CN110543473A - Crowdsourcing data fusion optimization method and device and storage medium - Google Patents
Crowdsourcing data fusion optimization method and device and storage medium Download PDFInfo
- Publication number
- CN110543473A CN110543473A CN201910770521.8A CN201910770521A CN110543473A CN 110543473 A CN110543473 A CN 110543473A CN 201910770521 A CN201910770521 A CN 201910770521A CN 110543473 A CN110543473 A CN 110543473A
- Authority
- CN
- China
- Prior art keywords
- track
- point
- traffic sign
- speed
- low
- 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
Classifications
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
Abstract
The invention relates to a crowdsourcing data fusion optimization method, a crowdsourcing data fusion optimization device and a storage medium. The method comprises the following steps: acquiring crowdsourcing data of the same area, and extracting specific data in the crowdsourcing data to form an observation data table; splicing the observation data tables, performing label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values for the same traffic sign entity; predicting a second track point according to the track motion equation and the first track point; optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point; and optimizing the position of the traffic sign according to a coslam graph optimization process based on the association between the optimized track point and the traffic sign. By the scheme, the optimization process of the vehicle track and the traffic sign position can be simplified, the calculation amount and the bandwidth requirement are reduced, and the load of a server is reduced.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to a crowdsourcing data fusion optimization method, a crowdsourcing data fusion optimization device and a storage medium.
background
in the field of automatic driving, in order to accurately control the driving of a vehicle, a high-precision map is often required to be drawn, the cost of drawing a collection vehicle to be used is high, and the requirement for collecting the vehicle is correspondingly increased for the high-precision map in a large area. Therefore, with the help of crowdsourcing of multi-vehicle data, multiple batches of multiple vehicles are collected in the same area or different areas, and the collection cost can be effectively reduced.
the crowdsourcing data acquired by multiple vehicles has different precision, the accuracy is difficult to guarantee, and the slam (synchronous positioning in map construction) data of the multiple vehicles needs to be optimized. However, if the data uploaded by multiple vehicles is optimized directly, the requirements on bandwidth and storage space are high, and at the same time, the load of the server is excessive.
disclosure of Invention
In view of this, embodiments of the present invention provide a crowdsourcing data fusion optimization method, apparatus and storage medium, which can effectively reduce server load and reduce resource requirements.
in a first aspect of the embodiments of the present invention, a method for optimizing crowdsourcing data fusion is provided, including:
acquiring crowdsourcing data of a preset area, and extracting specific data in the crowdsourcing data to form an observation data table, wherein the specific data comprises traffic sign position information, vehicle track information and an incidence relation between the vehicle track information and the traffic sign position information;
splicing the observation data tables, carrying out label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values for the same traffic sign entity;
Predicting a second track point according to the track motion equation and the first track point;
Optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point;
And optimizing the position of the traffic sign according to a coslam graph optimization process based on the association between the optimized track point and the traffic sign.
in a second aspect of the embodiments of the present invention, there is provided a crowdsourced data fusion optimization device, including:
The system comprises an extraction module, a position acquisition module and a display module, wherein the extraction module is used for acquiring crowdsourcing data of a preset area, extracting specific data in the crowdsourcing data to form an observation data table, and the specific data comprises traffic sign position information, vehicle track information and an incidence relation between the vehicle track information and the traffic sign position information;
the splicing module is used for splicing the observation data tables, performing label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values of the same traffic sign entity;
The prediction module is used for predicting the second track point according to the track motion equation and the first track point;
the first optimization module is used for optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point;
And the second optimization module is used for optimizing the position of the traffic sign according to the coslam graph optimization process based on the association between the optimized track point and the traffic sign.
In a third aspect of the embodiments of the present invention, there is provided an apparatus, including a memory, a processor, and a computer program stored in the memory and executable by the processor, where the processor executes the computer program to implement the steps of the method according to the first aspect of the embodiments of the present invention.
in a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which stores a computer program, which when executed by a processor implements the steps of the method provided by the first aspect of the embodiments of the present invention.
In a fifth aspect of embodiments of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by one or more processors, performs the steps of the method provided in the first aspect of embodiments of the present invention.
