CN113506459A - Crowdsourcing map acquisition method for underground parking lot - Google Patents
Crowdsourcing map acquisition method for underground parking lot Download PDFInfo
- Publication number
- CN113506459A CN113506459A CN202110654296.9A CN202110654296A CN113506459A CN 113506459 A CN113506459 A CN 113506459A CN 202110654296 A CN202110654296 A CN 202110654296A CN 113506459 A CN113506459 A CN 113506459A
- Authority
- CN
- China
- Prior art keywords
- map
- parking lot
- nth
- data
- semantic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/0969—Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
-
- 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
Abstract
The invention belongs to the technical field of parking lot map acquisition, and discloses an underground parking lot crowdsourcing map acquisition method, which comprises the following steps: acquiring data information of an Nth area of a parking lot through an Nth acquisition vehicle, and establishing an Nth local map according to the data information of the Nth area; acquiring data information of an N +1 th area of a parking lot by an N +1 th acquisition vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and acquiring positioning information of the N +1 th acquisition vehicle in the N +1 th local map; extracting the motion trail and semantic data identification of the Nth local map and the (N + 1) th local map, and establishing the matching relation of the trail shape and the correlation of the semantic data identification; combining the topological map and the vector semantic map to form a global map; the invention reduces the adaptation time of the new parking lot to the autonomous parking function and accelerates the speed of acquiring the map.
Description
Technical Field
The invention belongs to the technical field of parking lot map acquisition, and particularly relates to a crowdsourcing map acquisition method for an underground parking lot.
Background
The autonomous parking system is used for solving the problem of automatic driving of the vehicle from an entrance of a parking lot to a parking space, and is a defined scene completely unmanned system with level 4. The high-precision map is used as an important data source depending on the automatic driving field, and can effectively assist the autonomous parking system in positioning and path planning. However, most of high-precision map acquisition is usually carried out on the ground at a position which needs to be referenced by a GNSS signal, and the high-precision map is established in an underground parking lot due to the lack of related reference positioning information, the quantity is large, and the links are complex. In the case of an unknown parking lot, the vehicle is likely to get lost. The conventional acquisition method has a long manufacturing period. A plurality of local maps are established by adopting a crowdsourcing method, and the map establishing efficiency of the underground parking lot can be improved by combining the local maps. In addition, the crowdsourcing map can gradually increase the coverage rate of the parking lot, gradually expand the application range of the autonomous parking function in the target parking lot, reduce the workload of professional collection, and achieve the aim of establishing the parking available high-precision map at low cost.
Disclosure of Invention
The invention aims to provide a crowdsourcing map acquisition method for an underground parking lot, which aims to solve the existing problems.
In order to achieve the purpose, the invention provides the following technical scheme: a crowdsourcing map acquisition method for an underground parking lot comprises the following steps:
s100, acquiring data information of an Nth area of a parking lot through an Nth acquisition vehicle, and establishing an Nth local map according to the data information of the Nth area;
s200, acquiring data information of an N +1 th area of a parking lot by an N +1 th acquisition vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and acquiring positioning information of the N +1 th acquisition vehicle in the N +1 th local map;
s300, extracting the motion track of the Nth local map and the (N + 1) th local map and the semantic data identifier, and establishing the matching relation of the track shape and the correlation of the semantic data identifier;
s400, generating a vector semantic map and a topological map according to the matching relation of the track shape and the correlation of the semantic data identification;
s500, combining the topological map and the vector semantic map to form a global map.
Preferably, as a method for collecting a crowdsourcing map of an underground parking lot according to the present invention, the nth collection vehicle and the (N + 1) th collection vehicle both start data collection from an entrance of the parking lot.
Preferably, the data information includes ground target detection data, obstacle detection data, OCR detection data, and vehicle cruising track data.
Preferably, the ground detection data comprises ground identification lines and characters, road arrows, parking spaces, parking lot numbers and deceleration strips;
the obstacle detection data comprises crossing gates, road edges, stand columns, lamp posts, advertising boards and road piles;
the OCR detection data comprises numbers, English and partial Chinese characters;
the vehicle cruise track data includes almanac information and inertial navigation unit information.
