CN109297500A - High-precision positioner and method based on lane line characteristic matching - Google Patents
High-precision positioner and method based on lane line characteristic matching Download PDFInfo
- Publication number
- CN109297500A CN109297500A CN201811023537.4A CN201811023537A CN109297500A CN 109297500 A CN109297500 A CN 109297500A CN 201811023537 A CN201811023537 A CN 201811023537A CN 109297500 A CN109297500 A CN 109297500A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane line
- map
- location
- lane
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005070 sampling Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3423—Multimodal routing, i.e. combining two or more modes of transportation, where the modes can be any of, e.g. driving, walking, cycling, public transport
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Abstract
The invention discloses a kind of high-precision positioner and method based on lane line characteristic matching；Method includes: to match vehicle in the map location of high-precision map by locating module；Position obtains map lane line information in high-precision map according to the map；Lane really first lane line information is acquired by in-vehicle camera；The matching of lane line information and first lane line information according to the map determines the first estimated location of vehicle；Several sample points of random arrangement around first estimated location；The predicted position of next acquisition moment sample point is predicted according to the motion state of vehicle and kinematical equation；In-vehicle camera in next acquisition moment acquisition vehicle in rear lane line information, and according in the sampling location for matching determination vehicle of rear lane line information and map lane line information；According to the predicted position close to sampling location correspond to sample point set estimation vehicle in rear estimated location.The present invention can obtain the vehicle location with degree of precision.
Description
Technical field
The present invention relates to active safety and automatic Pilot fields, are based on lane line characteristic matching in particular to one kind
High-precision positioner and method.
Background technique
The positioning fusion of RTK and Multiple Source Sensor is usually used in the high accuracy positioning of vehicle at present.RTK needs to establish base
It stands at high cost and generally requires cooperation high-frequency output IMU progress data fusion.Multiple Source Sensor mainly include camera, radar,
IMU, GNSS etc..
Wherein, camera cannot independently realize the high accuracy positioning to lane line；Radar needs the offline grid that generates to perceive spy
Expropriation of land figure and characteristics map have the higher cost of freshness requirement, exploitation and maintenance.The combinational algorithm of GNSS and IMU realize it is complicated and
It needs to solve time synchronization, IMU accumulated error, data delay and resolves the problems such as time-consuming, it is difficult to industrial applications.
Summary of the invention
The embodiment of the present invention at least provides a kind of high-precision locating method based on lane line characteristic matching,
It is able to solve in the prior art using high-precision map or Multiple Source Sensor to vehicle location, precision
Not high and high application cost problem.
The specific implementation of above-described embodiment, as described below.
The described method includes:
Step110, vehicle is matched in the map location of the high-precision map by locating module；
Step120, map lane line information is obtained in the high-precision map according to the map location；
Step200, lane really first lane line information is acquired by in-vehicle camera；
Step300, according to the matching of the map lane line information and first lane line information, determine formerly estimating for vehicle
Count position；
Step410, several sample points of random arrangement around the first estimated location；
Step420, the prediction bits that next acquisition moment sample point is predicted according to the motion state and kinematical equation of vehicle
It sets；
Step430, in-vehicle camera in next acquisition moment acquisition vehicle in rear lane line information, and according to described
In the sampling location for matching determining vehicle of rear lane line information and the map lane line information；
Step440, the set for correspond to sample point according to predicted position close to sampling location estimate vehicle rear
Estimated location.
Preferred version is the Step110 in the present embodiment, comprising:
Step111, the location information of vehicle and the outline information of angle information are included at least by locating module input；
Step112, according to the outline information in the map location where the high-precision map-matched automobile.
Preferred version is the Step120 in the present embodiment, comprising:
Step121, the model data according to the map location in lane where high-precision map acquisition vehicle；
Step122, the form point data for obtaining lane according to the model data in the high-precision map；
Step123, the geodetic coordinates established vehicle axis system and configure the vehicle axis system Yu the high-precision map
First coordinate relationship of system；
Step124, it is based on the first coordinate relationship, coordinate converts the form point data to the vehicle axis system；
Step125, converted according to coordinate after the form point data establish map lane line information.
