CN105448108B - A kind of hypervelocity method of discrimination based on Hidden Markov road network - Google Patents
A kind of hypervelocity method of discrimination based on Hidden Markov road network Download PDFInfo
- Publication number
- CN105448108B CN105448108B CN201511018790.7A CN201511018790A CN105448108B CN 105448108 B CN105448108 B CN 105448108B CN 201511018790 A CN201511018790 A CN 201511018790A CN 105448108 B CN105448108 B CN 105448108B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- vehicle
- probability
- road
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of hypervelocity method of discrimination based on Hidden Markov road network, on the basis of existing satellite positioning device, realize that Vehicle Speed monitors and can determine that whether vehicle exceeds the speed limit in this running section in real time, the cost of vehicle monitoring is reduced on the basis of high-accuracy is kept.The best matching path proposed by the present invention that position error can be effectively reduced based on Hidden Markov algorithm and vehicle traveling is accurately found out.According to the database for the national road speed limit size set up, the maximum travelling speed of the speed that vehicle is travelled and the road, which is compared, obtains the conclusion whether vehicle traveling exceeds the speed limit, if hypervelocity so reminds driver vehicle to exceed the speed limit by guider.
Description
Technical field
It is particularly a kind of to be based on Hidden Markov road network the present invention relates to physical field, more particularly to e measurement technology
Hypervelocity method of discrimination.
Background technology
With the continuous improvement of living standard, automobile quantity is also continued to increase.The problem of bringing is car accident quantity
It is constantly soaring.It is most also generally the maximum traffic violation of harmfulness, more than 90% particularly serious friendship that overspeed of vehicle traveling, which is,
Interpreter's event is relevant with hypervelocity.Because driving over the speed limit greatly prolongs braking distance, the processing crisis time greatly shortens, and driver runs into
Often it is caught unprepared when dangerous.Meanwhile, driving over the speed limit also easily makes one fatigue, because chance of overtaking other vehicles increases, and vehicular gap shortens,
The energy expenditure for driving human psychological and body is greatly increased.Drive over the speed limit and also increase the working strength and operating load of vehicle,
Component wear is exacerbated, tyre temperature can particularly raised and triggers accident etc. of blowing out, is sentenced so being badly in need of vehicle traveling hypervelocity
Determine technology.Therefore, China sets different road driving speed limits according to different sections of highway, different time sections.
Current vehicle is largely mounted with the Big Dipper/gps satellite positioner, and this is to realize whether software approach judges vehicle
Hypervelocity brings opportunity.This method is on the basis of existing satellite positioning device, and design monitoring software realizes Vehicle Speed
Monitor in real time and can determine that whether vehicle exceeds the speed limit in this running section, this greatly reduces vehicle monitoring cost.It is existing
In technology, judge whether vehicle exceeds the speed limit using the location information collected according to the Big Dipper/gps satellite alignment system extensively.
But, the drift of the Big Dipper/gps satellite positioning signal and low sampling rate influence the accuracy of location data, so as to be difficult to judge car
Whether exceed the speed limit.
The content of the invention
It is an object of the invention to provide a kind of hypervelocity method of discrimination based on Hidden Markov road network, described this
The drift of satellite positioning signal in the prior art will be solved and low by planting the hypervelocity method of discrimination based on Hidden Markov road network
The technical problem that sample rate influence overspeed of vehicle judges.
A kind of hypervelocity method of discrimination based on Hidden Markov road network of the present invention, including one obtain from satellite and position
The process of data, during the acquisition location data from satellite, comprises the following steps：
Step one：The optimal running section of vehicle is found out using Hidden Markov road network algorithm；
Step 2：The details of vehicle running section, including speed limit size are found out using electronic map, car is therefrom found out
The path of traveling simultaneously obtains the maximum travelling speed in these paths, corresponding road section speed limit is obtained from road speed limit database big
It is small；
Step 3：From satellite obtain location data in obtain Vehicle Speed, and by described Vehicle Speed with
The speed limit in the section is compared, and is differentiated to whether vehicle traveling exceeds the speed limit.