Preferably, as an acquisition method of a crowd-sourced map for an underground parking lot, in S100, data information of an nth area of the parking lot is acquired by an nth acquisition vehicle, and after an nth local map is established according to the data information of the nth area, the method includes:
s110, the Nth local map is sent to a cloud.
Preferably, in S200, the method for collecting the crowdsourcing map of the underground parking lot includes the steps of collecting data information of an N +1 th area of the parking lot by an N +1 th collection vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and acquiring positioning information of the N +1 th collection vehicle in the N +1 th local map, and then:
s210, the (N + 1) th local map and the positioning information are sent to a cloud.
As an advantageous method for collecting the crowdsourcing map of the underground parking lot, the step of combining the topological map and the vector semantic map to form a global map in S500 includes:
s600, the global map is sent to a cloud end, all vehicles are synchronized, and map updating is completed.
Preferably, the S400 generates the vector semantic map and the topological map according to the matching relationship of the track shape and the association of the semantic data identifier, and specifically includes the steps of:
s410, merging the (N + 1) th local map into the Nth local map based on the correlation of the semantic data identifier, and modifying vector information to obtain the vector semantic map;
and S420, fusing the matching relation of the track shapes to generate the topological map.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the underground parking lot map for autonomous parking is generated based on a low-cost crowdsourcing acquisition mode, and vehicle-end operation resources are utilized in the process of acquiring a local map, so that the resources for acquiring data transmission are reduced; the map is acquired in an incremental mode, so that the adaptation time of a new parking lot to the autonomous parking function is shortened, and the map acquisition speed is increased.
Drawings
FIG. 1 is a flow chart N of the present invention;
FIG. 2 is a flow chart of N +1 according to the present invention;
FIG. 3 is a third flow chart of the present invention;
FIG. 4 is a fourth flowchart of the present invention;
FIG. 5 is a fifth flowchart of the present invention;
FIG. 6 is a block diagram of a parking lot local map data collected in a crowd-sourced manner in accordance with the present invention;
fig. 7 is a complete parking lot map generated by combining the partial maps according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides the following technical solutions: a crowdsourcing map acquisition method for an underground parking lot comprises the following steps:
s100, acquiring data information of an Nth area of a parking lot through an Nth acquisition vehicle, and establishing an Nth local map according to the data information of the Nth area;
s200, acquiring data information of an N +1 th area of a parking lot by an N +1 th acquisition vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and acquiring positioning information of the N +1 th acquisition vehicle in the N +1 th local map;
s300, extracting the motion track of the Nth local map and the (N + 1) th local map and the semantic data identifier, and establishing the matching relation of the track shape and the correlation of the semantic data identifier;
s400, generating a vector semantic map and a topological map according to the matching relation of the track shape and the correlation of the semantic data identification;
s500, combining the topological map and the vector semantic map to form a global map.
It is to be noted that N is 1 or more.
In the embodiment, data information of a first area of a parking lot is collected through a first collection vehicle, and a first local map is established according to the data information of the first area; acquiring data information of a second area of the parking lot through a second acquisition vehicle, establishing a second local map according to the data information of the second area, and acquiring positioning information of the second acquisition vehicle in the first local map; extracting the marks of the motion tracks of the first local map and the second local map and semantic data, and establishing the matching relation of track shapes and the correlation of the semantic data marks; generating a vector semantic map and a topological map according to the matching relation of the track shape and the correlation of the semantic data identification; and combining the topological map and the vector semantic map to form a global map.
In this embodiment, an initial map is needed in a scene established by the crowdsourcing map, an nth vehicle entering a target parking lot is used as an I-th collection vehicle (subsequently, a II-th collection vehicle, a III-th collection vehicle, and the like), and data collection is started from a ground entrance of the parking lot. The vehicle cruise control system comprises ground target detection data (such as ground identification lines and characters, road arrows, parking spaces, parking lot position numbers, speed bumps and the like), obstacle detection data (such as intersection gates, road edges, stand columns, lamp posts, advertising boards, road posts and the like), OCR detection data (including numbers, English and partial Chinese characters), and vehicle cruise track data (mileometers and inertial navigation units). And a small-area local map I in the underground parking lot can be obtained based on the detection result, and the map I is sent to the cloud.