In the embodiment of the invention, a data table is formed by track information and traffic sign information acquired by a plurality of vehicles, the data tables of different vehicles in different areas are spliced, the spliced data tables are clustered uniformly, each category is used as observation of the same traffic sign, track points are optimized through a g2o diagram based on a track motion equation, and then the positions of the traffic signs are optimized through coslam based on the observation of the traffic signs by track points. Direct realization is fused the crowdsourcing data of multizone through the data sheet concatenation, optimizes track point and traffic sign respectively according to the error of deduction value and actual value again to avoid traditional direct upload back, slam rear end optimization needs complicated matrix transformation and signpost pixel coordinate to acquire, can reduce bandwidth and calculated amount demand, alleviates server load. Meanwhile, the vehicle track and the traffic sign position are accurately determined, and accurate and reliable reference basis is provided for subsequent map construction.
drawings
Fig. 1 is a schematic flow chart of a crowdsourcing data fusion optimization method according to an embodiment of the present invention;
Fig. 2 is another schematic diagram of a crowdsourced data fusion optimization method according to an embodiment of the present invention;
Fig. 3 is another schematic diagram of a crowdsourced data fusion optimization method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a crowdsourcing data fusion optimization device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a crowdsourcing data fusion optimization method, a device and a storage medium, which are used for fusing and optimizing crowdsourcing data uploaded by multiple vehicles.
in order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
referring to fig. 1, a schematic flow chart of a crowdsourcing data fusion optimization method according to an embodiment of the present invention includes:
s101, crowdsourcing data of a preset area is obtained, specific data in the crowdsourcing data are extracted to form an observation data table, and the specific data comprise traffic sign position information, vehicle track information and an incidence relation between the vehicle track information and the traffic sign position information;
The crowdsourcing data is data collected by a collection vehicle in a predetermined area, in this embodiment, the crowdsourcing data at least includes collected vehicle trajectory information and traffic sign information, trajectory parameters in the vehicle trajectory information may include a position, a speed, a heading angle, and the like, the traffic sign information may include observation information of a traffic sign, a traffic sign position, and the like, and may also include a traffic sign type, which is not limited herein. The traffic signs are traffic sign boards, such as speed limit signs, turning signs, signal lamps and the like.
the observation data table is composed of specific data in crowdsourcing data, is formed by actually collecting data, can be used for separately forming a data table for crowdsourcing collection data of different collection vehicles, different areas or different collection batches, and different types of data in the data table are provided with corresponding type identifications and IDs.
S102, splicing the observation data tables, carrying out label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values of the same traffic sign entity;
For example, the maximum value of the corresponding ID in the spliced data table can be added to the ID of the traffic sign and the ID of the track point in the spliced data table, so as to prevent the IDs from being duplicated.
And (3) obtaining a plurality of data sets by tag-free clustering on the spliced observation data table, wherein the tag-free clustering is to remove data type tags, and data clusters in a plurality of different ranges can be obtained according to the characteristics of multi-vehicle and multi-batch data.
For a range of data clusters, it can be used as multiple observations of the same traffic sign. The same traffic sign entity is the actually observed traffic sign, such as a signal light. The observed value may include a timestamp of the observed traffic sign entity, a traffic sign distance and a location, and the like.
s103, predicting a second track point according to the track motion equation and the first track point;
the track motion equation is an object motion equation, the motion process of an object can be calculated according to the object motion law, and the first track point and the second track point are both adjacent track points in the same motion track.
Specifically, first track point and second track point are two track points adjacent according to gathering vehicle direction of travel in the same track line, just contain the track point position in first track point and the second track point at least, the instantaneous speed of track point and the course angle of track point.
Illustratively, the trajectory information of each vehicle is parameterized as (px, py, vx, vy, θ), which respectively represent the position coordinates of the trajectory in the x and y directions of the coordinate axis, the speed in the x and y directions, and the heading angle of the vehicle motion. Assuming that the motion parameter moves from the k-th time to the k + 1-th time, the motion parameter at the k + 1-th time can be estimated by using the motion parameter at the k-th time, and specifically, the motion parameter is calculated by the following five formulas:
And calculating the predicted value of the trace point at the k +1 th moment according to a formula, wherein the predicted value is represented by five motion parameters. Further, the trajectory parameter at the time k may be used as a first trajectory, and the predicted value at the time k +1 may be used as a second trajectory predicted value.
s104, optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point;
And the actual observed value corresponding to the second track point in the corresponding motion track can be obtained by the observation data table, and a calculation function of the error can be obtained by combining the error between the predicted value and the observed value of the second track point in the plurality of tracks.
the g2o graph is optimized to be a graph optimization framework, and the parameters of the trace points can be optimized through iterative computation according to the initial trace points and the error function.
optionally, track points with the instantaneous speed smaller than a predetermined threshold value in the vehicle track information are obtained, and the track points smaller than the predetermined threshold value are added to the low-speed point set;
And normalizing the low-speed point set to form a low-speed aggregation point, and deleting all track points in the low-speed point set.