Further, comprise the steps in described step one：
The step of one calculating observation probability, first by anchor point ztIn each road closed on riOn possibility definition
For observation probability p (zt|ri), it is assumed that point ztSubpoint to each road is xt,i, the great circle of coordinate points and candidate's subpoint away from
From for | | zt,i-xt,i||greatcircle, anchor point zt+1Subpoint to each road is xt+1,j, subpoint xt,iTo subpoint
xt+1,jVehicle operating range is referred to as being designated as | | xt+1,j-xt.i||route,
Assuming that position error is obeys the Gaussian Profile of zero-mean, then observation probability is：
Wherein σzFor anchor point ztStandard error；
The step of one calculating initial observation probability, utilize initial observation probability πiRepresent before road network near
Section in find out probability of the vehicle in this section, have with first fix data points as the starting point of initial observation probability
πi=p (z1|ri),
The step of calculating road transition probability, represents that vehicle exists between moment t to moment t+1 using road transition probability
The transition probability between road is matched, p (q are expressed ast+1=rj|qt=ri), definition draws base respectively in terms of distance and speed two
In the transition probability p of anchor point distancel(qt+1=rj|qt=ri) and based on the transition probability p for positioning spot speedv(qt+1=rj|qt
=ri)：
pv(qt+1=rj|qt=ri)=V (ri→rj).F(ri→rj) (3)
Wherein,
I in formula*,j*The real running section of vehicle is represented, β is used to adjust dtInfluence to result
Size, sets β=mediant(||ri-rj| |)/ln (2),
U represents the section number around t anchor point, | | zt-zt+1||EuclidenceDis tan ceRepresent earth surface arc
Linear distance, e'u.v the maximal rate in section is represented,Represent average speed, F (ri→rj) represent between former and later two time points
Observation station and real candidate point information, when both distance more near then transition probabilities it is bigger, V (ri→rj) represent former and later two
The rate information at time point, when the more similar then probability of the intensity of variation of Mean Speed and maximum rate is bigger；
The step of calculating vehicle optimal running section, is calculated using above-mentioned formula (1), formula (2) and viterbi algorithm
The optimal path travelled to vehicle, the path one status switch of correspondence, so that the optimal section of vehicle traveling is inferred to, in institute
T state is calculated in the viterbi algorithm stated for the probability in i all single paths and maximum max (δ are therefrom found outt
(i)), using formula (2) as path transition probability, and likelihood is setWhen the phase of each path probability of t
Use formula (3) as the path transition probability at the moment when being less than the threshold value of setting like rate, then obtain the another set moment
Path probability and therefrom select maximum probability, repeated the above steps at the t+1 moment, calculating all observation probabilities and transfer is general
After rate, the best match road at last moment is determined, and the first moment vehicle is reversely released to last moment vehicle with this
The best matching path of traveling, finally exports the optimal running section of vehicle of vehicle traveling.
Further, in described step two, each sections of road speed limit database is set up.
Further, in described step three, when the speed that vehicle is travelled is more than the section speed limit, driver has been pointed out
Through hypervelocity.
It is to reduce the important technology guarantee of vehicle safety accident rate that hypervelocity, which differentiates, is using computer software technology as base
Plinth, the Data Analysis Services technology whether vehicle exceeds the speed limit is judged by particular model and algorithm.According to the Big Dipper/gps satellite positioning
The location information that system acquisition is obtained, reduces the influence that drift and low sampling rate are brought, by vehicle driving trace using algorithm
It is fitted on corresponding section, the speed limit size that Vehicle Speed then is obtained into corresponding road section with retrieval is contrasted, finally
Judge whether vehicle traveling exceeds the speed limit.
HMM proposed by the present invention can effectively reduce position error and accurately find out vehicle
The best matching path of traveling.Then according to set up national road speed limit size database, by the speed of vehicle travel
The maximum travelling speed of degree and the road, which is compared, obtains the conclusion whether vehicle traveling exceeds the speed limit, if hypervelocity is so by leading
Boat device reminds driver vehicle to exceed the speed limit.The present invention is using software engineering to the vehicle travelled on different sections of highway in difference
Whether the period, which exceeds the speed limit, is differentiated, substantially increase hypervelocity differentiation rate, and can real-time reminding driver whether exceed the speed limit, from
And reduce the incidence of accident.
The present invention compares with prior art, and its effect is positive and obvious.The present invention is in existing satellite positioning device
On the basis of, realize that Vehicle Speed monitors and can determine that whether vehicle exceeds the speed limit in this running section in real time, protecting
Hold the cost that vehicle monitoring is reduced on the basis of high-accuracy.