Preferred version is the Step200 in the present embodiment, comprising:
Step210, camera coordinates system is determined according to the intrinsic parameter and outer parameter of in-vehicle camera configuration；
The second coordinate relationship of Step220, the configuration vehicle axis system and the camera coordinates system；
Step230, it is based on the second coordinate relationship, the first lane of the vehicle axis system is located at by in-vehicle camera acquisition
Line information.
Preferred version is the Step300 in the present embodiment, comprising:
Step310, the first lane line information are the true cubic polynomial of at least one in-vehicle camera detection
Equation；
Step320, map lane line information is fitted as map cubic polynomial equation based on least square method；
Step330, using curve co-insides degree and similarity algorithm, match the map cubic polynomial equation and at least one
True cubic polynomial equation described in item extracts the true cubic polynomial equation of Optimum Matching；
Step340, the origin that the vehicle axis system is estimated according to the true cubic polynomial equation of Optimum Matching
Position, the origin position are the first estimated location of the vehicle in lane.
Preferred version is that the Step410 is configured that in the present embodiment
Several sample points are configured in the vehicle axis system using Gaussian Profile around the first estimated location.
Preferred version is the Step420 in the present embodiment, comprising:
Step421, the present speed and current angular that vehicle is acquired by Inertial Measurement Unit；
Step422, using the present speed and the current angular as the input parameter of vehicle kinematics equation, prediction
The predicted position of next acquisition moment all sample points.
Preferred version is the Step440 in the present embodiment, comprising:
Step441, Bayesian filter is carried out with all predicted positions and sampling location, extracts the sample point being effectively matched
Sample set；
Step442, weighted average sample set in all sample points, estimate vehicle in rear estimated location.
Preferred version is the Step441 in the present embodiment, comprising:
Step4411, Bayesian filter is carried out with all predicted positions and sampling location, estimated described in the conduct of sample estimates point
The weight of position is counted,
Step4412, the sample point is divided into the small sample point and satisfaction for being unsatisfactory for minimal weight requirement according to weight
The large sample point that minimal weight requires,
Step4413, it rejects small sample point and duplication is weighted to large sample point, obtain weight sample point,
Step4414, weight update is carried out according to all same points and is unsatisfactory for minimal weight requirement after rejecting update
Weight sample point；
The Step442 is configured to be weighted and averaged all same points for meeting minimal weight requirement, estimates vehicle
In rear estimated location.
The embodiment of the present invention separately discloses a kind of high-precision positioner based on lane line characteristic matching, described device packet
It includes:
Map-matching module is configured to
By locating module input location information match vehicle the high-precision map map location,
According to the map location in high-precision map match lane,
Lane model is establishd or updated according to matched lane；
Lane line matching module, is configured to
The map lane line information for being located at vehicle axis system is obtained according to lane model,
By in-vehicle camera input current lane line information and the map lane line information matches, determine vehicle
First estimated location；
Location estimation module, is configured to
Several sample points of random arrangement around the first estimated location,
The predicted position of next acquisition moment sample point is predicted according to the motion state of vehicle and kinematical equation；
In-vehicle camera in next acquisition moment acquisition vehicle in rear lane line information, and according to described in rear lane
The sampling location for matching determining vehicle of line information and the map lane line information；
According to the predicted position close to sampling location correspond to the sample point set estimation vehicle in rear estimated location.
For above scheme, the present invention is by being referring to the drawings described in detail disclosed exemplary embodiment, also
The other feature and its advantage for making the embodiment of the present invention understand.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow chart of embodiment one；
Fig. 2 is the module map of embodiment one；
Fig. 3 is the flow chart of embodiment two.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
Embodiment one
The present embodiment discloses a kind of high-precision locating method based on lane line characteristic matching, can be provided by Ublox
Outline information including location data, speed data and course data passes through accurately diagram data and above-mentioned outline information
Matching obtains map lane line information；First lane line information is acquired by MobilEye again and is carried out with map lane line information
Matching, obtaining has higher transverse precision and the generally longitudinally vehicle location of precision.