Preferably, the low-speed aggregation point position is set as an average value of all track points in the low-speed point set, the instantaneous speed of the low-speed aggregation point is 0, and the heading angle of the low-speed aggregation point is set as an average value of all heading angles in the low-speed point set.
As shown in fig. 2, fig. 2 is a schematic diagram of the low-speed trace point optimization process, for a low-speed point set in the trace line 20, first, given a speed threshold, a continuous series of low-speed points lower than the threshold are added into one set, and a plurality of continuous low-speed point sets can be obtained. The time interval of the preceding node associated with each set of consecutive slow points and the first slow point and the time interval of the subsequent node and the last slow point are recorded. Then, points in each low-speed point set can be normalized to form a low-speed aggregation point 201, all the low-speed points are deleted from the track sequence, and the position of the low-speed aggregation point is the average value of all track points in the low-speed point set, the instantaneous speed of the low-speed aggregation point is 0, and the heading angle of the low-speed aggregation point is the average value of all heading angles in the low-speed point set. Finally, the time interval between the low-speed aggregation point 201 and the preamble node is set as the time interval between the first low-speed aggregation point and the preamble node; the time interval between the low-speed aggregation point 201 and the subsequent node is set to the time interval between the last low-speed point and the subsequent node. The low-speed point processing process can be performed before or after track point optimization.
and S105, optimizing the position of the traffic sign according to the coslam graph optimization process based on the association between the optimized track point and the traffic sign.
The method comprises the steps of acquiring track points which can observe the traffic signs in vehicle tracks, associating the track points with the traffic signs, and solving the positions of the traffic signs according to the observation data of the track points on the traffic signs.
Based on the incidence relation between the track points before optimization and the traffic signs, the incidence relation between the track points after optimization and the traffic signs can be obtained.
Specifically, the traffic sign positions when the same traffic sign entity is observed in different vehicle tracks are obtained, and the average value of the traffic sign positions is obtained; taking the observed track points corresponding to the same traffic sign and the position of the traffic sign as vertexes, and taking the distance between the corresponding track points and the average value of the positions of the traffic sign as the pre-estimation of the value of a connecting edge between the two vertexes; and taking the actual distance of the same traffic sign entity observed by the corresponding track points as an observed value, calculating the error between the estimated value and the observed value, and optimizing the position of the traffic sign through coslam graph optimization.
As shown in fig. 3, fig. 3 is a schematic diagram of a traffic sign position optimization process, where a track point is used as a vertex of the diagram, namely a track vertex 31, and a traffic sign is used as another vertex, namely a traffic sign vertex 32. Preferably, the track points associated with the traffic signs can be numbered according to the time sequence, the numbers are used as track point IDs, meanwhile, the non-label clustering result IDs are used as the same traffic sign entity IDs, and the setting of the marks on the track points and the traffic signs can be conveniently optimized. Connecting lines are arranged between the two vertexes, the distance from the track point to the average value of the position of the traffic sign is used as the prediction of the value of the connecting edge in 301, further, the actual distance is used as an observed value in combination with 302, the connecting edge is optimized according to the error of the observed value and the predicted value, and then the position of the traffic sign is optimized based on graph optimization.
it should be noted that the tracks observed by different track points on the same traffic sign entity are optimized track points. And taking the error between the estimated value observed by the optimized track point to the traffic sign and the actual observed value as an optimization parameter, and combining a plurality of optimization parameters to optimize and adjust the position of the traffic sign.
