CN110375753A - Map-matching method, device, server and storage medium - Google Patents
Map-matching method, device, server and storage medium Download PDFInfo
- Publication number
- CN110375753A CN110375753A CN201910599214.8A CN201910599214A CN110375753A CN 110375753 A CN110375753 A CN 110375753A CN 201910599214 A CN201910599214 A CN 201910599214A CN 110375753 A CN110375753 A CN 110375753A
- Authority
- CN
- China
- Prior art keywords
- tracing point
- effective
- effective tracing
- matching
- candidate state
- 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
- 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
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- 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 present invention is suitable for field of computer technology, proposes a kind of map-matching method, and effective tracing point of vehicle is obtained including the track data based on vehicle；Determine the candidate state of each effectively tracing point；Goal displacement cost between the adjacent effective tracing point of each matching distance and any two effectively between tracing point and corresponding candidate state of calculating；Linear path adaptation function is constructed based on matching distance and goal displacement cost；Linear path adaptation function is solved, the coupling path of effective tracing point of vehicle on the electronic map is obtained.By constructing the linear path adaptation function of the matching distance between effective tracing point and corresponding candidate state and the transfer value between the adjacent effective tracing point of any two, by solving the linear path adaptation function, the accuracy rate of map match is improved.
Description
Technical field
The invention belongs to field of computer technology more particularly to a kind of map-matching method, device, server and storage to be situated between
Matter.
Background technique
Map match is a kind of positioning correction method based on software technology, basic thought be by vehicle location track with
Electronic map information in numerical map connects, and the position of vehicle is determined thus relative to map.In practical applications,
The accuracy rate of map match and the quality of positioning device sampled signal are closely related, such as reduction, the position error of sample frequency
Increasing, signal loss, can all increase the inaccuracy of map match.And due to by positioning device sole mass and city
The influence of the noises such as building, above situation often occur in practical applications, so that track of vehicle is with physical location, there are one
Determine deviation, not can guarantee the accuracy rate of map match.Therefore, how to improve the accuracy rate of map match is urgently to be resolved ask
Topic.
Summary of the invention
In view of this, the embodiment of the invention provides map-matching method, device, server and storage medium, to solve
In the prior art since track of vehicle and physical location are there are certain deviation, the phenomenon that caused coupling path is distorted, improve ground
Scheme matched accuracy rate.
The first aspect of the embodiment of the present invention provides a kind of map-matching method, comprising:
Track data based on vehicle obtains effective tracing point of the vehicle；
Determine that the candidate state of each effective tracing point, the candidate state are effective tracing point in matching model
The subpoint on K road in enclosing；
It calculates matching distance between each effective tracing point and corresponding candidate state and any two is adjacent
Effective tracing point between goal displacement cost, the goal displacement cost having between adjacent effective tracing point
Imitate the transfer value of transfer path；
Linear path adaptation function is constructed based on the matching distance and the goal displacement cost；
The linear path adaptation function is solved, the coupling path of effective tracing point of vehicle on the electronic map is obtained.
Optionally, the track data includes acquisition time and location information；The track data based on vehicle obtains
Effective tracing point of the vehicle, comprising:
Abnormal tracing point and dwell point are determined according to the acquisition time and the location information；
Abnormal tracing point and the dwell point in the track data are rejected, effective tracing point is obtained.
Optionally, the candidate state of each effective tracing point of the determination, comprising:
The matching range of each effective tracing point on the electronic map is determined according to preset positioning accuracy；
K road in the matching range of each effective tracing point is obtained respectively；
Subpoint of each effective tracing point on the K road is obtained, the subpoint has to be each described
Imitate the candidate state of tracing point.
Optionally, the subpoint for obtaining each effective tracing point on the K road, the subpoint are
The candidate state of each effective tracing point, comprising:
If there is effective tracing point on any one road in the K road, effective tracing point is in institute
Stating the subpoint on any one road is effective tracing point；
If effective tracing point not on the K road, is calculated according to the subpoint of preset point to road
Method calculates subpoint of each effective tracing point on the K road.
Optionally, the matching distance calculated between each effective tracing point and corresponding candidate state, and
Transfer value between the adjacent effective tracing point of any two, comprising:
The Euclidean distance between each effective tracing point and corresponding candidate state is calculated, the Euclidean distance is institute
State matching distance；
The candidate state for obtaining each effective tracing point respectively generates each institute according to preset Path Planning
State the candidate state sequence of effective tracing point；
The candidate state in the candidate state sequence of the adjacent effective tracing point of any two is carried out respectively
Pairing obtains effective transfer path between the candidate state of the adjacent effective tracing point of any two；
Effective transfer path is matched from electronic map map, and according to preset transfer value calculation formula meter
Calculate the transfer value of effective transfer path.
Optionally, the Euclidean distance calculated between each effective tracing point and corresponding candidate state, it is described
Euclidean distance is the matching distance, comprising:
According to the acquisition time of each effective tracing point, the sequence of effective tracing point is generated；
If there is the candidate state collection of effective tracing point for sky, it is determined that the matching status of presently described effective tracing point
It whether is init state；
If the matching status of presently described effective tracing point is init state, it is determined that presently described effective tracing point
The time interval of acquisition time and the acquisition time of the last one effective tracing point in the sequence of effective tracing point is
It is no to be less than default break period threshold value；
If being less than preset break period threshold value, it is determined that presently described effective tracing point is invalid tracing point, skips and works as
Preceding effective tracing point obtains the next effective tracing point adjacent with presently described effective tracing point and calculates the matching
Distance；
If more than preset break period threshold value, it is determined that presently described effective tracing point is in the infull position of electronic map
It sets, sets doubtful new line state for presently described effective tracing point；
Illusion matching detection is carried out to the sequence of effective tracing point.
Optionally, the sequence to effective tracing point carries out illusion matching detection, comprising:
If the frequency that presently described effective tracing point triggering matching is interrupted is greater than or equal to preset frequency threshold；Then determine
The currently active tracing point is in doubtful new line state, and the sequence of effective tracing point is in artifacts matching status；
If the frequency that triggering matching is interrupted is less than the preset frequency threshold, it is determined that presently described effective tracing point is
The sequence of invalid tracing point, effective tracing point is in non-artifacts matching status.
