the overlapping area is characterized by comprising the following steps:
s01: when any vehicle is in a map building mode, acquiring information perception data of the vehicle and extracting landmark information from the information perception data;
s02: generating a landmark map and a vehicle running track according to the motion gesture of the vehicle and the landmark information based on the SLAM algorithm;
s03: comparing the similarity of the overlapping areas for the map constructed in the step S02, wherein when the similarity of the overlapping areas is compared, the map information perceived data constructed in the steps is extracted, the absolute position of the landmark information is judged according to the position, the size and the angle of the landmark information contained in the information perceived data of the map boundary in the image, and two or more maps constructed in the steps are matched according to the absolute position of one or more landmark information, and then are spliced after the matching is successful;
s04: and circularly performing a map construction process to form a local or global map.
2. The method according to claim 1, wherein if a 2D map is created, two or more maps created in batches are matched and spliced according to the absolute positions of three landmark information until a global map is obtained; wherein the three landmark information are not on the same straight line; and if the 3D map is built, matching and splicing two or more maps which are built in batches according to the absolute positions of the four landmark information, wherein the three landmark information is in one dimension, and the other landmark information and the rest three landmark information are in different dimensions.
3. The method according to any one of claims 1 to 2, further comprising comparing the constructed map with a regional model of the same coordinate point or coordinate range of the vehicle map, and if the data are inconsistent, reporting errors by the system; and then identifying whether the change is needed or not according to the deep learning network.
4. A method according to claim 3, further comprising: and comparing the constructed map with the vehicle-mounted map, and when the constructed map is updated, sending updated contents to a cloud server of the vehicle-mounted map and downloading the updated contents so as to update and display the vehicle-mounted map.
5. A system for building and updating a map in an overlapping area, comprising:
the acquisition processing module is used for acquiring information perception data of the vehicles and extracting landmark information from the information perception data when any vehicle is in a map construction mode;
the landmark map module is used for generating a landmark map and a vehicle running track according to information perception data of the vehicle based on the SLAM algorithm;
and the comparison matching module is used for comparing the similarity of the overlapping areas, extracting the map information perceived data constructed in batches when comparing the similarity of the overlapping areas, judging the absolute position of the landmark information according to the position, the size and the angle of the landmark information contained in the information perceived data of the map boundary in the image, matching two or more maps constructed in batches according to the absolute position of one or more landmark information, and forming a local or global constructed map by matching the landmark information coordinates of the overlapping areas with the map constructed in batches.
6. The system according to claim 5, further comprising a map data updating unit configured to compare the constructed map with a vehicle-mounted map, and when the constructed map is updated, send updated content to a cloud server of the vehicle-mounted map, so that the constructed map is updated and displayed in the vehicle-mounted map.
7. The system according to claim 6, further comprising a map changing unit for comparing the constructed map with the region model of the same coordinate point or coordinate range of the vehicle-mounted map, and reporting errors if the data are inconsistent;
and then identifying whether the map is required to be changed or not according to the deep learning network.
8. A mobile terminal, characterized in that it comprises a system according to any of claims 5 to 7.
9. A computer-readable storage medium having stored thereon a computer program, characterized by: the program, when executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710440699.7A CN109086277B (en) | 2017-06-13 | 2017-06-13 | Method, system, mobile terminal and storage medium for constructing map in overlapping area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710440699.7A CN109086277B (en) | 2017-06-13 | 2017-06-13 | Method, system, mobile terminal and storage medium for constructing map in overlapping area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109086277A CN109086277A (en) | 2018-12-25 |
| CN109086277B true CN109086277B (en) | 2024-02-02 |
Family
ID=64838959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710440699.7A Active CN109086277B (en) | 2017-06-13 | 2017-06-13 | Method, system, mobile terminal and storage medium for constructing map in overlapping area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086277B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109959937B (en) * | 2019-03-12 | 2021-07-27 | 广州高新兴机器人有限公司 | Laser radar-based positioning method for corridor environment, storage medium and electronic equipment |
