CN107221195A - Automobile track Forecasting Methodology and track level map - Google Patents
Automobile track Forecasting Methodology and track level map Download PDFInfo
- Publication number
- CN107221195A CN107221195A CN201710384424.6A CN201710384424A CN107221195A CN 107221195 A CN107221195 A CN 107221195A CN 201710384424 A CN201710384424 A CN 201710384424A CN 107221195 A CN107221195 A CN 107221195A
- Authority
- CN
- China
- Prior art keywords
- road section
- vehicle
- road
- track
- numbering
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses automobile track Forecasting Methodology and track level map, the level of vehicle current driving road segment can be judged using historical trajectory data and track level map datum, in the case of being particularly layered at the path space level conversion such as viaduct, judge this car and subject vehicle whether in same section level, three dimensions scope whether there is risk of collision, so as to inhibit false alarm.
Description
Technical field
Field, specifically related to road adaptive forecasting method are driven the invention belongs to Vehicular intelligent.
Background technology
Intersection collision warning systems (Intersection Collision Warning System, ICWS) are first
Enter drive assist system (Advanced Driver Assistance Systems, ADAS) important component, for road
Road traffic, can prevent the collision accident of intersection and increase the traffic efficiency of intersection.
Intersection collision warning systems of the prior art based on radar, based on V2X systems are only used for two dimensional surface traffic,
False early warning is easily occurred into as potential threat for the vehicle in Different Plane level by mistake in multilevel traffic, driver is influenceed
Normal driving.
Therefore, it is necessary to a kind of road vehicle Forecasting Methodology based on three dimensions is provided, it is excellent before vehicle collision prewarning
First judge Ben Che and object car space road information, avoid the disjoint section vehicle in space from collision wrong report occur.
The content of the invention
Automobile track disclosed by the invention Forecasting Methodology, high frequency time is mapped out by vehicle historical track point and two-dimensional map
Road section ID, numbers so as to be accurately judged to road section ID residing for Current vehicle, improves this car future travel path forecasting accuracy.
Automobile track disclosed by the invention Forecasting Methodology, comprises the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Interior for the previous period one group vehicle location, the course information data of current point in time are gathered by satellite fix, are formed
One group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency, will appear from frequency highest road section ID and is set as that the road section ID residing for Current vehicle in three dimensions is compiled
Number.
It is further, further comprising the steps of,
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
Invention additionally discloses automobile track Forecasting Methodology, high frequency is mapped out by vehicle historical track point and two-dimensional map
Secondary road section ID, is obtained by mulitpath form fit on vehicle historical track shape two-dimensional map corresponding with current vehicle position
Road form fit road section ID is obtained, fusion high frequency time road section ID matches road section ID with road shape, so as to be accurately judged to current
Road section ID residing for vehicle is numbered, and improves this car future travel path forecasting accuracy.
Automobile track disclosed by the invention Forecasting Methodology, comprises the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
Road shape is matched into the road section ID numbering road section ID numbering high with frequency of occurrence and merges judgement, is drawn residing for Current vehicle
Road section ID is numbered.
Further, the road shape matching road section ID numbering road section ID numbering high with frequency of occurrence, which is merged, is judged as weighting
Fusion method, selects the corresponding road section ID numberings that matching degree is high and frequency of occurrence is high and is numbered as road section ID residing for vehicle.
It is further, further comprising the steps of,
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
Invention additionally discloses automobile track Forecasting Methodology, high frequency is mapped out by vehicle historical track point and two-dimensional map
Secondary road section ID, passes through the road direction of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle
Match somebody with somebody, obtain road direction matching ID numberings, fusion high frequency time road section ID matches road section ID with road direction, so as to be accurately judged to
Road section ID residing for Current vehicle is numbered, and improves this car future travel path forecasting accuracy.
Automobile track disclosed by the invention Forecasting Methodology, comprises the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
Road direction is matched into the ID numberings road section ID numbering high with frequency of occurrence and merges judgement, section residing for Current vehicle is drawn
ID is numbered.
Further, the road direction matching road section ID numbering road section ID numbering high with frequency of occurrence, which is merged, is judged as weighting
Fusion method, selects the corresponding road section ID numberings that matching degree is high and frequency of occurrence is high and is numbered as road section ID residing for vehicle.