Optionally, the goal displacement cost between adjacent effective tracing point indicates are as follows:
Wherein,Indicate transfer value, drouteIndicate effective transfer path distance, TturnIndicate effective
Number, T are turned in transfer pathroadclassIndicate that category of roads changes in effective transfer path, TownershipIndicate effectively transfer
Road is transferred to the number in outer lane, T from inside lane in pathruleIndicate rule-breaking vehicle driving behavior number, the w1、w2、
w3、w4It is preset weight coefficient.
Optionally, the linear path adaptation function are as follows:
Wherein, g is coupling path score, and μ is preset coefficient of balance, and n is the number of effective tracing point, and i is indicated i-th
Effective tracing point,For the matching distance of i-th of effective tracing point and p-th of candidate state,It is (i-1)-th
Transfer value in a effective tracing point in q-th of candidate state and i-th of effective tracing point between p-th of candidate state, institute
It is mutual for stating q-th of candidate state and p-th of candidate state in described i-th effective tracing point in (i-1)-th effective tracing point
The candidate state of pairing.
Optionally, described to solve the linear path adaptation function, obtain effective tracing point of vehicle on the electronic map
Coupling path, comprising:
The linear path adaptation function is solved based on dimension bit algorithm, obtains the minimum value of the coupling path score；
When the coupling path score minimum, the candidate state and the time of corresponding each effective tracing point
The road for selecting effective transfer path between state to constitute is the coupling path of effective tracing point of vehicle on the electronic map.
The second aspect of the embodiment of the present invention provides map matching means, comprising:
Module is obtained, effective tracing point of the vehicle is obtained for the track data based on vehicle；
Determining module, for determining that the candidate state of each effective tracing point, the candidate state are described effective
Subpoint of the tracing point on the K road in matching range；
Computing module, for calculating the matching distance between each effective tracing point and corresponding candidate state, with
And the goal displacement cost between the adjacent effective tracing point of any two, the goal displacement cost are described adjacent
The transfer value of effective transfer path between effective tracing point；
Module is constructed, for matching letter based on the matching distance and goal displacement cost building linear path
Number；
It solves module and obtains effective tracing point of vehicle in electronic map for solving the linear path adaptation function
On coupling path.
The third aspect of the embodiment of the present invention provides a kind of server, including memory, processor and is stored in institute
The computer program that can be run in memory and on the processor is stated, the processor executes real when the computer program
Now the step of map-matching method described in any embodiment as above.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes map described in any embodiment as above when being executed by processor
The step of method of completing the square.
Existing beneficial effect is the embodiment of the present invention compared with prior art: described in the track data based on vehicle obtains
Effective tracing point of vehicle；Determine that the candidate state of each effective tracing point, the candidate state are effective track
Subpoint of the point on the K road in matching range；It calculates between each effective tracing point and corresponding candidate state
Matching distance and the adjacent effective tracing point of any two between goal displacement cost, the goal displacement cost is
The transfer value of effective transfer path between adjacent effective tracing point；Based on the matching distance and the target
Transfer value constructs linear path adaptation function；The linear path adaptation function is solved, the effective tracing point for obtaining vehicle exists
Coupling path on electronic map.By constructing matching distance and any two between effective tracing point and corresponding candidate state
The linear path adaptation function of transfer value between adjacent effective tracing point, by solving the linear path adaptation function,
The matching error between track of vehicle and physical location is reduced, improves the accuracy rate of map match.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart of map-matching method provided in an embodiment of the present invention；
Fig. 2 is the specific implementation flow chart of S101 in Fig. 1；
Fig. 3 is the specific implementation flow chart of S102 in Fig. 1；
Fig. 4 is the specific implementation flow chart of S103 in Fig. 1；
Fig. 5 is the specific implementation process figure of S105 in Fig. 1；
Fig. 6 is the illustrative view of functional configuration of map matching means provided by the invention；
Fig. 7 is the schematic diagram of server provided by the invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.As shown in Figure 1,
It is the implementation process of map-matching method provided in an embodiment of the present invention, the executing subject of the present embodiment is server.It is described in detail such as
Under:
S101, the track data based on vehicle obtain effective tracing point of the vehicle.
Specifically, vehicle in the process of moving, is influenced by speed and road environment, the navigation positioning module of vehicle
It usually there will be some abnormal tracks in the track data of (such as GPS navigation positioning system, BDStar navigation system) acquisition
Point, for example, if the distance in long when shorter between two neighboring tracing point be greater than preset distance threshold or vehicle compared with
It in the long period, is constantly in fixed or lesser region, then collected tracing point may be to stop in corresponding duration
Therefore stationary point in the embodiment of this programme, needs the track data based on vehicle to obtain effective tracing point of vehicle.Specifically
Ground, the track data of vehicle include acquisition time and location information.
As shown in Fig. 2, being the specific implementation flow chart of S101 in Fig. 1, as shown in Figure 2, S101, comprising:
S1011 determines abnormal tracing point and dwell point according to the acquisition time and the location information.
Specifically, the location information includes timestamp, longitude and latitude.Navigation system during acquisition trajectories data,
Whether its acquisition time is usually to be increased continuously, therefore, can be corresponding consistent with acquisition time by judging timestamp, and is
No to be increased continuously, whether longitude and latitude exceeds preset navigation area boundary to determine the abnormal tracing point in track data.In addition,
It is blocked by city pile or navigation equipment self performance is influenced, lead in longer acquisition time that (at least one is adopted
In sample time interval), the tracing point of acquisition is fixed in the same position or lesser region, then needs to judge adjacent track
Whether the distance between point is less than preset distance threshold (for example, 1m), if there have the distance between adjacent track point to be less than to be default
Distance threshold, it is determined that the adjacent track point be dwell point.In addition, vehicle is not in frequent in a short time when moving
The track of the case where changing direction, corresponding vehicle should be smooth, therefore work as and occur what tracing point was turned back in a big way
Phenomenon then needs to judge whether there is the distance between track any two tracing point point by point and is continuously less than preset stop distance
Threshold value, and above-mentioned start-stop tracing point time interval is more than residence time threshold value；Determine that any two tracing point is to stop if having
Stationary point.