Since the initial map collection range cannot cover the complete parking lot, the second vehicle is used for expanding a new map on the basis of the map I. In addition to collecting raw inspection data (refer to step 1), positioning information of the vehicle II in the map I is collected at the same time. And forming a local map II based on the detection result, and sending the map II and the positioning information to the cloud.
In the map I and the map II, a plurality of overlapped scene target information exists, such as parking spaces with the same stock space number, obstacles with the same identification characters and similar track segments in a driving path, and the association between the two map identifiers can be established through the information.
And establishing a constraint relation based on the correlation information, and correcting the track result and the position of the map target by a map optimization method. And reforming vectorized semantic information through the corrected result to obtain merged vector semantic map data.
After the maps are combined, the original tracks are overlapped on a map coordinate system, and track points are aggregated and combined with a track thinning algorithm to obtain fewer track points by a distance clustering method. And connecting the track points to form a topological map, and performing navigation planning. And combining the topological map and the semantic map to obtain a final combined map. And the merged map is issued to the cloud and is synchronized to all vehicles to complete map updating.
Specifically, the nth collection vehicle and the (N + 1) th collection vehicle start data collection from an entrance of a parking lot.
Specifically, the data information includes ground target detection data, obstacle detection data, OCR detection data, vehicle cruise track data.
Specifically, the ground detection data comprises ground identification lines and characters, road arrows, parking spaces, parking lot numbers and deceleration strips;
the obstacle detection data comprises crossing gates, road edges, stand columns, lamp posts, advertising boards and road piles;
the OCR detection data comprises numbers, English and partial Chinese characters;
the vehicle cruise track data includes almanac information and inertial navigation unit information.
Referring to fig. 2, specifically, after the step S100 of acquiring data information of an nth area of a parking lot by an nth acquisition vehicle, and establishing an nth local map according to the data information of the nth area, the method includes the steps of:
s110, the Nth local map is sent to a cloud.
Referring to fig. 3, specifically, in S200, acquiring data information of an N +1 th area of a parking lot by an N +1 th collection vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and after acquiring positioning information of the N +1 th collection vehicle in the N +1 th local map, the method includes the steps of:
s210, the (N + 1) th local map and the positioning information are sent to a cloud.
Referring to fig. 4, specifically, after the S500 combines the topological map and the vector semantic map to form a global map, the method includes the steps of:
s600, the global map is sent to a cloud end, all vehicles are synchronized, and map updating is completed.
Referring to fig. 5, specifically, the step S400 of generating the vector semantic map and the topological map according to the matching relationship of the track shape and the association of the semantic data identifier specifically includes the steps of:
s410, merging the (N + 1) th local map into the Nth local map based on the correlation of the semantic data identifier, and modifying vector information to obtain the vector semantic map;
and S420, fusing the matching relation of the track shapes to generate the topological map.
In this embodiment, the crowdsourcing high-precision map established through the above steps can meet the requirements of autonomous parking on the high-precision map and positioning for a specific parking lot, and mainly includes: the map can provide requirements for path planning within the parking lot; the map can meet the requirement of positioning in the range of the parking lot; and the above requirements can be met by multi-vehicle incremental acquisition in the same N parking lots.
Referring to fig. 6 and 7, another N embodiments of the present invention provide a high-precision map for autonomous parking, which is based on semantic detection and crowd-sourced collection to establish an overbridge, sky, and underground parking lot, and includes the following steps:
s1, the 1 st vehicle enters the target parking lot from the ground and collects a local map I;
s2, after loading the local map I, the 2 nd and 3 rd vehicles enter the parking lot to drive different routes II and III; specifically, a partial map of 3 vehicles is shown in fig. 6.
S3, establishing a crowdsourcing high-precision map;
and S4, based on the generated high-precision map, realizing the autonomous parking function of the underground parking lot, including autonomous cruising, parking space searching and automatic parking.