It is further, further comprising the steps of,
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
Invention additionally discloses automobile track Forecasting Methodology, high frequency is mapped out by vehicle historical track point and two-dimensional map
Secondary road section ID, is obtained by mulitpath form fit on vehicle historical track shape two-dimensional map corresponding with current vehicle position
Road form fit road section ID is obtained, passes through multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle
Road direction matching obtain road direction matching ID numberings, fusion high frequency time road section ID, road shape matching road section ID and road
Road direction matches road section ID, is numbered so as to be accurately judged to road section ID residing for Current vehicle, improves this car future travel path pre-
Survey accuracy.
Automobile track disclosed by the invention Forecasting Methodology, comprises the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
The high road section ID numbering of the frequency, road shape matching road section ID numbering and road direction matching ID numbering fusions is will appear to sentence
It is disconnected, show that road section ID residing for Current vehicle is numbered.
Further, the high road section ID numbering of frequency of occurrence, road shape matching road section ID numbering and road direction matching
ID numbering fusions are judged as Weighted Fusion method, select shape, direction matching degree height and the high corresponding road section ID of frequency of occurrence
Numbering is numbered as road section ID residing for vehicle.
It is further, further comprising the steps of,
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
The invention also discloses track level map, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level.
Further, the track level map is stored on vehicle or on Cloud Server.
Advantageous effects of the present invention are：
1）Track level map is comprising two-dimensional map and can distinguish on two-dimensional map the unique of every road three dimensions level
Road section ID is numbered, different from commonly dimensionally picture library, this dimensionally picture library pass through Unique ID and distinguish different spaces section, will
Three-dimensional data can be compressed to greatest extent, while the need for satisfaction acquisition section three-dimensional data carries out traveling judgement to it again.
2）Vehicle running history tracing point is obtained, and each tracing point is mapped on two-dimensional map, each tracing point pair
Mulitpath is answered, is numbered by counting the road section ID that frequency of occurrence is high in this group of historical track point, so as to uniquely judge current vehicle
Three dimensions road section ID where, by the method for historical track correspondence two-dimensional map path probability, improves current location institute
Locate the accuracy that path judges, and computational efficiency is high.
3) the corresponding shape of vehicle running history tracing point is mapped to current vehicle position multigroup on two-dimensional map
Section form fit, can match the high current road segment ID of matching degree, three dimensions can be just realized using 2-D data
Position judgment, improves judging efficiency；
4）By multigroup section course matching on the two-dimensional map corresponding with current vehicle position of the current course of vehicle, it can match
Go out the high current road segment ID of matching degree, the position judgment of three dimensions can be just realized using 2-D data using 2-D data,
Improve judging efficiency；
5）Three groups of road section ID judged results of advantage 2,3,4 are weighted fusion, current road segment ID is improved and judges precision.
6）Judge the collision possibility of this car and subject vehicle on two-dimensional map, there is risk of collision, judging three-dimensional
Whether space road section ID intersects, non-intersect, does not alarm；Wrong report is substantially reduced, solves based on two-dimensional space to judge in the prior art
The wrong report problem of vehicle collision.
Brief description of the drawings
Fig. 1 is Vehicular system block diagram of the present invention；
Fig. 2 is the first pass figure that vehicle collision is judged using this automobile track Forecasting Methodology；
Fig. 3 is the second flow chart that vehicle collision is judged using this automobile track Forecasting Methodology；
Fig. 4 is the 3rd flow chart that vehicle collision is judged using this automobile track Forecasting Methodology；
Fig. 5 is the 4th flow chart that vehicle collision is judged using this automobile track Forecasting Methodology；
Fig. 6 is to judge vehicle collision application scenario diagram using this automobile track Forecasting Methodology；
Wherein, 1- short-range wireless communication modules, 2- satellite positioning modules, 3- tracks level map library module, 4- control units module,
5- alarm modules, 6- this car, 7- subject vehicles.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.
As shown in Fig. 2 automobile track Forecasting Methodology, comprises the following steps,
1）Level map in track in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguished on two-dimensional map
Unique road section ID numbering of every road three dimensions level；
2）Collection storage historical track：
Interior for the previous period one group vehicle location, the course information data of current point in time are gathered by satellite fix, are formed
One group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency, will appear from frequency highest road section ID and is set as that the road section ID residing for Current vehicle in three dimensions is compiled
Number.
So far, track prediction is completed, and can be used as intelligent automobile driving and be judged basic, such as addition following steps 4)
To make collision judgment.Its basic application principle is：It is two-dimentional when the numbering of the road section ID residing for Current vehicle in three dimensions is determined
The travel path in the section was both determined on map, can be judged according to current vehicle position by the road section information on two-dimensional map
This car future travel track, road vehicle is adaptively predicted.