Brief description of the drawings
Fig. 1 is the schematic diagram of the hypervelocity method of discrimination based on Hidden Markov road network of the present invention.
Embodiment
Embodiment 1:
As shown in figure 1, a kind of hypervelocity method of discrimination based on Hidden Markov road network of the present invention, including one from defending
Star obtains the process of location data, during the acquisition location data from satellite, comprises the following steps：
Step one：The optimal running section of vehicle is found out using Hidden Markov road network algorithm；
Step 2：The details of vehicle running section are found out using electronic map, and therefrom find sections of road most
Big speed.
Step 3：From satellite obtain location data in obtain Vehicle Speed, and by described Vehicle Speed with
The speed limit in the section is compared, and is differentiated to whether vehicle traveling exceeds the speed limit.
Further, comprise the steps in described step one：
1. calculating observation probability：
Anchor point ztReally in each road closed on riOn possibility, be defined as observation probability p (zt|ri)；Assuming that
Point ztSubpoint to each road is xt,i, the great-circle distance of coordinate points and candidate's subpoint is | | zt,i-xt,i||greatcircle。
Anchor point zt+1Subpoint to each road is xt+1,j, subpoint xt,iTo subpoint xt+1,jVehicle operating range is referred to as " path
Distance " is designated as | | xt+1,j-xt.i||route；
Assuming that position error is obeys the Gaussian Profile of zero-mean, then observation probability is：
Wherein σzFor anchor point ztStandard error.
2. calculate initial observation probability：
Initial observation probability πiRepresent before road network, vehicle is found out from neighbouring section in the general of this section
Rate.Generally there is π as the starting point of initial observation probability with first anchor pointi=p (z1|ri)。
3. calculate road transition probability：
Transition probability refers to transition probability of the vehicle between matching road between moment t to moment t+1, is expressed as p
(rj|ri).The present invention does not consider the information between observation station, and passage path show that road transfering probability distribution is apart from distance：
pv(qt+1=rj|qt=ri)=V (ri→rj).F(ri→rj) (3)
WhereinI in formula*,j*Represent the real running section of vehicle.β is used to adjust dtTo result
Influence size.General setting β=mediant(||ri-rj||)/ln(2)。
U represents the section number around t anchor point, | | zt-zt+1||EuclidenceDistanceRepresent earth surface camber line
Distance.e'u.v the maximal rate in section is represented,Represent average speed, F (ri→rj) represent between former and later two time points
The information of anchor point and real candidate point, when both more near then transition probabilities of distance are bigger.V(ri→rj) when representing former and later two
Between the rate information put, when the more similar then probability of the intensity of variation of Mean Speed and maximum rate is bigger.
4. export the optimal running section of vehicle
The optimal path for obtaining vehicle traveling is calculated using formula (1), formula (2) and viterbi algorithm.Viterbi is utilized
The thought of Dynamic Programming obtains maximum probability path i.e. optimal path, and this paths correspond to a status switch, so as to infer
Go out the optimal section of vehicle traveling.
Need to calculate t state for the probability in i all single paths in viterbi algorithm and therefrom find out most
Big value max (δt(i)), it is contemplated that the problem of amount of calculation, using formula (2) as road transition probability, but when path probability phase
The optimal path and actual path matching precision that difference is drawn when smaller according to the calculating transition probability be not high.Due to being shifted in calculating
Probability is continuously multiplied and causes obtained single path probability less and less, so needing to introduce the concept of a likelihood.If
Likelihood, then think therefrom to sentence when the likelihood of t each path probability is less than the threshold value of setting
Break and optimal path, it is necessary to using formula (3) as the road transition probability at the moment because formula (3) introduce velocity standard can
More accurately to obtain road transition probability.Then obtain the path probability of another set t and therefrom select maximum probability.
The t+1 moment repeats the above steps.
After all observation probabilities and transition probability are calculated, the best match road at last moment is determined, and with this
The best matching path that the first moment vehicle is travelled to last moment vehicle is reversely released, final output vehicle most preferably travels road
Section.
Step 2: setting up the database of each section maximum travelling speed.
Step 3: the speed and the speed in the section that are obtained using the GPS/ Big Dippeves are contrasted, whether vehicle traveling is surpassed
Speed is differentiated.