The present invention after obtaining above-mentioned vehicle location by all sample points next acquisition moment position prediction with
And position detection of the MobilEye at next acquisition moment matches effective sample point set as the height to vehicle actual position
Precision positioning.
In order to realize above scheme, referring to FIG. 1, the method for the present embodiment uses following steps.
Step110, vehicle is matched in the map location of high-precision map by Ublox: be preferably configured as follows.
Step111, the location data of vehicle for receiving Ublox input, the outline information of speed data and course data.
Step112 is simultaneously located at the adjustable threshold range of location data according to outline information above-mentioned in high-precision map
Interior lookup is with vehicle location apart from map location where lane that is nearest and meeting with vehicle course.
Step120, according to the map position obtain map lane line information in high-precision map: being preferably configured as follows.
Step121, lane information is extracted according to the map location found and lane model is established according to lane information.
Step122, the form point string for obtaining lane line according to model data in high-precision map, high-precision map generally use
Be earth coordinates, then the form point string of lane line can be expressed as shapePointWGS84 []={ pt1, pt2, pt3 ... },
Wherein pt1, pt2 are the form point coordinate of lane line.
The first of Step123, the earth coordinates established vehicle axis system and configure vehicle axis system and high-precision map
Coordinate relationship.
The present embodiment preferentially determines the first transformational relation of earth coordinates and Gauss plane coordinate system, then determines that Gauss is flat
Second transformational relation of areal coordinate system and vehicle axis system；Above-mentioned is configured according to the first transformational relation and the second transformational relation
One coordinate relationship.
Step124, it is based on the first coordinate relationship, coordinate converts form point data to vehicle axis system, then in vehicle coordinate
Above-mentioned form point string under system is shapePoint []={ ptA, ptB, ptC ... }.
Step125, obtain vehicle axis system form point string after establish map lane line information.
Step200, current time vehicle vehicle in the process of moving is acquired by MobilEye combination lane detection algorithm
The true first lane line information in road: it is preferably configured as follows.
Step210, camera coordinates system is determined according to the intrinsic parameter and outer parameter of MobilEye configuration.
Step220, the second coordinate relationship for configuring vehicle axis system and camera coordinates system.
Step230, it is based on the second coordinate relationship, vehicle is located at by the acquisition of MobilEye combination lane detection algorithm and is sat
Mark the first lane line information of system.
The matching of Step300, according to the map lane line information and first lane line information determines the first estimation position of vehicle
It sets: being preferably configured as follows.
Step310, a plurality of lane line fitting for including according to the first lane line information of acquisition are a plurality of true multinomial three times
Formula equation.
Step320, fitting map lane line information are map cubic polynomial equation.
It is preferably based on least square method and is fitted true cubic polynomial equation and map cubic polynomial equation as three times
Polynomial equation；
The generally expression formula of cubic polynomial equation are as follows:
The value range of y=C0+C1*X+C2*X*X+C3*X*X*X, X are MinX to MinX,
Wherein equation parameter includes that C0, C1, C3, C4 are coefficient, and X, Y are vehicle axis system coordinate, and Minx is the minimum of X
Value, MaxX are the maximum value of X.
Step330, using curve co-insides degree and similarity algorithm to map cubic polynomial equation and it is all it is true three times
Polynomial equation is matched, and at least one true cubic polynomial equation of Optimum Matching is extracted.
Step340, under vehicle axis system according at least one true cubic polynomial equation of Optimum Matching, can estimate
The probability of the origin position of vehicle axis system is counted, origin position is first estimated location of the vehicle in lane.