According to the invention, map data are acquired in a low-cost crowdsourcing mode and are updated in an incremental manner, so that autonomous parking and navigation are satisfied; the problem of large-scale map building of an underground parking lot is solved, and the problem that a plurality of maps cannot be aligned due to lack of GNSS is solved; the problem that a lot of manual later-period adjustment operations are needed when the map is frequently collected by the parking lot is solved, and the map updating efficiency is improved; the local map is calculated by utilizing the calculation resources of the vehicle, so that the data transmission flow is reduced, and the calculation amount of cloud map combination is simplified.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A crowdsourcing map acquisition method for an underground parking lot is characterized by comprising the following steps:
s100, acquiring data information of an Nth area of a parking lot through an Nth acquisition vehicle, and establishing an Nth local map according to the data information of the Nth area;
s200, acquiring data information of an N +1 th area of a parking lot by an N +1 th acquisition vehicle, establishing an N +1 th local map according to the data information of the N +1 th area, and acquiring positioning information of the N +1 th acquisition vehicle in the N +1 th local map;
s300, extracting the motion track of the Nth local map and the (N + 1) th local map and the semantic data identifier, and establishing the matching relation of the track shape and the correlation of the semantic data identifier;
s400, generating a vector semantic map and a topological map according to the matching relation of the track shape and the correlation of the semantic data identification;
s500, combining the topological map and the vector semantic map to form a global map.
2. The method as claimed in claim 1, wherein the nth and the (N + 1) th collection vehicles both start data collection from an entrance of a parking lot.
3. The method as claimed in claim 2, wherein the data information includes ground target detection data, obstacle detection data, OCR detection data, vehicle cruise track data.
4. The method for collecting the crowdsourcing map of the underground parking lot according to claim 3, wherein:
the ground detection data comprises ground identification lines and characters, road arrows, parking spaces, parking lot numbers and deceleration strips;
the obstacle detection data comprises crossing gates, road edges, stand columns, lamp posts, advertising boards and road piles;
the OCR detection data comprises numbers, English and partial Chinese characters;
the vehicle cruise track data includes almanac information and inertial navigation unit information.
5. The method as claimed in claim 1, wherein the step S100 of collecting data information of an nth area of the parking lot by an nth collection vehicle, and after the nth local map is built according to the data information of the nth area, includes:
s110, the Nth local map is sent to a cloud.
6. The method as claimed in claim 1, wherein in S200, the step of collecting data information of an N +1 th region of the parking lot by an N +1 th collection vehicle, the step of creating an N +1 th local map according to the data information of the N +1 th region, and the step of obtaining the positioning information of the N +1 th collection vehicle in the N th local map includes:
s210, the (N + 1) th local map and the positioning information are sent to a cloud.
7. The method for collecting the crowdsourcing map of the underground parking lot according to claim 1, wherein after the step S500 of combining the topological map and the vector semantic map to form a global map, the method comprises the steps of:
s600, the global map is sent to a cloud end, all vehicles are synchronized, and map updating is completed.
8. The method for collecting the crowdsourcing map of the underground parking lot according to claim 1, wherein the step S400 of generating the vector semantic map and the topological map according to the matching relationship of the track shape and the association of the semantic data identifier specifically comprises the steps of:
s410, merging the (N + 1) th local map into the Nth local map based on the correlation of the semantic data identifier, and modifying vector information to obtain the vector semantic map;