S1012 rejects the abnormal tracing point in the track data, obtains effective tracing point.
It is to be appreciated that after determining the successively tracing point, it can be by data cleansing, delete processing, to pick
Except the abnormal tracing point in the track data, effective tracing point is obtained.
S102 determines that the candidate state of each effective tracing point, the candidate state are that effective tracing point exists
The subpoint on K road in matching range.
Specifically, navigation positioning system usually has fixed positioning accuracy, for example, civil navigation position system GPS
Positioning accuracy is within the scope of 10 meters, and with the difference of navigation equipment, identical navigation positioning system, which often exists, different to be determined
Position error.Position error is usually given before navigation equipment factory, usually assumes that position error Gaussian distributed, 66% point
Positioning accuracy is in 1 times in error range, and 99% spot placement accuracy is in 3 times in error range.In the present solution, with navigation
The positioning accuracy of positioning system is preset positioning accuracy, with the integral multiple of the positioning accuracy for each effective tracing point
Error range, taking the integral multiple (be greater than 1) of position error is orientation range, indicates the tolerance intensity to positioning point drift, should
Value is bigger, and expression drift is more serious, and the smaller expression positioning accuracy of the value is higher, drifts about not serious.Track correction is reduction anchor point
Actual position possibly actual approach section can not be searched from electronic map if not taking drift effect into account.Such as it is described
The positioning accuracy that error range is 3 times, does not do specific restriction herein.With the error range for each effective tracing point
Matching range determine the candidate state of each effective tracing point in the matching range of each effective tracing point,
The candidate state is subpoint of effective tracing point on every road in the K road, and the subpoint refers to
So that the shortest point of distance effectively on tracing point to particular link.
Specifically, as shown in figure 3, being the specific implementation flow chart of S102 in Fig. 1, from the figure 3, it may be seen that S102, comprising:
S1021 determines the matching range of each effective tracing point on the electronic map according to preset positioning accuracy.
Specifically, the preset positioning accuracy is the intrinsic positioning accuracy of the navigation system, and navigation system is positioning
During, it may be by each effective tracing point matching on the mulitpath of electronic map, therefore, it is necessary to limit matching
Range, to improve matched accuracy.
S1022 obtains K road in the matching range of each effective tracing point respectively.
In the matching range of each effective tracing point, generally comprised a plurality of road, every road with match model
The distance for the center enclosed is different, is presetting in the present solution, obtaining and being less than at a distance from the center of the matching range
Distance threshold K road, the candidate roads as each effective tracing point.Wherein, K is just whole more than or equal to 1
Number.
It is understood that K value is bigger, indicate to need matched space bigger, is matched to a possibility that being really path just
It is higher, but will lead to space complexity and the time increase of matching algorithm.It therefore, in practical applications, should be according to acquisition
K value is adaptively adjusted in location information between the quantity and any two adjacent track point of effective tracing point, here,
It is not described in detail and limits.
S1023 obtains subpoint of each effective tracing point on the K road, and the subpoint is each
The candidate state of effective tracing point.
Each effective tracing point can be projected on the corresponding K road, to obtain corresponding subpoint.
It should be noted that if there is effective tracing point on any one road in the K road, then effective tracing point
Subpoint on any one road is effective tracing point；If effective tracing point is not in the K road
On, then each effective tracing point is calculated on the K road according to the projection point calculating method of preset point to road
Subpoint.
Specifically, each effective tracing point is calculated described according to the projection point calculating method of preset point to road
Subpoint on K road, comprising:
Assuming that P1、P2For any two points, the P on road3For outside road a bit, P0For the subpoint of arbitrary point to road；Cause
For P0、P1、P2All on same straight line, it is possible to determine scale factor k* (P2-P1)=P0-P1, wherein k=| P0-P1|/
|P2-P1|；
Enable V1=P3-P2, V0=P2-P1；Then V1*V2=cos (seta) | P3-P1||P2-P1|=| P0-P1|*|P2-P1|；
Further, according to the value of k, subpoint P can be determined0。
It should be noted that the shortest distance of point to line is a little to arrive the vertical range of line, that is, put the throwing with point on straight line
The distance between shadow point, therefore, in the present solution, subpoint with each effective tracing point on the K road, makees
For the candidate state of each effective tracing point.
S103 calculates the matching distance and any two between each effective tracing point and corresponding candidate state
Goal displacement cost between a adjacent effective tracing point, the goal displacement cost are adjacent effective track
The transfer value of effective transfer path between point.
Specifically, Euclidean distance of the matching distance between two o'clock, during calculating the matching distance,
In order to improve calculating speed and prevent from calculating error, generated each generally according to the candidate state of each effective tracing point
The candidate state collection of effective tracing point；Each effective tracing point is calculated separately to concentrate each with corresponding candidate state
The Euclidean distance of candidate state obtains the matching distance.
As shown in figure 4, being the specific implementation flow chart of S103 in Fig. 1, as shown in Figure 4, S103, comprising:
S1031, calculates the Euclidean distance between each effective tracing point and corresponding candidate state, it is described it is European away from
From for the matching distance.
It should be noted that during calculating matching distance, according to the acquisition time of each effective tracing point,
Generate the sequence of effective tracing point；If the candidate state collection for having effective tracing point be it is empty (may for invalid tracing point,
Or the position incomplete in electronic map), it is determined that whether the matching status of presently described effective tracing point is init state；
If the matching status of presently described effective tracing point is init state, it is determined that the acquisition time of presently described effective tracing point
With that whether the time interval of the acquisition time of the last one effective tracing point in the sequence of effective tracing point is less than is pre-
If break period threshold value (for example, sampling time interval that preset break period threshold value is 6 times)；If be less than preset interruption
Between threshold value, it is determined that presently described effective tracing point is invalid tracing point, skips presently described effective tracing point, obtain with it is current
The adjacent next effective tracing point of effective tracing point simultaneously calculates the matching distance；
If more than preset break period threshold value, it is determined that presently described effective tracing point is in the infull position of electronic map
It sets, sets doubtful new line state for presently described effective tracing point；
Illusion matching detection is carried out to the sequence of effective tracing point.