Step410, in order to further increase longitudinal register precision, using Gaussian Profile above-mentioned first estimated location week
It encloses and configures several sample points under vehicle axis system, on sample point random distribution lane and adjacent lane.
Step420, the prediction bits that next acquisition moment sample point is predicted according to the motion state and kinematical equation of vehicle
It sets；It is preferably configured as follows.
The time of Step421, synchronous Inertial Measurement Unit and MobilEye, then vehicle is inputted by Inertial Measurement Unit
Current driving speed and current course angle degree；
Step422, using current driving speed and current course angle degree as the input parameter of vehicle kinematics equation, prediction
Predicted position of next acquisition moment all sample points under vehicle axis system.
Step430, MobilEye are in next acquisition moment acquisition vehicle in rear lane line information；And in next sampling
It carves using all sampled points as vehicle location and uses such as Step300 and specific steps in high-precision map, obtain all sampled points
Map lane line information；Institute is obtained in the matching of rear lane line information by the map lane line information of all sampled points again
There is the predicted position of sample point；
Step440, lookup relative sample position are located at the set that all predicted positions in distance threshold correspond to sample point
Estimate vehicle in rear estimated location；It is preferably configured as follows.
Step4411, Bayesian filter is carried out with all predicted positions and sampling location, sample estimates point is used as to be estimated after
The weight of position is counted,
Step4412, sample point is divided into the small sample point and satisfaction minimum for being unsatisfactory for minimal weight requirement according to weight
The large sample point that weight requires.Minimal weight requires it is considered that setting, specifically according to the position error range of vehicle GPS.
Step4413, it rejects small sample point and duplication is weighted to large sample point, obtain weight sample point.
Step4414,1 is added up in view of all same weights, then the necessary needs of weight of all heavy sample points
It is updated, while rejecting the heavy sample point for being unsatisfactory for minimal weight requirement after weight update；
Step442, after weight is updated and meet minimal weight requirement all same points be weighted and averaged, estimate
Vehicle in rear estimated location.
Through the above steps, the present embodiment in rear estimated location, more can really reflect vehicle in the reality in lane
Border position；Compared with prior art, smaller in the error of transverse direction and longitudinal direction.Meanwhile the realization of the present embodiment method only needs
The output of combined high precision map datum, MobilEye camera and consumer level Ublox chip, hardware cost are low.
Referring to FIG. 2, the present embodiment separately discloses a kind of high-precision positioner based on lane line characteristic matching, including ground
Figure matching module, lane line matching module and location estimation module.
Wherein, map-matching module is configured to the location information inputted by locating module and matches vehicle accurately
The map location of figure, position establishs or updates lane mould according to matched lane in high-precision map match lane according to the map
Type；
Lane line matching module is configured to obtain the map lane line information for being located at vehicle axis system according to lane model,
By the current lane line information and map lane line information matches of MobilEye input, the first estimated location of vehicle is determined；
Location estimation module is configured to several sample points of random arrangement around aforementioned first estimated location, according to vehicle
Motion state and kinematical equation predict it is next acquisition moment sample point predicted position；MobilEye is at next acquisition moment
Acquire vehicle determines vehicle with matching for map lane line information in rear lane line information, and according in rear lane line information
Sampling location；According to the predicted position close to sampling location correspond to sample point set estimation vehicle in rear estimated location.
Embodiment two
Referring to FIG. 3, the present embodiment discloses a kind of high-precision locating method based on lane line characteristic matching；The present embodiment
Difference compared to embodiment one is that the matching status of vehicle, the present embodiment are first determined before the outline information for receiving Ublox input
Matching status be divided into search condition and tracking mode.
The search condition configuration of the present embodiment is as follows.
Step110, the location data of vehicle for receiving Ublox input, the outline information of speed data and course data.
Step120, searched in high-precision map according to outline information above-mentioned meet at a distance from vehicle location it is certain
Threshold range, and closest to and the lane same or similar with vehicle course.