and S420, fusing the matching relation of the track shapes to generate the topological map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110654296.9A CN113506459B (en) | 2021-06-11 | 2021-06-11 | Crowdsourcing map acquisition method for underground parking lot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110654296.9A CN113506459B (en) | 2021-06-11 | 2021-06-11 | Crowdsourcing map acquisition method for underground parking lot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113506459A true CN113506459A (en) | 2021-10-15 |
| CN113506459B CN113506459B (en) | 2023-03-28 |
Family
ID=78010245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110654296.9A Active CN113506459B (en) | 2021-06-11 | 2021-06-11 | Crowdsourcing map acquisition method for underground parking lot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506459B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114690769A (en) * | 2022-03-07 | 2022-07-01 | 美的集团(上海)有限公司 | Path planning method, electronic device, storage medium and computer program product |
| CN114937369A (en) * | 2022-04-06 | 2022-08-23 | 福思(杭州)智能科技有限公司 | Autonomous valet parking method, system, vehicle, parking lot terminal, device and medium |
| CN114690769B (en) * | 2022-03-07 | 2024-05-10 | 美的集团(上海)有限公司 | Path planning method, electronic device, storage medium and computer program product |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053679A (en) * | 2017-12-05 | 2018-05-18 | 北京千方城市信息科技有限公司 | A kind of parking position guiding method and system based on crowdsourcing data |
| CN109086277A (en) * | 2017-06-13 | 2018-12-25 | 纵目科技（上海）股份有限公司 | A kind of overlay region building ground drawing method, system, mobile terminal and storage medium |
| CN109086278A (en) * | 2017-06-13 | 2018-12-25 | 纵目科技（上海）股份有限公司 | A kind of map constructing method, system, mobile terminal and storage medium for eliminating error |
| CN109141443A (en) * | 2017-06-16 | 2019-01-04 | 纵目科技（上海）股份有限公司 | The localization method and system of perception data are acquired according to mobile terminal |
| CN110599570A (en) * | 2019-09-17 | 2019-12-20 | 武汉中海庭数据技术有限公司 | Map generation method and system based on crowdsourcing data open scene |
| CN110704563A (en) * | 2019-09-27 | 2020-01-17 | Oppo广东移动通信有限公司 | Map fusion method and device, equipment and storage medium |
| CN110914888A (en) * | 2017-11-22 | 2020-03-24 | 咪酷维亚科技有限公司 | Map information processing device, map information processing method, and map information processing program |
| DE102018219220A1 (en) * | 2018-11-12 | 2020-05-14 | Robert Bosch Gmbh | Creation and updating of maps in the off-street area |
| US20200201890A1 (en) * | 2018-12-21 | 2020-06-25 | Here Global B.V. | Method, apparatus, and computer program product for building a high definition map from crowd sourced data |
| CN111462521A (en) * | 2019-10-15 | 2020-07-28 | 杭州海康威视系统技术有限公司 | Parking lot map determination method, device and equipment and storage medium |
| US20200334985A1 (en) * | 2019-04-22 | 2020-10-22 | Baidu Usa Llc | Parking management architecture for parking autonomous driving vehicles |
| WO2021057745A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Map fusion method and apparatus, device and storage medium |
| CN112632310A (en) * | 2020-12-29 | 2021-04-09 | 苏州物图科技有限公司 | High-precision map construction method for indoor parking lot |
| 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 |
-
2021
- 2021-06-11 CN CN202110654296.9A patent/CN113506459B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086277A (en) * | 2017-06-13 | 2018-12-25 | 纵目科技（上海）股份有限公司 | A kind of overlay region building ground drawing method, system, mobile terminal and storage medium |
| CN109086278A (en) * | 2017-06-13 | 2018-12-25 | 纵目科技（上海）股份有限公司 | A kind of map constructing method, system, mobile terminal and storage medium for eliminating error |
| CN109141443A (en) * | 2017-06-16 | 2019-01-04 | 纵目科技（上海）股份有限公司 | The localization method and system of perception data are acquired according to mobile terminal |
| CN110914888A (en) * | 2017-11-22 | 2020-03-24 | 咪酷维亚科技有限公司 | Map information processing device, map information processing method, and map information processing program |
| CN108053679A (en) * | 2017-12-05 | 2018-05-18 | 北京千方城市信息科技有限公司 | A kind of parking position guiding method and system based on crowdsourcing data |
| DE102018219220A1 (en) * | 2018-11-12 | 2020-05-14 | Robert Bosch Gmbh | Creation and updating of maps in the off-street area |
| US20200201890A1 (en) * | 2018-12-21 | 2020-06-25 | Here Global B.V. | Method, apparatus, and computer program product for building a high definition map from crowd sourced data |