Specifically, carrying out illusion matching detection to the sequence of effective tracing point includes: to assume presently described effective rail
Mark point is in the position that road network is not complete in electronic map, then the quantity of the candidate state of presently described effective tracing point is less than default
Candidate state amount threshold, the frequency interrupted by the presently described effective tracing point triggering matching of determination can determine described
Whether the sequence of effective tracing point is in artifacts matching status.
Specifically, if the frequency that presently described effective tracing point triggering matching is interrupted is greater than or equal to preset frequency threshold
Value；Then determine that the currently active tracing point is in doubtful new line state, the sequence of effective tracing point is in artifacts matching status；
Specifically, when matching distance of the effective tracing point at least two road is zero, matching can be triggered and interrupted.
If the frequency that triggering matching is interrupted is less than the preset frequency threshold, it is determined that presently described effective tracing point is
The sequence of invalid tracing point, effective tracing point is in non-artifacts matching status.
S1032 obtains the candidate state of each effective tracing point respectively, is generated according to preset Path Planning
The candidate state sequence of each effective tracing point.
Since each effective tracing point generally includes multiple candidate states, during path planning, basis is needed
Position of the candidate state of adjacent effective tracing point in electronic map, corresponding candidate state is matched, and is formed
The corresponding coupling path in electronic map, in the present solution, for convenience the candidate state of adjacent effective tracing point it
Between matching generated each according to positional relationship of the candidate state of each effective tracing point in corresponding electronic map
The candidate state sequence of effective tracing point carries out the matching between corresponding candidate state by candidate state sequence, can be with
Improve the matched accuracy of candidate state.
S1033, respectively by the candidate shape in the candidate state sequence of the adjacent effective tracing point of any two
State is matched, and effective transfer path between the candidate state of the adjacent effective tracing point of any two is obtained.
In general, the adjacent effective tracing point of any two includes equal number of candidate state, respectively will pass through
Candidate state in the candidate state sequence of the adjacent effective tracing point of any two is matched, and can be appointed
It anticipates two adjacent effective tracing points corresponding path on the electronic map, specifically, the adjacent institute of any two
State effective tracing point on the electronic map corresponding path be the adjacent effective tracing point of any two candidate shape
Transfer path between state.
Further, according to preset Invalid path deletion rule from the transfer path, it is adjacent that any two are deleted
Effective tracing point candidate state between invalid transfer path, obtain effective transfer path.
Specifically, comprising:
If the length of the transfer path between the adjacent effective tracing point of any two is two adjacent described with this
The difference of linear distance between effective tracing point is greater than preset distance difference threshold value, it is determined that the transfer path is invalid turns
It moves path and deletes；
Alternatively, according to transfer path and effective tracing point between the adjacent effective tracing point of any two
Average speed of the acquisition time interval calculation vehicle between any two adjacent effective tracing points；If having any two
Average speed between a adjacent effective tracing point is greater than preset vehicle speed thresholds, it is determined that any two phase
Transfer path between adjacent effective tracing point is invalid transfer path and deletes.
S1034 matches effective transfer path from electronic map, and according to preset transfer value calculation formula
Calculate the transfer value of effective transfer path.
Specifically, the transfer value occurs in violation of rules and regulations in driving process on effective transfer path for assessing vehicle
The probability that behavior pays for, optionally, the transfer value table of effective transfer path between adjacent effective tracing point
It is shown as:
Wherein,For transfer value, drouteIndicate effective transfer path distance, TturnIt indicates effectively to turn
It moves in path and turns to number, TroadclassIndicate that category of roads changes in effective transfer path, TownershipIndicate effectively transfer road
Road is transferred to the number in outer lane, T from inside lane in diameterruleIndicate rule-breaking vehicle driving behavior number, the w1、w2、w3、w4
It is preset weight coefficient.
It should be noted that transfer value introduces displacement behavior penalty term on the basis of transfer path, can make to match road
Diameter more meets true driving behavior, promotes matching accuracy rate.
S104 constructs linear path adaptation function based on the matching distance and the goal displacement cost.
Specifically, the linear path adaptation function are as follows:
Wherein, g is coupling path score, and μ is preset coefficient of balance, and n is the number of effective tracing point, and i is indicated i-th
Effective tracing point,For the matching distance of i-th of effective tracing point and p-th of candidate state,It is
Transfer value in i-1 effectively tracing points in q-th of candidate state and i-th of effective tracing point between p-th of candidate state,
Q-th of candidate state and p-th of candidate state in described i-th effective tracing point are phase in described (i-1)-th effective tracing point
The candidate state mutually matched.
S105 solves the linear path adaptation function, obtains the matching of effective tracing point of vehicle on the electronic map
Path.
Specifically, in practical applications, when needing the sequence to effective tracing point of continuous acquisition to carry out route matching,
Triggering solves the linear path adaptation function, or when to some effective tracing point in the sequence of effective tracing point
When candidate state determines, when determining that effective tracing point is doubtful new line state, need to trigger solving the linear path matching
Function further can be used the thought of Dynamic Programming to solve the linear path adaptation function, obtain so that the matching
Effective transfer road between the candidate state and the candidate state of the smallest each effective tracing point of the score in path
The road that diameter is constituted.Specifically, in the present solution, measure the superiority and inferiority of coupling path by the score of the coupling path, when
The smaller coupling path for indicating to obtain of the score of coupling path is more excellent, the coupling path that the score minimum of coupling path indicates
For optimal path.
Specifically, as shown in figure 5, being the specific implementation flow chart of S105 in Fig. 1, as shown in Figure 5, S105, comprising:
S1051 solves the linear path adaptation function based on dimension bit algorithm, obtains the coupling path score most
Small value.
Specifically, dimension bit algorithm is to solve for the common method of Hidden Markov problem, mainly uses Dynamic Programming
Thought solved.In the present solution, by map match problem be considered as Hidden Markov (Hidden Markov Model,
HMM) problem, still, common Hidden Markov construct the index letter about transition probability during carrying out map match
Number, so that calculation amount is very big because probability multiplication calculating causes evaluation index exponentially grade to increase.This programme by building matching away from
From the linear function with goal displacement cost, more practical significance, while can avoid leading to evaluation index because of probability multiplication calculating
Exponentially grade increases.
S1052, when the coupling path score minimum, the candidate state of corresponding each effective tracing point and
The road that effective transfer path between the candidate state is constituted is the matching of effective tracing point of vehicle on the electronic map
Path.