If Step130, matching lane are unsuccessful, return and judge search condition locating for vehicle or tracking mode.
If matching lane success, the lane information in lane is obtained after matching lane and establishes lane model, and setting
It is tracking mode with state.
Step140, the topological connection relation according to lane model foundation lane and the Step122 into embodiment one.
The tracking mode configuration of the present embodiment is as follows.
Step110, the location data of vehicle for receiving Ublox input, the outline information of speed data and course data.
Step120, directly lookup meets certain threshold value model at a distance from vehicle location from the topological connection relation in lane
The lane enclosed, and find out apart from nearest lane as matching lane.
If Step130, matching lane are unsuccessful, returning to matching status is above-mentioned search condition；If matching lane
Success obtains the corresponding lane information of topological connection relation and establishes new lane model, and matching status is arranged as tracking shape
State.
Step140, implemented according to lane information and the topological connection relation in the lane model modification lane of foundation and entrance
The Step122 of example one.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of high-precision locating method based on lane line characteristic matching, which is characterized in that
The described method includes:
Step110, vehicle is matched in the map location of the high-precision map by locating module；
Step120, map lane line information is obtained in the high-precision map according to the map location；
Step200, lane really first lane line information is acquired by in-vehicle camera；
Step300, according to the matching of the map lane line information and first lane line information, determine the first estimation position of vehicle
It sets；
Step410, several sample points of random arrangement around the first estimated location；
Step420, the predicted position that next acquisition moment sample point is predicted according to the motion state and kinematical equation of vehicle；
Step430, in-vehicle camera in next acquisition moment acquisition vehicle in rear lane line information, and according to described rear
The sampling location for matching determining vehicle of lane line information and the map lane line information；
Step440, the set for correspond to sample point according to predicted position close to sampling location estimate vehicle in rear estimation
Position.
2. the high-precision locating method as described in claim 1 based on lane line characteristic matching, which is characterized in that described
Step110, comprising:
Step111, the location information of vehicle and the outline information of angle information are included at least by locating module input；
Step112, according to the outline information in the map location where the high-precision map-matched automobile.
3. the high-precision locating method as described in claim 1 based on lane line characteristic matching, which is characterized in that described
Step120, comprising:
Step121, the model data according to the map location in lane where high-precision map acquisition vehicle；
Step122, the form point data for obtaining lane according to the model data in the high-precision map；
Step123, it establishes vehicle axis system and configures the vehicle axis system and the earth coordinates of the high-precision map
First coordinate relationship；
Step124, it is based on the first coordinate relationship, coordinate converts the form point data to the vehicle axis system；
Step125, converted according to coordinate after the form point data establish map lane line information.
4. the accuracy method as claimed in claim 3 based on lane line characteristic matching, which is characterized in that the Step200,
Include:
Step210, camera coordinates system is determined according to the intrinsic parameter and outer parameter of in-vehicle camera configuration；
The second coordinate relationship of Step220, the configuration vehicle axis system and the camera coordinates system；
Step230, it is based on the second coordinate relationship, is believed by the first lane line that in-vehicle camera acquisition is located at the vehicle axis system
Breath.
5. the high-precision locating method as claimed in claim 3 based on lane line characteristic matching, which is characterized in that described
Step300, comprising:
Step310, the first lane line information are the true cubic polynomial equation of at least one in-vehicle camera detection；
Step320, map lane line information is fitted as map cubic polynomial equation based on least square method；
Step330, using curve co-insides degree and similarity algorithm, match the map cubic polynomial equation and at least one institute
True cubic polynomial equation is stated, the true cubic polynomial equation of Optimum Matching is extracted；
Step340, the origin position that the vehicle axis system is estimated according to the true cubic polynomial equation of Optimum Matching,
The origin position is the first estimated location of the vehicle in lane.
6. the high-precision locating method as claimed in claim 5 based on lane line characteristic matching, which is characterized in that described
Step410 is configured that
Several sample points are configured in the vehicle axis system using Gaussian Profile around the first estimated location.