| US20200334985A1 (en) * | 2019-04-22 | 2020-10-22 | Baidu Usa Llc | Parking management architecture for parking autonomous driving vehicles |
| CN110599570A (en) * | 2019-09-17 | 2019-12-20 | 武汉中海庭数据技术有限公司 | Map generation method and system based on crowdsourcing data open scene |
| CN110704563A (en) * | 2019-09-27 | 2020-01-17 | Oppo广东移动通信有限公司 | Map fusion method and device, equipment and storage medium |
| WO2021057745A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Map fusion method and apparatus, device and storage medium |
| CN111462521A (en) * | 2019-10-15 | 2020-07-28 | 杭州海康威视系统技术有限公司 | Parking lot map determination method, device and equipment and storage medium |
| CN112632310A (en) * | 2020-12-29 | 2021-04-09 | 苏州物图科技有限公司 | High-precision map construction method for indoor parking lot |
| 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 |
Non-Patent Citations (5)
| Title |
|---|
| HANGBINWU ET AL.: "Automatic structural mapping and semantic optimization from indoor point clouds。", 《AUTOMATION IN CONSTRUCTION》 * |
| TONG QIN ET AL.: "AVP-SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot", 《2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)》 * |
| 曹文冠等: "面向地下停车场的无人车视觉语义建图与定位", 《智能计算机与应用》 * |
| 蒋民锋: "地下停车场出入口众包构建方法及应用探析", 《现代信息科技》 * |
| 蒋民锋;: "地下停车场出入口众包构建方法及应用探析" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114690769A (en) * | 2022-03-07 | 2022-07-01 | 美的集团(上海)有限公司 | Path planning method, electronic device, storage medium and computer program product |
| CN114690769B (en) * | 2022-03-07 | 2024-05-10 | 美的集团(上海)有限公司 | Path planning method, electronic device, storage medium and computer program product |
| CN114937369A (en) * | 2022-04-06 | 2022-08-23 | 福思(杭州)智能科技有限公司 | Autonomous valet parking method, system, vehicle, parking lot terminal, device and medium |
| CN114937369B (en) * | 2022-04-06 | 2023-04-04 | 福思(杭州)智能科技有限公司 | Autonomous agent parking method, system, vehicle, parking lot end, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113506459B (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11435194B2 (en) | Scaffolds for globally consistent maps | |
| Bresson et al. | Simultaneous localization and mapping: A survey of current trends in autonomous driving | |
| JP5064870B2 (en) | Digital road map generation method and map generation system | |
| JP6197393B2 (en) | Lane map generation device and program | |
| KR20200121274A (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| EP1975563B1 (en) | Feature information collecting apparatus and feature information collecting method | |
| CN109709593A (en) | Join automobile mounted terminal platform based on " cloud-end " tightly coupled intelligent network | |
| CN106568456B (en) | Non-stop charging method based on GPS/ Beidou positioning and cloud computing platform | |
| Li et al. | Lane-level map-matching with integrity on high-definition maps | |
| CN105371857A (en) | Device and method for constructing road network topology based on bus GNSS space-time tracking data | |
| CN111739323B (en) | Method and device for acquiring intersection information | |
| US20200193170A1 (en) | Determining Position Data | |
| CN109086278A (en) | A kind of map constructing method, system, mobile terminal and storage medium for eliminating error | |
| CN105096590A (en) | Traffic information generation method and device | |
| CN114509065A (en) | Map construction method, map construction system, vehicle terminal, server side and storage medium | |
| CN113506459B (en) | Crowdsourcing map acquisition method for underground parking lot | |
| CN109816982A (en) | Virtual networks non-motorized lane attribute modification method based on shared bicycle track | |
| CN112530158A (en) | Road network supplementing method based on historical track | |
| CN115344655A (en) | Method and device for finding change of feature element, and storage medium | |
| CN105427592A (en) | Electronic navigation map turning cost calculation method based on floating car | |
| Ibrahim et al. | High definition LiDAR mapping of perth CBD | |
| CN115046542A (en) | Map generation method, map generation device, terminal device and storage medium | |
| CN113155144B (en) | Automatic driving method based on high-precision map real-time road condition modeling | |
| CN114120631B (en) | Method and device for constructing dynamic high-precision map and traffic cloud control platform | |
| WO2022021209A9 (en) | Electronic map generation method and apparatus, computer device, and storage medium |
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 |