Specifically, the calculated result of the linear path adaptation function indicates coupling path score, when the coupling path
The value of score is smaller, indicates that match point is closer with initial trace point and coupling path cost is smaller.
By above-mentioned analysis it is found that map-matching method proposed by the present invention, comprising: the track data based on vehicle obtains
Effective tracing point of the vehicle；Determine that the candidate state of each effective tracing point, the candidate state are described effective
Upright projection point of the tracing point on the K road in matching range；Calculate each effective tracing point and corresponding candidate
Goal displacement cost between the adjacent effective tracing point of matching distance and any two between state, the target turn
Move the transfer value of effective transfer path of the cost between adjacent effective tracing point；Based on the matching distance and
The goal displacement cost constructs linear path adaptation function；The linear path adaptation function is solved, the effective of vehicle is obtained
The coupling path of tracing point on the electronic map.By determining each matching effectively between tracing point and corresponding candidate state
Goal displacement cost between distance and the adjacent effective tracing point of any two, and construct the matching distance with it is described
The linear path adaptation function of goal displacement cost cares for simultaneously to reduce the matching error between track of vehicle and physical location
Avoid the incomplete or inaccurate factor of electronic map, be arranged without matching status, avoiding matching by force leads to showing for coupling path distortion
As occurring, by solving the linear path adaptation function, the accuracy rate of map match is improved.
Fig. 6 is the illustrative view of functional configuration of map matching means provided by the invention.As shown in fig. 6, the ground of the reality example
Figure coalignment 6 includes: to obtain module 610, determining module 620, computing module 630, building module 640 and solve module
650.Wherein,
Module 610 is obtained, effective tracing point of the vehicle is obtained for the track data based on vehicle；
Determining module 620, for determining that the candidate state of each effective tracing point, the candidate state have to be described
Imitate upright projection point of the tracing point on the K road in matching range；
Computing module 630, for calculating the matching distance between each effective tracing point and corresponding candidate state,
And the goal displacement cost between the adjacent effective tracing point of any two, the goal displacement cost are described adjacent
Effective tracing point between effective transfer path transfer value；
Module 640 is constructed, for based on the matching distance and goal displacement cost building linear path matching
Function；
It solves module 650 and obtains effective tracing point of vehicle electronically for solving the linear path adaptation function
Coupling path on figure.
Further, the track data includes acquisition time and location information；Obtain module 610, comprising:
First determination unit, for determining abnormal tracing point according to the acquisition time and the location information；
Culling unit obtains effective tracing point for rejecting the abnormal tracing point in the track data.
Further, it is determined that module 620, comprising:
Second determination unit, for determining each effective tracing point on the electronic map according to preset positioning accuracy
Matching range；
First acquisition unit, the K road in the matching range for obtaining each effective tracing point respectively；
Second acquisition unit, for obtaining upright projection point of each effective tracing point on the K road, institute
State the candidate state that upright projection point is each effective tracing point.
Further, computing module 630, comprising:
First computing unit, for calculate the straight line between each effective tracing point and corresponding candidate state away from
From the linear distance is the matching distance；
Third acquiring unit, for obtaining the candidate state of each effective tracing point respectively, according to preset path planning
The candidate state collection of each effective tracing point of strategy generating；
Pairing unit, for respectively carrying out the candidate state sequence of the adjacent effective tracing point of any two
Pairing obtains effective transfer path between the candidate state of the adjacent effective tracing point of any two；
Second computing unit, for matching effective transfer path from electronic map map, and according to preset
Transfer value calculation formula calculates the transfer value of effective transfer path.
Further, the goal displacement cost between adjacent effective tracing point indicates are as follows:
Wherein, drouteIndicate transfer path distance, TturnIt indicates to turn to number, T in transfer pathroadclassIndicate transfer
Category of roads changes in path, TownershipRoad is transferred to the number in outer lane, T from inside lane in expression transfer pathruleTable
Show rule-breaking vehicle driving behavior number, the w1、w2、w3、w4It is preset weight coefficient.
Further, the linear path adaptation function are as follows:
Wherein, g is coupling path score, and μ is preset coefficient of balance, and n is the number of effective tracing point, and i is indicated i-th
Effective tracing point,For the matching distance of i-th of effective tracing point and p-th of candidate state,It is
Transfer value in i-1 effectively tracing points in q-th of candidate state and i-th of effective tracing point between p-th of candidate state,
Q-th of candidate state and p-th of candidate state in described i-th effective tracing point are phase in described (i-1)-th effective tracing point
The candidate state mutually matched.
Further, module 650 is solved, comprising:
Unit is solved, for solving the linear path adaptation function based on dimension bit algorithm, obtains the coupling path
The minimum value of score；
Third determination unit, when the coupling path score minimum, the candidate of corresponding each effective tracing point
The road that effective transfer path between state and the candidate state is constituted is effective tracing point of vehicle in electronic map
On coupling path.
Fig. 7 is the schematic diagram of server provided by the invention.As shown in fig. 7, the server 7 of the embodiment includes: processing
Device 70, memory 71 and it is stored in the computer program 72 that can be run in the memory 71 and on the processor 70,
Such as map matching program.The processor 70 realizes that above-mentioned each map-matching method is real when executing the computer program 72
Apply the step in example, such as step 101 shown in FIG. 1 is to 105.Alternatively, the processor 70 executes the computer program 72
The function of each module/unit in the above-mentioned map matching means embodiment of Shi Shixian, such as the function of module 610 to 650 shown in Fig. 6
Energy.
Illustratively, the computer program 72 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 71, and are executed by the processor 70, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 72 in the server 7 is described.For example, the computer program 72 can be divided
At obtaining module, determining module, computing module, building module and solving module (module in virtual bench), each module has
Body function is as follows:
Module is obtained, effective tracing point of the vehicle is obtained for the track data based on vehicle；
Determining module, for determining that the candidate state of each effective tracing point, the candidate state are described effective
Upright projection point of the tracing point on the K road in matching range；
Computing module, for calculating the matching distance between each effective tracing point and corresponding candidate state, with
And the goal displacement cost between the adjacent effective tracing point of any two, the goal displacement cost are described adjacent
The transfer value of effective transfer path between effective tracing point；
Module is constructed, for matching letter based on the matching distance and goal displacement cost building linear path
Number；
It solves module and obtains effective tracing point of vehicle in electronic map for solving the linear path adaptation function
On coupling path.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On communication unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Computer-readable Jie
Matter may include: can carry the computer program code any entity or device, recording medium, USB flash disk, mobile hard disk,
Magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (13)
1. a kind of map-matching method characterized by comprising
Track data based on vehicle obtains effective tracing point of the vehicle；
Determine that the candidate state of each effective tracing point, the candidate state are effective tracing point in matching range
K road on subpoint；
Calculate matching distance between each effective tracing point and corresponding candidate state and the adjacent institute of any two
State the goal displacement cost between effective tracing point, the goal displacement cost having between adjacent effective tracing point
Imitate the transfer value of transfer path；
Linear path adaptation function is constructed based on the matching distance and the goal displacement cost；
The linear path adaptation function is solved, the coupling path of effective tracing point of vehicle on the electronic map is obtained.
2. map-matching method as described in claim 1, which is characterized in that the track data includes acquisition time and position
Information；
The track data based on vehicle obtains effective tracing point of the vehicle, comprising:
Abnormal tracing point and dwell point are determined according to the acquisition time and the location information；
Abnormal tracing point and the dwell point in the track data are rejected, effective tracing point is obtained.
3. map-matching method as claimed in claim 2, which is characterized in that the time of each effective tracing point of determination
Select state, comprising:
The matching range of each effective tracing point on the electronic map is determined according to preset positioning accuracy；
K road in the matching range of each effective tracing point is obtained respectively；
Subpoint of each effective tracing point on the K road is obtained, the subpoint is each effective rail
The candidate state of mark point.
4. map-matching method as claimed in claim 3, which is characterized in that described to obtain each effective tracing point in institute
The subpoint on K road is stated, the subpoint is the candidate state of each effective tracing point, comprising:
If there is effective tracing point on any one road in the K road, effective tracing point is at described
The subpoint anticipated on a road is effective tracing point；
If effective tracing point is not on the K road, according to the projection point calculating method of preset point to road
Calculate subpoint of each effective tracing point on the K road.
5. map-matching method as claimed in claim 2, which is characterized in that it is described calculate each effective tracing point with it is right
Transfer value between the adjacent effective tracing point of the matching distance between candidate state and any two answered, packet
It includes:
The Euclidean distance between each effective tracing point and corresponding candidate state is calculated, the Euclidean distance is described
With distance；
The candidate state for obtaining each effective tracing point respectively has according to the generation of preset Path Planning is each described
Imitate the candidate state sequence of tracing point；
The candidate state in the candidate state sequence of the adjacent effective tracing point of any two is matched respectively,
Obtain effective transfer path between the candidate state of the adjacent effective tracing point of any two；
Effective transfer path is matched from electronic map map, and institute is calculated according to preset transfer value calculation formula
State the transfer value of effective transfer path.
6. map-matching method as claimed in claim 5, which is characterized in that it is described calculate each effective tracing point with it is right
The Euclidean distance between candidate state answered, the Euclidean distance are the matching distance, comprising:
According to the acquisition time of each effective tracing point, the sequence of effective tracing point is generated；
If there is the candidate state collection of effective tracing point for sky, it is determined that whether the matching status of presently described effective tracing point
For init state；
If the matching status of presently described effective tracing point is init state, it is determined that the acquisition of presently described effective tracing point
Whether time and the time interval of the acquisition time of the last one effective tracing point in the sequence of effective tracing point are small
In default break period threshold value；
If being less than preset break period threshold value, it is determined that presently described effective tracing point is invalid tracing point, skips current institute
State effective tracing point, obtain the next effective tracing point adjacent with presently described effective tracing point and calculate it is described match away from
From；
If more than preset break period threshold value, it is determined that presently described effective tracing point is in the infull position of electronic map,
Doubtful new line state is set by presently described effective tracing point；
Illusion matching detection is carried out to the sequence of effective tracing point.
7. map-matching method as claimed in claim 6, which is characterized in that the sequence to effective tracing point carries out
Illusion matching detection, comprising:
If the frequency that presently described effective tracing point triggering matching is interrupted is greater than or equal to preset frequency threshold；It then determines current
Effective tracing point is in doubtful new line state, and the sequence of effective tracing point is in artifacts matching status；
If the frequency that triggering matching is interrupted is less than the preset frequency threshold, it is determined that presently described effective tracing point is invalid
The sequence of tracing point, effective tracing point is in non-artifacts matching status.
8. map-matching method as claimed in claim 5, which is characterized in that the transfer value of effective transfer path indicates
Are as follows:
Wherein,Indicate transfer value, drouteIndicate effective transfer path distance, TturnIndicate effectively transfer road
Number, T are turned in diameterroadclassIndicate that category of roads changes in effective transfer path, TownershipIt indicates in effective transfer path
Road is transferred to the number in outer lane, T from inside laneruleIndicate rule-breaking vehicle driving behavior number, the w1、w2、w3、w4It is
Preset weight coefficient.
9. map-matching method as described in claim 1, which is characterized in that the linear path adaptation function are as follows:
Wherein, g is coupling path score, and μ is preset coefficient of balance, and n is the number of effective tracing point, and i-th of i expression effective
Tracing point,For the matching distance of i-th of effective tracing point and p-th of candidate state,Have for (i-1)-th
Imitate the transfer value in tracing point in q-th of candidate state and i-th of effective tracing point between p-th of candidate state, described the
Q-th of candidate state is mutually paired with p-th of candidate state in described i-th effective tracing point in i-1 effectively tracing points
Candidate state.
10. map-matching method as claimed in claim 9, which is characterized in that it is described to solve the linear path adaptation function,
Obtain the coupling path of effective tracing point of vehicle on the electronic map, comprising:
The linear path adaptation function is solved based on dimension bit algorithm, obtains the minimum value of the coupling path score；
When the coupling path score minimum, the candidate state of corresponding each effective tracing point and the candidate shape
The road that effective transfer path between state is constituted is the coupling path of effective tracing point of vehicle on the electronic map.
11. a kind of map matching means characterized by comprising
Module is obtained, effective tracing point of the vehicle is obtained for the track data based on vehicle；
Determining module, for determining that the candidate state of each effective tracing point, the candidate state are effective track
Subpoint of the point on the K road in matching range；
Computing module, for calculating the matching distance between each effective tracing point and corresponding candidate state, Yi Jiren
The goal displacement cost anticipated between two adjacent effective tracing points, the goal displacement cost are described adjacent effective
The transfer value of effective transfer path between tracing point；
Module is constructed, for constructing linear path adaptation function based on the matching distance and the goal displacement cost；
It solves module, for solving the linear path adaptation function, obtains effective tracing point of vehicle on the electronic map
Coupling path.
12. a kind of server, including memory, processor and storage can transport in the memory and on the processor
Capable computer program, which is characterized in that the processor realizes that claims 1 to 10 such as is appointed when executing the computer program
The step of one map-matching method.
13. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization map-matching method as described in any one of claims 1 to 10 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599214.8A CN110375753B (en) | 2019-07-04 | 2019-07-04 | Map matching method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599214.8A CN110375753B (en) | 2019-07-04 | 2019-07-04 | Map matching method, device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110375753A true CN110375753A (en) | 2019-10-25 |
| CN110375753B CN110375753B (en) | 2022-04-29 |
Family
ID=68251984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910599214.8A Active CN110375753B (en) | 2019-07-04 | 2019-07-04 | Map matching method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110375753B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956336A (en) * | 2019-12-13 | 2020-04-03 | 上海中旖能源科技有限公司 | Driving route mining method based on graph algorithm |
| CN111780774A (en) * | 2020-06-09 | 2020-10-16 | 当家移动绿色互联网技术集团有限公司 | Motion trajectory generation method and device, storage medium and electronic equipment |
| CN112013853A (en) * | 2020-08-20 | 2020-12-01 | 北京三快在线科技有限公司 | Method and device for verifying track points of unmanned equipment |
| CN112013856A (en) * | 2020-08-27 | 2020-12-01 | 上海钧正网络科技有限公司 | Track fitting method, device, terminal and medium based on road network and track data |
| CN112509356A (en) * | 2020-10-30 | 2021-03-16 | 深圳市跨越新科技有限公司 | Vehicle driving route generation method and system |
| CN112748451A (en) * | 2021-01-26 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Track processing method and device, electronic equipment and medium |
| CN112825160A (en) * | 2019-11-21 | 2021-05-21 | 北京图森智途科技有限公司 | State transition library construction method, path planning method and related equipment |
| CN112985430A (en) * | 2019-12-13 | 2021-06-18 | 百度在线网络技术（北京）有限公司 | Map matching disaster recovery method, device, equipment and storage medium |
| CN112991722A (en) * | 2021-02-03 | 2021-06-18 | 浙江浙大中控信息技术有限公司 | Method and system for predicting real-time intersection of bus at high-frequency gps point |
| CN112985371A (en) * | 2019-12-12 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Path determination method, device and equipment |
| CN113029163A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle path matching method and device, computer equipment and storage medium |
| CN113029171A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle path matching method and device, computer equipment and storage medium |
| CN113050621A (en) * | 2020-12-22 | 2021-06-29 | 北京百度网讯科技有限公司 | Trajectory planning method and device, electronic equipment and storage medium |
| CN113380049A (en) * | 2021-07-27 | 2021-09-10 | 京东城市(北京)数字科技有限公司 | Violation detection method and device for vehicle, server and storage medium |
| CN114360240A (en) * | 2021-12-06 | 2022-04-15 | 合肥湛达智能科技有限公司 | High-precision positioning method based on vehicle networking track characteristics |
| WO2022161315A1 (en) * | 2021-01-26 | 2022-08-04 | 深圳市普渡科技有限公司 | Robot path planning method, operation method, robot and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011067472A1 (en) * | 2009-12-03 | 2011-06-09 | Teconer Oy | Method and system for mapping road conditions by means of terminals |
| US20140358414A1 (en) * | 2013-06-01 | 2014-12-04 | Faroog Ibrahim | System and method for creating, storing, and updating local dynamic MAP database with safety attribute |
| CN104197945A (en) * | 2014-08-27 | 2014-12-10 | 浙江工业大学 | Global voting map matching method based on low-sampling-rate floating vehicle data |
| CN105444769A (en) * | 2015-11-26 | 2016-03-30 | 北京百度网讯科技有限公司 | Map matching method and device |
| CN106595680A (en) * | 2016-12-15 | 2017-04-26 | 福州大学 | Vehicle GPS data map matching method based on hidden markov model |
| CN106855415A (en) * | 2017-01-09 | 2017-06-16 | 北京京东尚科信息技术有限公司 | Map-matching method and system |
| CN107742126A (en) * | 2017-09-26 | 2018-02-27 | 南京航空航天大学 | A kind of Floating Car map-matching method based on hidden Markov model |
| CN108362293A (en) * | 2018-02-24 | 2018-08-03 | 中电福富信息科技有限公司 | A kind of track of vehicle matching process based on key point technology |
-
2019
- 2019-07-04 CN CN201910599214.8A patent/CN110375753B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011067472A1 (en) * | 2009-12-03 | 2011-06-09 | Teconer Oy | Method and system for mapping road conditions by means of terminals |
| US20140358414A1 (en) * | 2013-06-01 | 2014-12-04 | Faroog Ibrahim | System and method for creating, storing, and updating local dynamic MAP database with safety attribute |
| CN104197945A (en) * | 2014-08-27 | 2014-12-10 | 浙江工业大学 | Global voting map matching method based on low-sampling-rate floating vehicle data |
| CN105444769A (en) * | 2015-11-26 | 2016-03-30 | 北京百度网讯科技有限公司 | Map matching method and device |
| CN106595680A (en) * | 2016-12-15 | 2017-04-26 | 福州大学 | Vehicle GPS data map matching method based on hidden markov model |
| CN106855415A (en) * | 2017-01-09 | 2017-06-16 | 北京京东尚科信息技术有限公司 | Map-matching method and system |