7. the high-precision locating method as claimed in claim 2 based on lane line characteristic matching, which is characterized in that described
Step420, comprising:
Step421, the present speed and current angular that vehicle is acquired by Inertial Measurement Unit；
Step422, using the present speed and the current angular as the input parameter of vehicle kinematics equation, predict it is next
Acquire the predicted position of moment all sample points.
8. the high-precision locating method as described in claim 1 based on lane line characteristic matching, which is characterized in that described
Step440, comprising:
Step441, Bayesian filter is carried out with all predicted positions and sampling location, extracts the sample for the sample point being effectively matched
Collection；
Step442, weighted average sample set in all sample points, estimate vehicle in rear estimated location.
9. the high-precision locating method as claimed in claim 8 based on lane line characteristic matching, which is characterized in that
The Step441, comprising:
Step4411, Bayesian filter is carried out with all predicted positions and sampling location, sample estimates point is as the estimation position
The weight set,
Step4412, the sample point is divided into the small sample point and satisfaction minimum for being unsatisfactory for minimal weight requirement according to weight
The large sample point that weight requires,
Step4413, it rejects small sample point and duplication is weighted to large sample point, obtain weight sample point,
Step4414, weight update is carried out according to all same points and is unsatisfactory for the same of minimal weight requirement after rejecting update
This point；
The Step442 is configured to be weighted and averaged all same points for meeting minimal weight requirement, estimates vehicle
In rear estimated location.
10. a kind of high-precision positioner based on lane line characteristic matching, which is characterized in that
Described device includes:
Map-matching module is configured to
By locating module input location information match vehicle the high-precision map map location,
According to the map location in high-precision map match lane,
Lane model is establishd or updated according to matched lane；
Lane line matching module, is configured to
The map lane line information for being located at vehicle axis system is obtained according to lane model,
The current lane line information and the map lane line information matches inputted by in-vehicle camera determines formerly estimating for vehicle
Count position；
Location estimation module, is configured to
Several sample points of random arrangement around the first estimated location,
The predicted position of next acquisition moment sample point is predicted according to the motion state of vehicle and kinematical equation；
In-vehicle camera is believed in rear lane line information, and according to described in rear lane line next acquisition moment acquisition vehicle
Cease the sampling location for matching determining vehicle with the map lane line information；
According to the predicted position close to sampling location correspond to the sample point set estimation vehicle in rear estimated location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023537.4A CN109297500B (en) | 2018-09-03 | 2018-09-03 | High-precision positioning device and method based on lane line feature matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023537.4A CN109297500B (en) | 2018-09-03 | 2018-09-03 | High-precision positioning device and method based on lane line feature matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109297500A true CN109297500A (en) | 2019-02-01 |
| CN109297500B CN109297500B (en) | 2020-12-15 |
Family
ID=65166250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811023537.4A Active CN109297500B (en) | 2018-09-03 | 2018-09-03 | High-precision positioning device and method based on lane line feature matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109297500B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147382A (en) * | 2019-05-28 | 2019-08-20 | 北京百度网讯科技有限公司 | Lane line update method, device, equipment, system and readable storage medium storing program for executing |
| CN110160540A (en) * | 2019-06-12 | 2019-08-23 | 禾多科技（北京）有限公司 | Lane line data fusion method based on high-precision map |
| CN110398713A (en) * | 2019-07-29 | 2019-11-01 | 相维(北京)科技有限公司 | A method of receiver motion state is detected using wireless signal |
| CN110954113A (en) * | 2019-05-30 | 2020-04-03 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN111256711A (en) * | 2020-02-18 | 2020-06-09 | 北京百度网讯科技有限公司 | Vehicle pose correction method, device, equipment and storage medium |
| WO2020232648A1 (en) * | 2019-05-22 | 2020-11-26 | 深圳市大疆创新科技有限公司 | Lane line detection method, electronic device and storage medium |
| CN112560680A (en) * | 2020-12-16 | 2021-03-26 | 北京百度网讯科技有限公司 | Lane line processing method and device, electronic device and storage medium |
| CN113175938A (en) * | 2021-03-16 | 2021-07-27 | 惠州市德赛西威智能交通技术研究院有限公司 | Vehicle positioning enhancement system and method based on high-precision map |
| CN112001456B (en) * | 2020-10-28 | 2021-07-30 | 北京三快在线科技有限公司 | Vehicle positioning method and device, storage medium and electronic equipment |
| CN115143996A (en) * | 2022-09-05 | 2022-10-04 | 北京智行者科技股份有限公司 | Positioning information correction method, electronic device, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104180801A (en) * | 2014-08-20 | 2014-12-03 | 广州海格通信集团股份有限公司 | Method and system for predicting track points based on ADS-B system |
| KR20160049695A (en) * | 2014-10-28 | 2016-05-10 | 현대모비스 주식회사 | Method for map matching of vehicle and apparatus thereof |
| CN105783936A (en) * | 2016-03-08 | 2016-07-20 | 武汉光庭信息技术股份有限公司 | Road sign drawing and vehicle positioning method and system for automatic drive |
| CN106225790A (en) * | 2016-07-13 | 2016-12-14 | 百度在线网络技术（北京）有限公司 | A kind of determination method and device of unmanned vehicle positioning precision |
| CN107782321A (en) * | 2017-10-10 | 2018-03-09 | 武汉迈普时空导航科技有限公司 | A kind of view-based access control model and the Combinated navigation method of high-precision map lane line constraint |
| CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
| CN108303103A (en) * | 2017-02-07 | 2018-07-20 | 腾讯科技（深圳）有限公司 | The determination method and apparatus in target track |
| CN108413971A (en) * | 2017-12-29 | 2018-08-17 | 驭势科技（北京）有限公司 | Vehicle positioning technology based on lane line and application |
-
2018
- 2018-09-03 CN CN201811023537.4A patent/CN109297500B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104180801A (en) * | 2014-08-20 | 2014-12-03 | 广州海格通信集团股份有限公司 | Method and system for predicting track points based on ADS-B system |
| KR20160049695A (en) * | 2014-10-28 | 2016-05-10 | 현대모비스 주식회사 | Method for map matching of vehicle and apparatus thereof |
| CN105783936A (en) * | 2016-03-08 | 2016-07-20 | 武汉光庭信息技术股份有限公司 | Road sign drawing and vehicle positioning method and system for automatic drive |
| CN106225790A (en) * | 2016-07-13 | 2016-12-14 | 百度在线网络技术（北京）有限公司 | A kind of determination method and device of unmanned vehicle positioning precision |
| CN108303103A (en) * | 2017-02-07 | 2018-07-20 | 腾讯科技（深圳）有限公司 | The determination method and apparatus in target track |
| CN107782321A (en) * | 2017-10-10 | 2018-03-09 | 武汉迈普时空导航科技有限公司 | A kind of view-based access control model and the Combinated navigation method of high-precision map lane line constraint |
| CN108413971A (en) * | 2017-12-29 | 2018-08-17 | 驭势科技（北京）有限公司 | Vehicle positioning technology based on lane line and application |
| CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020232648A1 (en) * | 2019-05-22 | 2020-11-26 | 深圳市大疆创新科技有限公司 | Lane line detection method, electronic device and storage medium |
| CN110147382A (en) * | 2019-05-28 | 2019-08-20 | 北京百度网讯科技有限公司 | Lane line update method, device, equipment, system and readable storage medium storing program for executing |
| CN110954113A (en) * | 2019-05-30 | 2020-04-03 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN110954113B (en) * | 2019-05-30 | 2021-10-15 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN110160540A (en) * | 2019-06-12 | 2019-08-23 | 禾多科技（北京）有限公司 | Lane line data fusion method based on high-precision map |