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；The determination methods of this car future travel track are not limited to；Such as, it can just be confirmed according to current road segment ID following one section
The path in the time section, both the vehicle path to be travelled；Or, according to current vehicle location, direct of travel and Vehicular yaw
Angular speed predicts that this car future travel track has been well known intelligent automobile field vehicle route anticipation mode；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
As shown in figure 3, automobile track Forecasting Methodology, comprises the following steps,
1）Level map in track in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguished on two-dimensional map
Unique road section ID numbering of every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
By road shape matching road section ID numbering with the high road section ID numbering Weighted Fusion of frequency of occurrence, select matching degree height and
The high corresponding road section ID numberings of frequency of occurrence are numbered as road section ID residing for vehicle.
So far, track prediction is completed, and can be used as intelligent automobile driving and be judged basic, such as addition following steps 4)
To make collision judgment.
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
As shown in figure 4, automobile track Forecasting Methodology, comprises the following steps,
1）Level map in track in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguished on two-dimensional map
Unique road section ID numbering of every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
By road direction matching ID numbering with the high road section ID numbering Weighted Fusion method of frequency of occurrence, select matching degree height and
The high corresponding road section ID numberings of frequency of occurrence are numbered as road section ID residing for vehicle.
So far, track prediction is completed, and can be used as intelligent automobile driving and be judged basic, such as addition following steps 4)
To make collision judgment.
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
As shown in figure 5, automobile track Forecasting Methodology, comprises the following steps,
1）Level map in track in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguished on two-dimensional map
Unique road section ID numbering of every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
The high road section ID numbering of the frequency, road shape matching road section ID numbering and road direction matching ID numbering weightings is will appear to melt
Conjunction method, selects the corresponding road section ID that shape, direction matching degree are high and frequency of occurrence is high and numbers as road section ID residing for vehicle
Numbering；
So far, track prediction is completed, and can be used as intelligent automobile and drive to judge basic, such as addition following steps 4) make
Collision judgment.
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
As shown in figure 1, track level map library module 3, preserves dimensionally picture library, comprising two-dimensional map and two dimension can be distinguished
Unique road section ID numbering of every road three dimensions level on map.Track level map in track level map library module 3
It is stored on vehicle or is obtained from Cloud Server.
As shown in figure 1, automotive system, including：Short-range wireless communication module 1, satellite positioning module 2, track level map office
Module 3, control unit module 4；
Short-range wireless communication module 1, satellite positioning module 2 and track level map library module 3 are used as data input cell and control
Unit module 4 is communicated to connect；
Short-range wireless communication module 1 receives the driving information of 7 transmissions of object car from surrounding（Including：Position, course and speed
Spend information）, send that information to control unit module 4；
Satellite positioning module 2 receives the driving information of this car 6 by satellite positioning method（Including：Position, course and velocity information）,
And send that information to control unit 4；
Track level map library module 3 is dimensionally picture library, and block is comprising two-dimensional map and can distinguish every road on two-dimensional map
Unique road section ID numbering of three dimensions level；
Control unit module 4, according to the driving information of satellite positioning module 2, this car is mapped on two-dimensional map and matched pair
Answer path and its road section ID to number, judge this car future travel track.Control unit module 4 can also be according to short-distance wireless communication
The object car driving information that module 1 is sent, judges this car and object car collision situation.
As shown in fig. 6, in the disjoint overpass scene of three dimensions, the section 1 under overpass of this car 6 is travelled, right
As vehicle 7, section 2 is travelled on overpass, according to intersection collision warning algorithm in existing intelligent automobile technology two-dimensional map,
There is no the consideration of spatial level, section 1 is projected in two-dimensional map plane with section 2 joining, in fact it could happen that false alarm；
Using technical scheme disclosed by the invention, it is possible to use historical trajectory data and road level map datum judge vehicle current driving
The level in section（It is layered at the path space level conversion such as viaduct）, judge this car and subject vehicle not in same section layer
It is secondary, without risk of collision, so as to inhibit false alarm.
Claims (10)
1. automobile track Forecasting Methodology, it is characterised in that：Comprise the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Interior for the previous period one group vehicle location, the course information data of current point in time are gathered by satellite fix, are formed
One group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency, will appear from frequency highest road section ID and is set as that the road section ID residing for Current vehicle in three dimensions is compiled
Number.
2. automobile track Forecasting Methodology, it is characterised in that：Comprise the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
Road shape is matched into the road section ID numbering road section ID numbering high with frequency of occurrence and merges judgement, is drawn residing for Current vehicle
Road section ID is numbered.
3. automobile track as claimed in claim 2 Forecasting Methodology, it is characterised in that：Road shape matching road section ID numbering is with going out
The high road section ID numbering fusion of the existing frequency is judged as Weighted Fusion method, selects matching degree height and the high corresponding road of frequency of occurrence
Section ID numberings are numbered as road section ID residing for vehicle.
4. automobile track Forecasting Methodology, it is characterised in that：Comprise the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
Road direction is matched into the ID numberings road section ID numbering high with frequency of occurrence and merges judgement, section residing for Current vehicle is drawn
ID is numbered.
5. automobile track as claimed in claim 4 Forecasting Methodology, it is characterised in that：Road direction matching road section ID numbering is with going out
The high road section ID numbering fusion of the existing frequency is judged as Weighted Fusion method, selects matching degree height and the high corresponding road of frequency of occurrence
Section ID numberings are numbered as road section ID residing for vehicle.
6. automobile track Forecasting Methodology, it is characterised in that：Comprise the following steps,
1）The track level map in information of vehicles is transferred, the track level map includes two-dimensional map and can distinguish two-dimensional map
Unique road section ID numbering of upper every road three dimensions level；
2）Collection storage historical track：
Position, the course information data, shape of interior for the previous period the one group vehicle of current point in time are gathered by satellite fix
Into one group of vehicle running history tracing point；
3）Judge that road section ID residing for Current vehicle is numbered：
By step 2）In one group of vehicle running history tracing point project track level map in two-dimensional map on, a vehicle
The multiple road section ID numberings of running history tracing point correspondence, obtain this group of vehicle running history tracing point corresponding road section ID numbering and occur
The high road section ID of the frequency；
Multiple roads in the trajectory shape two-dimensional map corresponding with current vehicle location that vehicle running history tracing point is constituted
ID road shape matching, obtains road shape matching road section ID numbering；
By the road direction matching of multiple road ID in the two-dimensional map corresponding with current vehicle location of the current course of vehicle, obtain
Road direction matching ID numberings；
The high road section ID numbering of the frequency, road shape matching road section ID numbering and road direction matching ID numbering fusions is will appear to sentence
It is disconnected, show that road section ID residing for Current vehicle is numbered.
7. automobile track as claimed in claim 6 Forecasting Methodology, it is characterised in that：The high road section ID numbering of frequency of occurrence, road
Road form fit road section ID numbering and road direction matching ID numbering fusions are judged as Weighted Fusion method, select shape, side
Numbered to the corresponding road section ID numberings that matching degree is high and frequency of occurrence is high as road section ID residing for vehicle.
8. the automobile track Forecasting Methodology as described in claim 1 or 2 or 4 or 6, it is characterised in that：It is further comprising the steps of,
4）Predict future travel track and alarm
According to this car future travel rail on the vehicle running history tracing point of this car, yaw rate prediction two-dimensional map
Mark, or according to residing for Current vehicle road section ID numbering and two-dimensional map on Current vehicle position judgment this car future travel rail
Mark；
The future travel track of surroundings car is obtained by vehicle communication；
When finding that object car drives into cross street and when having risk of collision on two-dimensional map, road section ID is compiled according to residing for Current vehicle
Number and subject vehicle residing for road section ID numbering, judge in three dimensions, this car whether with object bus or train route footpath intersect；
It is intersecting, alarm；It is non-intersect, not alarm.
9. track level map, it is characterised in that：The track level map includes two-dimensional map and can distinguish every on two-dimensional map
Unique road section ID numbering of bar road three dimensions level.
10. level map in track as claimed in claim 9, it is characterised in that：Track level map be stored on vehicle or
On Cloud Server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384424.6A CN107221195B (en) | 2017-05-26 | 2017-05-26 | Automobile lane prediction method and lane level map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384424.6A CN107221195B (en) | 2017-05-26 | 2017-05-26 | Automobile lane prediction method and lane level map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107221195A true CN107221195A (en) | 2017-09-29 |
| CN107221195B CN107221195B (en) | 2020-03-17 |
Family
ID=59945458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710384424.6A Active CN107221195B (en) | 2017-05-26 | 2017-05-26 | Automobile lane prediction method and lane level map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107221195B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
| CN110174892A (en) * | 2019-04-08 | 2019-08-27 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the computer readable storage medium of vehicle direction |
| CN110489510A (en) * | 2019-08-23 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Processing method, device, readable storage medium storing program for executing and the computer equipment of road data |
| EP3640679A1 (en) | 2018-10-15 | 2020-04-22 | Zenuity AB | A method for assigning ego vehicle to a lane |
| CN111337045A (en) * | 2020-03-27 | 2020-06-26 | 北京百度网讯科技有限公司 | Vehicle navigation method and device |
| CN111626097A (en) * | 2020-04-09 | 2020-09-04 | 吉利汽车研究院（宁波）有限公司 | Method and device for predicting future trajectory of obstacle, electronic equipment and storage medium |
| CN111788571A (en) * | 2018-03-15 | 2020-10-16 | 蓝色视觉实验室英国有限公司 | Vehicle tracking |
| CN112130137A (en) * | 2020-09-17 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Method and device for determining lane-level track and storage medium |
| WO2022007143A1 (en) * | 2020-07-09 | 2022-01-13 | 惠州市德赛西威智能交通技术研究院有限公司 | Roadside internet of vehicles device, flyover road segment identification method, and vehicle-mounted internet of vehicles device |
| US20220172618A1 (en) * | 2019-04-12 | 2022-06-02 | Continental Automotive Systems, Inc. | Electronic Control Device For A Vehicle And Method For Reducing Intersection False-Positive Detection |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101788298A (en) * | 2008-10-31 | 2010-07-28 | 歌乐牌株式会社 | Guider and air navigation aid |
| CN103175536A (en) * | 2011-12-22 | 2013-06-26 | 罗伯特·博世有限公司 | Method for displaying object on display of navigation system in simply and 3-D manner |
| CN103557870A (en) * | 2013-10-09 | 2014-02-05 | 董路 | Dynamic trajectory navigation method and cloud platform |
| CN104680838A (en) * | 2013-11-28 | 2015-06-03 | 三星电子（中国）研发中心 | Safety assisting method and system for automobile |
| CN104916133A (en) * | 2015-06-09 | 2015-09-16 | 福建工程学院 | Road altitude information extraction method and system based on traffic track data |
| US20150281677A1 (en) * | 2013-02-20 | 2015-10-01 | Intel Corporation | Real-time automatic conversion of 2-dimensional images or video to 3-dimensional stereo images or video |
| US20160092068A1 (en) * | 2014-09-30 | 2016-03-31 | International Business Machines Corporation | Visualization of addresses |
| CN105893565A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术（北京）有限公司 | Method and device for establishing a three-dimensional map database and transmitting three-dimensional map data |
| CN106251699A (en) * | 2016-08-19 | 2016-12-21 | 深圳市元征科技股份有限公司 | Vehicle running collision method for early warning and device |
-
2017
- 2017-05-26 CN CN201710384424.6A patent/CN107221195B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101788298A (en) * | 2008-10-31 | 2010-07-28 | 歌乐牌株式会社 | Guider and air navigation aid |
| CN103175536A (en) * | 2011-12-22 | 2013-06-26 | 罗伯特·博世有限公司 | Method for displaying object on display of navigation system in simply and 3-D manner |
| US20150281677A1 (en) * | 2013-02-20 | 2015-10-01 | Intel Corporation | Real-time automatic conversion of 2-dimensional images or video to 3-dimensional stereo images or video |
| CN103557870A (en) * | 2013-10-09 | 2014-02-05 | 董路 | Dynamic trajectory navigation method and cloud platform |
| CN104680838A (en) * | 2013-11-28 | 2015-06-03 | 三星电子（中国）研发中心 | Safety assisting method and system for automobile |
| US20160092068A1 (en) * | 2014-09-30 | 2016-03-31 | International Business Machines Corporation | Visualization of addresses |
| CN104916133A (en) * | 2015-06-09 | 2015-09-16 | 福建工程学院 | Road altitude information extraction method and system based on traffic track data |
| CN105893565A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术（北京）有限公司 | Method and device for establishing a three-dimensional map database and transmitting three-dimensional map data |
| CN106251699A (en) * | 2016-08-19 | 2016-12-21 | 深圳市元征科技股份有限公司 | Vehicle running collision method for early warning and device |
Non-Patent Citations (1)
| Title |
|---|
| 张林: "动态车辆导航系统车道级路径引导方法研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111788571A (en) * | 2018-03-15 | 2020-10-16 | 蓝色视觉实验室英国有限公司 | Vehicle tracking |
| CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
| CN108629978B (en) * | 2018-06-07 | 2020-12-22 | 重庆邮电大学 | Traffic track prediction method based on high-dimensional road network and recurrent neural network |
| EP3640679A1 (en) | 2018-10-15 | 2020-04-22 | Zenuity AB | A method for assigning ego vehicle to a lane |
| US11776392B2 (en) | 2018-10-15 | 2023-10-03 | Zenuity Ab | Method for assigning ego vehicle to a lane |
| CN110174892A (en) * | 2019-04-08 | 2019-08-27 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the computer readable storage medium of vehicle direction |
| US20220172618A1 (en) * | 2019-04-12 | 2022-06-02 | Continental Automotive Systems, Inc. | Electronic Control Device For A Vehicle And Method For Reducing Intersection False-Positive Detection |
| CN110489510A (en) * | 2019-08-23 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Processing method, device, readable storage medium storing program for executing and the computer equipment of road data |
| CN110489510B (en) * | 2019-08-23 | 2022-05-20 | 腾讯科技（深圳）有限公司 | Road data processing method and device, readable storage medium and computer equipment |
| CN111337045A (en) * | 2020-03-27 | 2020-06-26 | 北京百度网讯科技有限公司 | Vehicle navigation method and device |
| CN111626097A (en) * | 2020-04-09 | 2020-09-04 | 吉利汽车研究院（宁波）有限公司 | Method and device for predicting future trajectory of obstacle, electronic equipment and storage medium |
| WO2022007143A1 (en) * | 2020-07-09 | 2022-01-13 | 惠州市德赛西威智能交通技术研究院有限公司 | Roadside internet of vehicles device, flyover road segment identification method, and vehicle-mounted internet of vehicles device |
| CN112130137A (en) * | 2020-09-17 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Method and device for determining lane-level track and storage medium |
| CN112130137B (en) * | 2020-09-17 | 2023-10-20 | 杭州海康威视数字技术股份有限公司 | Method, device and storage medium for determining lane-level track |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107221195B (en) | 2020-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107221195A (en) | Automobile track Forecasting Methodology and track level map | |
| KR101901024B1 (en) | Map update determination system | |
| CN104217590B (en) | Method for making the electronic controller in main vehicle determine traffic density | |
| CN102473346B (en) | Vehicle controller, control method for vehicle and control system for vehicle | |
| CN102132335B (en) | Traveling environment recognition device | |
| CN102449672B (en) | Vehicular peripheral surveillance device | |
| EP2826687B1 (en) | Technique for lane assignment in a vehicle | |
| CN110060467A (en) | Prediction meanss, prediction technique and storage medium | |
| US20220198842A1 (en) | Predictive analytics for vehicle health | |
| CN115552200A (en) | Method and system for generating importance occupancy grid map | |
| CN105206108A (en) | Early warning method against vehicle collision based on electronic map | |
| CN108292475A (en) | The generation method and device of the prediction information of vehicles used in the traveling of road vehicle net | |
| EP3551968A1 (en) | Advanced threat warning for autonomous vehicles | |
| CN113223326B (en) | Multi-vehicle multi-control multi-source low-speed auxiliary parking system based on road side | |
| CN107200016A (en) | Road adaptive forecasting method and the Vehicular system using this method | |
| CN105806353A (en) | Automatic driving device | |
| Kim et al. | Design of integrated risk management-based dynamic driving control of automated vehicles | |
| CN105976606A (en) | Intelligent urban traffic management platform | |
| WO2012129437A2 (en) | Driver assistance system | |
| CN103221665A (en) | Driving support system and driving support managing device | |
| CN106355890A (en) | Method and device for judging classification of target vehicle | |
| CN104742901A (en) | Method and control device and detection device for recognizing an entry of a motor vehicle into a traffic lane opposite a driving direction | |
| CN112445226A (en) | Method for autonomous driving of a maneuver plan navigating around a parked vehicle | |
| US20230419830A1 (en) | Determining right of way | |
| US20230168368A1 (en) | Guardrail estimation method based on multi-sensor data fusion, and vehicle-mounted device |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170929 Assignee: CHONGQING CHANGAN NEW ENERGY AUTOMOBILE TECHNOLOGY Co.,Ltd. Assignor: Chongqing Changan Automobile Co.,Ltd. Contract record no.: X2021500000014 Denomination of invention: Vehicle lane prediction method and lane level map Granted publication date: 20200317 License type: Common License Record date: 20211014 |
|
| EE01 | Entry into force of recordation of patent licensing contract |