| CN107742126A (en) * | 2017-09-26 | 2018-02-27 | 南京航空航天大学 | A kind of Floating Car map-matching method based on hidden Markov model |
| CN108362293A (en) * | 2018-02-24 | 2018-08-03 | 中电福富信息科技有限公司 | A kind of track of vehicle matching process based on key point technology |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112825160A (en) * | 2019-11-21 | 2021-05-21 | 北京图森智途科技有限公司 | State transition library construction method, path planning method and related equipment |
| CN112985371A (en) * | 2019-12-12 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Path determination method, device and equipment |
| CN112985371B (en) * | 2019-12-12 | 2023-02-28 | 杭州海康威视数字技术股份有限公司 | Path determination method, device and equipment |
| CN110956336B (en) * | 2019-12-13 | 2023-05-30 | 中海服信息科技股份有限公司 | Driving route mining method based on graph algorithm |
| CN112985430A (en) * | 2019-12-13 | 2021-06-18 | 百度在线网络技术（北京）有限公司 | Map matching disaster recovery method, device, equipment and storage medium |
| CN110956336A (en) * | 2019-12-13 | 2020-04-03 | 上海中旖能源科技有限公司 | Driving route mining method based on graph algorithm |
| CN113029163A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle path matching method and device, computer equipment and storage medium |
| CN113029171A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle path matching method and device, computer equipment and storage medium |
| CN111780774A (en) * | 2020-06-09 | 2020-10-16 | 当家移动绿色互联网技术集团有限公司 | Motion trajectory generation method and device, storage medium and electronic equipment |
| CN112013853A (en) * | 2020-08-20 | 2020-12-01 | 北京三快在线科技有限公司 | Method and device for verifying track points of unmanned equipment |
| CN112013853B (en) * | 2020-08-20 | 2022-07-15 | 北京三快在线科技有限公司 | Method and device for verifying track points of unmanned equipment |
| CN112013856A (en) * | 2020-08-27 | 2020-12-01 | 上海钧正网络科技有限公司 | Track fitting method, device, terminal and medium based on road network and track data |
| CN112509356A (en) * | 2020-10-30 | 2021-03-16 | 深圳市跨越新科技有限公司 | Vehicle driving route generation method and system |
| CN112509356B (en) * | 2020-10-30 | 2022-04-05 | 深圳市跨越新科技有限公司 | Vehicle driving route generation method and system |
| CN113050621A (en) * | 2020-12-22 | 2021-06-29 | 北京百度网讯科技有限公司 | Trajectory planning method and device, electronic equipment and storage medium |
| CN113050621B (en) * | 2020-12-22 | 2023-04-28 | 北京百度网讯科技有限公司 | Track planning method, track planning device, electronic equipment and storage medium |
| CN112748451B (en) * | 2021-01-26 | 2022-04-22 | 腾讯科技（深圳）有限公司 | Track processing method and device, electronic equipment and medium |
| WO2022161315A1 (en) * | 2021-01-26 | 2022-08-04 | 深圳市普渡科技有限公司 | Robot path planning method, operation method, robot and medium |
| CN112748451A (en) * | 2021-01-26 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Track processing method and device, electronic equipment and medium |
| CN112991722A (en) * | 2021-02-03 | 2021-06-18 | 浙江浙大中控信息技术有限公司 | Method and system for predicting real-time intersection of bus at high-frequency gps point |
| CN113380049A (en) * | 2021-07-27 | 2021-09-10 | 京东城市(北京)数字科技有限公司 | Violation detection method and device for vehicle, server and storage medium |
| CN113380049B (en) * | 2021-07-27 | 2023-06-23 | 京东城市(北京)数字科技有限公司 | Method, device, server and storage medium for detecting vehicle violations |
| CN114360240A (en) * | 2021-12-06 | 2022-04-15 | 合肥湛达智能科技有限公司 | High-precision positioning method based on vehicle networking track characteristics |
| CN114360240B (en) * | 2021-12-06 | 2023-09-19 | 合肥湛达智能科技有限公司 | High-precision positioning method based on Internet of vehicles track characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110375753B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110375753A (en) | Map-matching method, device, server and storage medium | |
| CN106574975B (en) | Trace matching using peripheral signals | |
| CN106781478B (en) | Trajectory tracking method based on LTE (Long term evolution) signaling data | |
| CN109782763A (en) | A kind of method for planning path for mobile robot under dynamic environment | |
| CN109697221A (en) | Method for digging, device, storage medium and the electronic equipment of track rule | |
| CN109612474B (en) | Map road matching method, map road matching device, map road matching server and storage medium | |
| CN108827307A (en) | Air navigation aid, device, terminal and computer readable storage medium | |
| KR20150124396A (en) | System and Method for Location Determination, Mapping, and Data Management through Crowdsourcing | |
| CN106912018A (en) | Map-matching method and system based on signaling track | |
| Lv et al. | Outlier trajectory detection: A trajectory analytics based approach | |
| CN104900059A (en) | Method for enhancing cell phone base station positioning precision by using Hidden Markov map-matching algorithm | |
| CN105091889A (en) | Hotspot path determination method and hotspot path determination equipment | |
| CN102395192A (en) | Method and device for locating wireless sensor terminal | |
| CN107968987B (en) | RSSI weighted centroid positioning method based on fixed integral combined with environmental parameters | |
| CN107229033A (en) | Multiple target reaching time-difference localization method based on height dimension sectioning search | |
| CN106658701A (en) | Positioning method and apparatus | |
| CN105629198A (en) | Indoor multi-target tracking method using density-based fast search clustering algorithm | |
| CN110399365A (en) | Determination method, apparatus, storage medium and the electronic equipment of map missing road | |
| CN106355203A (en) | Method and system for classifying crowds participating in activity | |
| CN109974699A (en) | A kind of robot and its autonomous heuristic approach of map and device | |
| CN103607772A (en) | Taylor positioning algorithm based on LMBP (Levenberg-Marquardt Back Propagation) neural network | |
| Carrabs et al. | An adaptive heuristic approach to compute upper and lower bounds for the close-enough traveling salesman problem | |
| Song et al. | Hidden Markov model and driver path preference for floating car trajectory map matching | |
| CN110830915B (en) | Method and device for determining starting point position | |
| CN106294485A (en) | Determine the method and device in notable place |
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 |