| CN110398713A (en) * | 2019-07-29 | 2019-11-01 | 相维(北京)科技有限公司 | A method of receiver motion state is detected using wireless signal |
| CN111256711A (en) * | 2020-02-18 | 2020-06-09 | 北京百度网讯科技有限公司 | Vehicle pose correction method, device, equipment and storage medium |
| CN111256711B (en) * | 2020-02-18 | 2022-05-20 | 北京百度网讯科技有限公司 | Vehicle pose correction method, device, equipment and storage medium |
| CN112001456B (en) * | 2020-10-28 | 2021-07-30 | 北京三快在线科技有限公司 | Vehicle positioning method and device, storage medium and electronic equipment |
| CN112560680A (en) * | 2020-12-16 | 2021-03-26 | 北京百度网讯科技有限公司 | Lane line processing method and device, electronic device and storage medium |
| CN113175938A (en) * | 2021-03-16 | 2021-07-27 | 惠州市德赛西威智能交通技术研究院有限公司 | Vehicle positioning enhancement system and method based on high-precision map |
| CN115143996A (en) * | 2022-09-05 | 2022-10-04 | 北京智行者科技股份有限公司 | Positioning information correction method, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109297500B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109297500A (en) | High-precision positioner and method based on lane line characteristic matching | |
| CN105628026B (en) | A kind of positioning and orientation method and system of mobile object | |
| CN108171131B (en) | Improved MeanShift-based method for extracting Lidar point cloud data road marking line | |
| US9420275B2 (en) | Visual positioning system that utilizes images of a working environment to determine position | |
| EP2813816B1 (en) | Method for performing map matching in user terminal | |
| CN107305126A (en) | The data configuration of environmental map, its manufacturing system and preparation method and its more new system and update method | |
| CN110702091B (en) | High-precision positioning method for moving robot along subway rail | |
| CN105652306A (en) | Dead reckoning-based low-cost Big Dipper and MEMS tight-coupling positioning system and method | |
| CN111429716A (en) | Method for determining position of own vehicle | |
| CN108645420B (en) | Method for creating multipath map of automatic driving vehicle based on differential navigation | |
| CN110411462A (en) | A kind of GNSS/ inertia/lane line constraint/odometer multi-source fusion method | |
| JP2007333385A (en) | Immobile object position recording device | |
| CN108759823B (en) | Low-speed automatic driving vehicle positioning and deviation rectifying method on designated road based on image matching | |
| CN107179079A (en) | The indoor orientation method merged based on PDR with earth magnetism | |
| KR102371984B1 (en) | Method for detecting the changing point of road | |
| CN110332945B (en) | Vehicle navigation method and device based on traffic road marking visual identification | |
| CN111025366B (en) | Grid SLAM navigation system and method based on INS and GNSS | |
| JP2016109650A (en) | Position estimation system, position estimation method, and position estimation program | |
| CN108759834A (en) | A kind of localization method based on overall Vision | |
| CN109141427A (en) | EKF localization method under nlos environment based on distance and angle probabilistic model | |
| CN114565674B (en) | Method and device for purely visually positioning urban structured scene of automatic driving vehicle | |
| Mueller et al. | GIS-based topological robot localization through LIDAR crossroad detection | |
| CN110346821A (en) | A kind of SINS/GPS integrated attitude determination localization method solving the problems, such as GPS long-time losing lock and system | |
| CN109325390A (en) | A kind of localization method combined based on map with FUSION WITH MULTISENSOR DETECTION and system | |
| CN110388939A (en) | One kind being based on the matched vehicle-mounted inertial navigation position error modification method of Aerial Images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A high-precision positioning device and method based on lane line feature matching Granted publication date: 20201215 Pledgee: Productivity Promotion Center of Wuhan East Lake New Technology Development Zone Pledgor: WUHHAN KOTEL BIG DATE Corp. Registration number: Y2024980005100 |