Claims (3)
1. a kind of hypervelocity method of discrimination based on Hidden Markov road network, including from the process of satellite acquisition location data,
It is characterized in that：During the acquisition location data from satellite, comprise the following steps：
Step one：The optimal running section of vehicle is found out using Hidden Markov road network algorithm；Also wrapped in described step one
Include following step：
The step of one calculating observation probability, first by anchor point ztIn each road closed on riOn possibility be defined as see
Survey Probability p (zt|ri), it is assumed that point ztSubpoint to each road is xt,i, the great-circle distance of coordinate points and candidate's subpoint is |
|zt,i-xt,i||greatcircle, anchor point zt+1Subpoint to each road is xt+1,j, subpoint xt,iTo subpoint xt+1,jCar
Operating range is referred to as being designated as | | xt+1,j-xt.i||route,
Assuming that position error is obeys the Gaussian Profile of zero-mean, then observation probability is：
<mrow>
<mi>p</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>z</mi>
<mi>t</mi>
</msub>
<mo>|</mo>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<msqrt>
<mrow>
<mn>2</mn>
<mi>&pi;</mi>
</mrow>
</msqrt>
<msub>
<mi>&sigma;</mi>
<mi>z</mi>
</msub>
</mrow>
</mfrac>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mn>0.5</mn>
<msup>
<mrow>
<mo>(</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>z</mi>
<mrow>
<mi>t</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>t</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
<mo>|</mo>
<msub>
<mo>|</mo>
<mrow>
<mi>g</mi>
<mi>r</mi>
<mi>e</mi>
<mi>a</mi>
<mi>t</mi>
<mi>c</mi>
<mi>i</mi>
<mi>r</mi>
<mi>c</mi>
<mi>l</mi>
<mi>e</mi>
</mrow>
</msub>
</mrow>
<msub>
<mi>&sigma;</mi>
<mi>z</mi>
</msub>
</mfrac>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein σzFor anchor point ztStandard error,
The step of one calculating initial observation probability, utilize initial observation probability πiRepresent before road network from neighbouring road
Probability of the vehicle in this section is found out in section, has π as the starting point of initial observation probability with first fix data pointsi=
p(z1|ri)；
The step of one calculating road transition probability, represent that vehicle exists between moment t to moment t+1 using road transition probability
The transition probability between road is matched, p (q are expressed ast+1=rj|qt=ri), wherein qtFor the running section of t automobile, from away from
From definition draws transition probability p with a distance from based on anchor point respectively with the aspect of speed twol(qt+1=rj|qt=ri) and based on positioning
The transition probability p of spot speedv(qt+1=rj|qt=ri)：
<mrow>
<msub>
<mi>p</mi>
<mi>l</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>q</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>r</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msub>
<mi>q</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>&alpha;e</mi>
<mrow>
<mo>-</mo>
<msub>
<mi>&beta;d</mi>
<mi>t</mi>
</msub>
</mrow>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
pv(qt+1=rj|qt=ri)=V (ri→rj).F(ri→rj) (3)
Wherein,
Wherein dtRepresent t subpointTo subpointOperating range, i in formula*,j*Point
I-th of real section and j-th of real section are not represented, and β is used to adjust dtInfluence size to result, sets β=mediant
(||ri-rj| |)/ln (2),
<mrow>
<mi>F</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>&RightArrow;</mo>
<msub>
<mi>r</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>z</mi>
<mi>t</mi>
</msub>
<mo>-</mo>
<msub>
<mi>z</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>|</mo>
<msub>
<mo>|</mo>
<mrow>
<mi>E</mi>
<mi>u</mi>
<mi>c</mi>
<mi>l</mi>
<mi>i</mi>
<mi>d</mi>
<mi>e</mi>
<mi>a</mi>
<mi>n</mi>
<mi>D</mi>
<mi>i</mi>
<mi>s</mi>
<mi>tan</mi>
<mi>c</mi>
<mi>e</mi>
</mrow>
</msub>
</mrow>
<mrow>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>r</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msub>
<mo>|</mo>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>u</mi>
<mi>t</mi>
<mi>e</mi>
</mrow>
</msub>
</mrow>
</mfrac>
</mrow>
<mrow>
<mi>V</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>&RightArrow;</mo>
<msub>
<mi>r</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>u</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</msubsup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>e</mi>
<mi>u</mi>
<mo>&prime;</mo>
</msubsup>
<mo>.</mo>
<mi>v</mi>
<mo>&times;</mo>