Compared with the traditional method for directly uploading crowdsourced data, the method provided by the embodiment is complex in calculation and large in data transmission bandwidth because the slam process of the server needs to be based on continuous rotation and translation matrix transformation and pixel coordinate information observed by the traffic sign, is based on the fused data table, optimizes the track point and the traffic sign through g2o diagram optimization and coslam processes, is simple, can effectively reduce the calculation amount, and reduces the load of the server.
example two:
fig. 4 is a schematic structural diagram of a crowdsourced data fusion optimization device provided in the second embodiment of the present invention, including:
An extracting module 410, configured to obtain crowdsourcing data of a predetermined area, and extract specific data in the crowdsourcing data to form an observation data table, where the specific data includes traffic sign position information, vehicle trajectory information, and an association relationship between the vehicle trajectory information and the traffic sign position information;
The splicing module 420 is configured to splice the observation data tables, perform label-free clustering on the spliced observation data tables, and use a category corresponding to each cluster as a group of observation values for the same traffic sign entity;
The prediction module 430 is configured to predict the second trajectory point according to the trajectory motion equation and the first trajectory point;
Optionally, the first track point and the second track point are two adjacent track points in the same track line according to the driving direction of the collected vehicle, and the first track point and the second track point at least comprise track point positions, the instantaneous speed of the track points and the course angle of the track points.
the first optimization module 440 is configured to optimize the track points in the vehicle track information based on the g2o diagram optimization technology according to the error between the predicted value and the actual observed value of the second track point;
optionally, the first optimization module 440 further includes:
the low-speed point processing module is used for acquiring track points of which the instantaneous speed is less than a preset threshold value in the vehicle track information and adding the track points of which the instantaneous speed is less than the preset threshold value to the low-speed point set;
And normalizing the low-speed point set to form a low-speed aggregation point, and deleting all track points in the low-speed point set.
Optionally, the normalizing the low-speed point set to form the low-speed aggregation point further includes:
And setting the low-speed aggregation point position as the average value of all track points in the low-speed point set, setting the instantaneous speed of the low-speed aggregation point to be 0, and setting the course angle of the low-speed aggregation point to be the average value of all course angles in the low-speed point set.
and a second optimization module 450, configured to optimize the positions of the traffic signs according to a coslam graph optimization process based on the association between the optimized track points and the traffic signs.
optionally, the optimizing the position of the traffic sign according to the coslam graph optimization process based on the association between the optimized track point and the traffic sign specifically includes:
acquiring traffic sign positions when the same traffic sign entity is observed in different vehicle tracks, and taking an average value of the traffic sign positions;
taking the observed track points corresponding to the same traffic sign and the position of the traffic sign as vertexes, and taking the distance between the corresponding track points and the average value of the positions of the traffic sign as the pre-estimation of the value of a connecting edge between the two vertexes;
and taking the actual distance of the same traffic sign entity observed by the corresponding track points as an observed value, calculating the error between the estimated value and the observed value, and optimizing the position of the traffic sign through coslam graph optimization.
Through the device of this embodiment, crowdsourcing data optimization calculation can be simplified, and bandwidth and storage space occupation can be reduced based on the optimization processes in the first optimization module and the second optimization module.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
it will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by a program to instruct associated hardware, where the program may be stored in a computer-readable storage medium, and when the program is executed, the program includes steps S101 to S105, where the storage medium includes, for example: ROM/RAM, magnetic disk, optical disk, etc.
the above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. a crowdsourced data fusion optimization method is characterized by comprising the following steps:
acquiring crowdsourcing data of a preset area, and extracting specific data in the crowdsourcing data to form an observation data table, wherein the specific data comprises traffic sign position information, vehicle track information and an incidence relation between the vehicle track information and the traffic sign position information;
Splicing the observation data tables, carrying out label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values for the same traffic sign entity;
Predicting a second track point according to the track motion equation and the first track point;
Optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point;
and optimizing the position of the traffic sign according to a coslam graph optimization process based on the association between the optimized track point and the traffic sign.
2. the method according to claim 1, wherein the first track point and the second track point are two track points adjacent to each other in the same track line according to the collected vehicle traveling direction, and the first track point and the second track point at least comprise a track point position, an instantaneous speed of the track point and a course angle of the track point.
3. The method according to claim 1, wherein optimizing the trajectory points in the vehicle trajectory information based on the g2o graph optimization technique based on the error between the predicted value and the actual observed value of the second trajectory point further comprises:
Obtaining track points of which the instantaneous speed is smaller than a preset threshold value in the vehicle track information, and adding the track points smaller than the preset threshold value to a low-speed point set;
And normalizing the low-speed point set to form a low-speed aggregation point, and deleting all track points in the low-speed point set.