| WO2020190082A1 (en) * | 2019-03-20 | 2020-09-24 | 엘지전자 주식회사 | Method for providing navigation service using mobile terminal, and mobile terminal |
| CN110162040B (en) * | 2019-05-10 | 2022-06-17 | 重庆大学 | A deep learning-based low-speed automatic driving car control method and system |
| CN110412595A (en) * | 2019-06-04 | 2019-11-05 | 深圳市速腾聚创科技有限公司 | Roadbed cognitive method, system, vehicle, equipment and storage medium |
| CN110321398A (en) * | 2019-06-26 | 2019-10-11 | 浙江吉利控股集团有限公司 | A kind of dead space is parked method for building up, device and the terminal of map |
| CN112148742B (en) * | 2019-06-28 | 2024-09-10 | Oppo广东移动通信有限公司 | Map updating method and device, terminal and storage medium |
| CN110634104B (en) * | 2019-09-05 | 2022-11-18 | 北京智行者科技股份有限公司 | Multi-map mosaic method and device |
| CN110704562B (en) * | 2019-09-27 | 2022-07-19 | Oppo广东移动通信有限公司 | Map fusion method and device, device and storage medium |
| CN112785700B (en) * | 2019-11-08 | 2024-09-24 | 华为技术有限公司 | Virtual object display method, global map updating method and equipment |
| CN110986969B (en) * | 2019-11-27 | 2021-12-28 | Oppo广东移动通信有限公司 | Map fusion method and device, equipment and storage medium |
| CN111538918B (en) * | 2020-04-23 | 2022-03-29 | 上海高仙自动化科技发展有限公司 | Recommendation method and device, electronic equipment and storage medium |
| CN112097744B (en) * | 2020-09-16 | 2022-08-30 | 上海遥程信息科技有限公司 | Image scanning method, device, equipment and storage medium for vertical face |
| CN115035728B (en) * | 2020-12-28 | 2024-06-25 | 苏州易航远智智能科技有限公司 | Autonomous parking system and method based on cloud sharing and map fusion |
| CN112836003A (en) * | 2021-02-04 | 2021-05-25 | 广州小鹏自动驾驶科技有限公司 | Map processing method and device |
| CN113506459B (en) * | 2021-06-11 | 2023-03-28 | 上海追势科技有限公司 | Crowdsourcing map acquisition method for underground parking lot |
| CN114862956B (en) * | 2022-07-07 | 2022-09-09 | 中国长江三峡集团有限公司 | Scanning equipment mobile positioning method and system suitable for tunnel construction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207634A (en) * | 2013-03-20 | 2013-07-17 | 北京工业大学 | Data fusion system and method of differential GPS (Global Position System) and inertial navigation in intelligent vehicle |
| DE102013208521A1 (en) * | 2013-05-08 | 2014-11-13 | Bayerische Motoren Werke Aktiengesellschaft | Collective learning of a highly accurate road model |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | A system and method for generating a lane-level navigation map of an unmanned vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8340852B2 (en) * | 2009-04-29 | 2012-12-25 | Honeywell International Inc. | System and method for simultaneous localization and map building |
-
2017
- 2017-06-13 CN CN201710440699.7A patent/CN109086277B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207634A (en) * | 2013-03-20 | 2013-07-17 | 北京工业大学 | Data fusion system and method of differential GPS (Global Position System) and inertial navigation in intelligent vehicle |
| DE102013208521A1 (en) * | 2013-05-08 | 2014-11-13 | Bayerische Motoren Werke Aktiengesellschaft | Collective learning of a highly accurate road model |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | A system and method for generating a lane-level navigation map of an unmanned vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 曹梦龙 ; 崔平远 ; .即时定位与制图辅助的INS/GPS组合导航系统.中国惯性技术学报.2007,(04),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109086277A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086277B (en) | Method, system, mobile terminal and storage medium for constructing map in overlapping area | |
| JP7020728B2 (en) | System, method and program | |
| CN108959321B (en) | Parking lot map construction method, system, mobile terminal and storage medium | |
| CN111902694B (en) | System and method for determining navigation parameters | |
| JP7432285B2 (en) | Lane mapping and navigation | |
| CN111102986B (en) | Automatic generation of reduced-size maps for vehicle navigation and time-space positioning | |
| CN107145578B (en) | Map construction method, device, equipment and system | |
| EP3290952B1 (en) | Automatic localization geometry detection | |
| CN107144285B (en) | Pose information determination method and device and movable equipment | |
| US11086334B2 (en) | Crowdsourcing a sparse map for autonomous vehicle navigation | |
| CN108303103B (en) | Method and device for determining target lane | |
| CN110945320B (en) | Vehicle positioning method and system | |
| JP7477256B2 (en) | SYSTEM AND METHOD FOR OPTIMIZING MAP TILES REQUESTS FOR NAVIGATION - Patent application | |
| US20180024562A1 (en) | Localizing vehicle navigation using lane measurements | |
| CN114729813A (en) | System and method for vehicle navigation | |
| US10782411B2 (en) | Vehicle pose system | |
| US11512975B2 (en) | Method of navigating an unmanned vehicle and system thereof | |
| EP3673407A1 (en) | Automatic occlusion detection in road network data | |
| CN115516277A (en) | Navigating Vehicles Using the Electronic Horizon | |
| US11668573B2 (en) | Map selection for vehicle pose system | |
| JP2023539868A (en) | Map-based real world modeling system and method | |
| CN118836885A (en) | System and method for automatically generating a navigation map | |
| CN117677972A (en) | System and method for road segment drawing | |
| CN115735168A (en) | Control loop for navigating a vehicle | |
| CN114127738A (en) | Automatic map making and positioning |
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 |