<msub>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msqrt>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>u</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>e</mi>
<mi>u</mi>
<mo>&prime;</mo>
</msubsup>
<mo>.</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>&times;</mo>
<msqrt>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>u</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
</mfrac>
</mrow>
U represents the section number around t anchor point, | | zt-zt+1||EuclidenceDistanceEarth surface camber line distance is represented,
e'u.v the maximal rate in section is represented,Represent average speed, F (ri→rj) represent observation station between former and later two time points
With the information of real candidate point, when both distance more near then transition probabilities it is bigger, V (ri→rj) represent former and later two time points
Rate information, when the more similar then probability of the intensity of variation of Mean Speed and maximum rate is bigger；
The step of one calculating vehicle optimal running section, calculated using above-mentioned formula (1), formula (2) and viterbi algorithm
The optimal path travelled to vehicle, the path one status switch of correspondence, so that the optimal section of vehicle traveling is inferred to, in dimension
Spy is than calculating t state for the probability in i all single paths and therefrom finding out maximum max (δ in algorithmt(i)), make
With formula (2) as path transition probability, and set likelihoodWherein a, b represent that t vehicle match is arrived respectively
Probability on two paths, use formula (3) to be used as this when the likelihood of t each path probability is less than the threshold value of setting
The path transition probability at moment, then obtained the path probability at another set moment and therefrom selects maximum probability, at the t+1 moment
Repeat the above steps, after all observation probabilities and transition probability is calculated, determine the best match road at last moment, and
The best matching path that the first moment vehicle is travelled to last moment vehicle is reversely released with this, the car of vehicle traveling is finally exported
Optimal running section；
Step 2：The details of vehicle running section are found out using electronic map, and therefrom find the maximum speed of sections of road
Degree；
Step 3：From satellite obtain location data in obtain Vehicle Speed, and by described Vehicle Speed and the road
The speed limit of section is compared, and is differentiated to whether vehicle traveling exceeds the speed limit.
2. the hypervelocity method of discrimination according to claim 1 based on Hidden Markov road network, it is characterised in that：It is described
The step of two in, set up each sections of road speed limit database.
3. the hypervelocity method of discrimination according to claim 1 based on Hidden Markov road network, it is characterised in that：It is described
The step of three in, vehicle travel speed be more than the section speed limit when, point out driver exceeded the speed limit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511018790.7A CN105448108B (en) | 2015-12-30 | 2015-12-30 | A kind of hypervelocity method of discrimination based on Hidden Markov road network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511018790.7A CN105448108B (en) | 2015-12-30 | 2015-12-30 | A kind of hypervelocity method of discrimination based on Hidden Markov road network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105448108A CN105448108A (en) | 2016-03-30 |
| CN105448108B true CN105448108B (en) | 2017-10-03 |
Family
ID=55558232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511018790.7A Active CN105448108B (en) | 2015-12-30 | 2015-12-30 | A kind of hypervelocity method of discrimination based on Hidden Markov road network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105448108B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127586A (en) * | 2016-06-17 | 2016-11-16 | 上海经达信息科技股份有限公司 | Vehicle insurance rate aid decision-making system under big data age |
| CN106095963B (en) * | 2016-06-17 | 2019-12-06 | 上海经达信息科技股份有限公司 | Vehicle driving behavior analysis big data public service platform under internet + era |
| CN106197445B (en) * | 2016-06-30 | 2019-07-02 | 百度在线网络技术（北京）有限公司 | A kind of method and device of route planning |
| CN106683418A (en) * | 2016-12-15 | 2017-05-17 | 清华大学苏州汽车研究院（吴江） | Vehicle overspeed real-time analyzing system and vehicle overspeed real-time analyzing method |
| 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 |