4. the method of claim 3, wherein the normalizing the set of low-speed points to form a low-speed aggregate point further comprises:
And setting the low-speed aggregation point position as the average value of all track points in the low-speed point set, setting the instantaneous speed of the low-speed aggregation point to be 0, and setting the course angle of the low-speed aggregation point to be the average value of all course angles in the low-speed point set.
5. The method according to claim 1, wherein optimizing the traffic sign position according to the coslam graph optimization process based on the optimized association of the trajectory point with the traffic sign specifically is:
acquiring traffic sign positions when the same traffic sign entity is observed in different vehicle tracks, and taking an average value of the traffic sign positions;
Taking the observed track points corresponding to the same traffic sign and the entity position of the traffic sign as vertexes, and taking the distance between the corresponding track points and the average value of the positions of the traffic sign as the pre-estimation of the value of a connecting edge between the two vertexes;
And taking the actual distance of the same traffic sign entity observed by the corresponding track points as an observed value, calculating the error between the estimated value and the observed value, and optimizing the position of the traffic sign through coslam graph optimization.
6. a crowdsourced data fusion optimization apparatus, comprising:
The system comprises an extraction module, a position acquisition module and a display module, wherein the extraction module is used for acquiring crowdsourcing data of a preset area, extracting specific data in the crowdsourcing data to form an observation data table, and the specific data comprises traffic sign position information, vehicle track information and an incidence relation between the vehicle track information and the traffic sign position information;
the splicing module is used for splicing the observation data tables, performing label-free clustering on the spliced observation data tables, and taking the category corresponding to each cluster as a group of observation values of the same traffic sign entity;
the prediction module is used for predicting the second track point according to the track motion equation and the first track point;
the first optimization module is used for optimizing the track points in the vehicle track information based on the g2o graph optimization technology according to the error between the predicted value and the actual observed value of the second track point;
and the second optimization module is used for optimizing the position of the traffic sign according to the coslam graph optimization process based on the association between the optimized track point and the traffic sign.
7. The apparatus of claim 6, wherein the first optimization module further comprises:
the low-speed point processing module is used for acquiring track points of which the instantaneous speed is less than a preset threshold value in the vehicle track information and adding the track points of which the instantaneous speed is less than the preset threshold value to the low-speed point set;
and normalizing the low-speed point set to form a low-speed aggregation point, and deleting all track points in the low-speed point set.
8. the apparatus of claim 7, wherein the normalizing the set of low-speed points to form a low-speed aggregate point further comprises:
and setting the low-speed aggregation point position as the average value of all track points in the low-speed point set, setting the instantaneous speed of the low-speed aggregation point to be 0, and setting the course angle of the low-speed aggregation point to be the average value of all course angles in the low-speed point set.
9. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the crowdsourced data fusion optimization method as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for crowd-sourced data fusion optimization as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910770521.8A CN110543473B (en) | 2019-08-20 | 2019-08-20 | Crowdsourcing data fusion optimization method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910770521.8A CN110543473B (en) | 2019-08-20 | 2019-08-20 | Crowdsourcing data fusion optimization method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110543473A true CN110543473A (en) | 2019-12-06 |
| CN110543473B CN110543473B (en) | 2022-03-25 |
Family
ID=68711799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910770521.8A Active CN110543473B (en) | 2019-08-20 | 2019-08-20 | Crowdsourcing data fusion optimization method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543473B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110986970A (en) * | 2019-12-21 | 2020-04-10 | 武汉中海庭数据技术有限公司 | Method and system for optimizing positions of track points and traffic signs |
| CN111190989A (en) * | 2019-12-31 | 2020-05-22 | 深圳安智杰科技有限公司 | Discrete trajectory analysis method and device, electronic equipment and readable storage medium |
| CN112488217A (en) * | 2020-12-05 | 2021-03-12 | 武汉中海庭数据技术有限公司 | Zebra crossing correction method, electronic device and storage medium |
| CN112985404A (en) * | 2021-02-09 | 2021-06-18 | 广州小鹏自动驾驶科技有限公司 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120296559A1 (en) * | 2011-05-18 | 2012-11-22 | Gueziec Andre | System for providing traffic data and driving efficiency data |
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
| 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 |
| CN109186617A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | A kind of view-based access control model crowdsourcing data automatically generate method, system and the memory of lane grade topological relation |
| CN109408578A (en) * | 2018-10-30 | 2019-03-01 | 环境保护部华南环境科学研究所 | One kind being directed to isomerous environment monitoring data fusion method |
-
2019
- 2019-08-20 CN CN201910770521.8A patent/CN110543473B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120296559A1 (en) * | 2011-05-18 | 2012-11-22 | Gueziec Andre | System for providing traffic data and driving efficiency data |
| 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 |
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
| CN109186617A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | A kind of view-based access control model crowdsourcing data automatically generate method, system and the memory of lane grade topological relation |
| CN109408578A (en) * | 2018-10-30 | 2019-03-01 | 环境保护部华南环境科学研究所 | One kind being directed to isomerous environment monitoring data fusion method |
Non-Patent Citations (1)
| Title |
|---|
| 朱自升: "基于神经网络的车辆轨迹预测算法的研究与实现", 《中国优秀硕士学位论文全文数据库（工程科技2辑）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110986970A (en) * | 2019-12-21 | 2020-04-10 | 武汉中海庭数据技术有限公司 | Method and system for optimizing positions of track points and traffic signs |
| CN111190989A (en) * | 2019-12-31 | 2020-05-22 | 深圳安智杰科技有限公司 | Discrete trajectory analysis method and device, electronic equipment and readable storage medium |
| CN111190989B (en) * | 2019-12-31 | 2023-03-14 | 深圳安智杰科技有限公司 | Discrete trajectory analysis method and device, electronic equipment and readable storage medium |
| CN112488217A (en) * | 2020-12-05 | 2021-03-12 | 武汉中海庭数据技术有限公司 | Zebra crossing correction method, electronic device and storage medium |
| CN112985404A (en) * | 2021-02-09 | 2021-06-18 | 广州小鹏自动驾驶科技有限公司 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110543473B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110543473B (en) | Crowdsourcing data fusion optimization method and device and storage medium | |
| EP3505869B1 (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| JP7351487B2 (en) | Intelligent navigation method and system based on topology map | |
| CN108955702B (en) | Lane-level map creation system based on three-dimensional laser and GPS inertial navigation system | |
| CN111192284B (en) | Vehicle-mounted laser point cloud segmentation method and system | |
| CN111582189A (en) | Traffic signal lamp identification method and device, vehicle-mounted control terminal and motor vehicle | |
| CN113593017A (en) | Method, device and equipment for constructing surface three-dimensional model of strip mine and storage medium | |
| CN110458083B (en) | Lane line vectorization method, device and storage medium | |
| WO2021254019A1 (en) | Method, device and system for cooperatively constructing point cloud map | |
| CN115540896A (en) | Path planning method, path planning device, electronic equipment and computer readable medium | |
| CN103632044A (en) | Camera topology building method and device based on geographic information system | |
| CN110796066A (en) | Lane line group construction method and device | |
| CN110717141B (en) | Lane line optimization method, device and storage medium | |
| CN113971723B (en) | Method, device, equipment and storage medium for constructing three-dimensional map in high-precision map | |
| CN114387410A (en) | Road data fusion map generation method and device and electronic equipment | |
| CN112883236B (en) | Map updating method and device, electronic equipment and storage medium | |
| CN113989760A (en) | Method, device and equipment for detecting lane line by high-precision map and storage medium | |
| CN113918666A (en) | Map data processing method, device, system and storage medium | |
| CN113392170A (en) | High-precision map data generation method and device and server | |
| CN110544201A (en) | Large-range splicing method and device for vehicle-mounted laser scanning point cloud | |
| CN114511590A (en) | Intersection multi-guide-line construction method based on monocular vision 3D vehicle detection and tracking | |
| CN102231207A (en) | Moving target tracking method based on Mean Shift and block matching | |
| CN112446315A (en) | High-precision map zebra crossing fusion method, system, server and storage medium | |
| CN116465394B (en) | Road network structure generation method and device based on vehicle track data | |
| CN112509452B (en) | Ground marking fusion method and system based on road structure, server and 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 |