| CN108492563B (en) * | 2018-04-12 | 2020-11-06 | 西南交通大学 | Overspeed event detection method based on average speed |
| CN108492564B (en) * | 2018-04-18 | 2020-08-07 | 山东省交通规划设计院 | Method and system for measuring running speed of highway vehicle based on road network matching |
| CN108909706A (en) * | 2018-07-03 | 2018-11-30 | 天津英创汇智汽车技术有限公司 | automatic parking method and device |
| CN109270563A (en) * | 2018-10-12 | 2019-01-25 | 南通大学 | A kind of map-matching method based on enhanced hidden Markov model |
| CN111554102A (en) * | 2020-04-24 | 2020-08-18 | 上海经达信息科技股份有限公司 | Vehicle overspeed judging method, system, storage medium and terminal |
| CN111785012B (en) * | 2020-04-27 | 2022-02-11 | 南斗六星系统集成有限公司 | Energy consumption road spectrum analysis method for vehicle cloud cooperative computing |
| CN111783034B (en) * | 2020-04-27 | 2024-04-02 | 南斗六星系统集成有限公司 | Emission road spectrum analysis method for vehicle-cloud cooperative computing |
| CN113129603B (en) * | 2021-03-26 | 2022-06-17 | 深圳市跨越新科技有限公司 | Parallel road overspeed determination method, device, terminal and storage medium |
| CN113870580B (en) * | 2021-09-01 | 2022-09-20 | 北京中交兴路信息科技有限公司 | Overspeed detection method and device for truck, truck vehicle and truck system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FI114535B (en) * | 2002-07-10 | 2004-10-29 | Ekahau Oy | positioning Technology |
| CN102253398A (en) * | 2010-05-18 | 2011-11-23 | 苏州汉扬精密电子有限公司 | Intelligent alarming apparatus for speed and method thereof |
| CN102568200B (en) * | 2011-12-21 | 2015-04-22 | 辽宁师范大学 | Method for judging vehicle driving states in real time |
| CN103192714A (en) * | 2013-04-12 | 2013-07-10 | 北京汽车股份有限公司 | Vehicle speed limit control method and vehicle speed limit control system |
| CN104537209B (en) * | 2014-12-09 | 2017-04-05 | 上海交通大学 | Determination methods based on the vehicle travel type of HMM |
-
2015
- 2015-12-30 CN CN201511018790.7A patent/CN105448108B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105448108A (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105448108B (en) | A kind of hypervelocity method of discrimination based on Hidden Markov road network | |
| Berndt et al. | Continuous driver intention recognition with hidden markov models | |
| CN105046956B (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN107399333B (en) | A kind of accurate parking method of train towards train automatic Pilot | |
| CN110910636A (en) | Vehicle abnormal turning behavior analysis method based on mass traffic data analysis | |
| CN108848462A (en) | Real-time vehicle trajectory predictions method suitable for signalized crossing | |
| CN106956680B (en) | Electric automobile driving behavior recognition analysis method | |
| JP7354295B2 (en) | Apparatus and method for processing vehicle signals and calculating behavioral risk measures | |
| CN110428621B (en) | Track data-based monitoring and early warning method for dangerous driving behavior of floating car | |
| CN106503398B (en) | A kind of highway alignment safety evaluation method based on vehicle dynamics simulation and accident tree | |
| CN104424808B (en) | A kind of navigation hint method and device, navigation system | |
| CN103552560A (en) | Driver driving state recognition-based lane departure alarming method | |
| CN204055561U (en) | Vehicle safe driving caution system | |
| CN110979339A (en) | Front road form reconstruction method based on V2V | |
| CN108177524A (en) | ARHUD systems and its lane line method for drafting | |
| CN109583081A (en) | A kind of prediction model of vehicle speed construction method | |
| US11836994B2 (en) | Methods and apparatus for automatic collection of under-represented data for improving a training of a machine learning model | |
| TW201339031A (en) | Method for calculating fuel consumption during driving and driving fuel consumption calculation system | |
| CN112356849A (en) | Early warning method and device for dangerous driving | |
| CN115935672A (en) | Fuel cell automobile energy consumption calculation method fusing working condition prediction information | |
| CN105620486B (en) | Driving mode judgment means and method applied to vehicle energy management | |
| CN110610326A (en) | Driving management system based on driving data | |
| CN110509925B (en) | Method for identifying sharp turn based on Internet of vehicles data | |
| Li et al. | Traffic accident analysis based on C4. 5 algorithm in WEKA | |
| CN105303837A (en) | Method and system for detecting following behavior characteristic parameter of driver |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |