CN105374212A - Intelligent terminal sensing-based highway vehicle lane identification method and system - Google Patents
Intelligent terminal sensing-based highway vehicle lane identification method and system Download PDFInfo
- Publication number
- CN105374212A CN105374212A CN201510927456.7A CN201510927456A CN105374212A CN 105374212 A CN105374212 A CN 105374212A CN 201510927456 A CN201510927456 A CN 201510927456A CN 105374212 A CN105374212 A CN 105374212A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- acceleration
- wave
- intelligent terminal
- 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.)
- Granted
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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
Abstract
The invention relates to an intelligent terminal sensing-based highway vehicle lane identification method and system. The method includes the following steps that: a built-in sensor in an intelligent terminal is utilized to acquire data; jitter noise in the data are removed through a low-pass filter; the coordinate system of the intelligent terminal is aligned with the coordinate system of a vehicle; and the lane changing behavior of the current vehicle and the number of lane dividing lines which are crossed by the vehicle in lane changing can be judged according to acceleration information detected by the intelligent terminal. According to the intelligent terminal sensing-based highway vehicle lane identification method and system of the invention, a lane where a vehicle running on a highway is located can be judged through sensing different types of lane changing behaviors.
Description
Technical field
What the present invention relates to is a kind of technology of unmanned field, specifically a kind of vehicle on highway lane recognition method based on intelligent terminal sensing and system.
Background technology
Along with the maturing of transportation network and complicated, Vehicle positioning system creates higher importance in driving is driven.In many application (as route guidance, Vehicle security system, car networking), the accuracy of location determines the getable service quality quality of user institute largely.
Therefore, nowadays the location of widely used road grade at last replace by the location of track rank.From security standpoint, if track, vehicle place can by real-time perception, dangerous behavior of changing just can be reminded in time.From convenient angle, if driver was prepared on correct track by pre-tip before entering upper and lower gate, conversion highway, then key crossing can not be missed.From road management angle, if the flow information in every bar track can be obtained, just can dredge track in time or keep in repair.
At present, locate this problem for track rank, the main method of solution is the camera function based on vehicle-mounted or intelligent terminal, and combining image treatment technology identifies the lane line of vehicle front.But, the method when weather not good cause fuzzy, the road of shooting to lack to safeguard cause that lane line is unintelligible, front vehicles or other barrier obstruction cannot judge current lane according to image.
In addition, some systems judge current lane by the information interaction cooperation between vehicle.The method is applicable to the good and situation that in communication network, vehicle node is intensive of network condition.
In addition, some areas adopt the reference base station of known fixed coordinate to make positioning system more accurate.The method reach is wide, can arrive the degree of accuracy within 5 meters.But building this base station in bulk needs a large amount of fund inputs, be not suitable in under-developed area using.
By data acquisition and the analysis of driving behavior in a large amount of actual life, we have found dissimilar behavior of changing and can produce different impacts to the data of intelligent terminal sensor (being mainly acceleration transducer).Suppose that first vehicle is in outermost track when entering highway, that change each time after track just can judge according to track, place before.Like this, the problem of lane identification just roughly can be converted to the perception of vehicle lane-changing behavior.
Summary of the invention
The present invention is directed to prior art above shortcomings, propose a kind of vehicle on highway lane recognition method based on intelligent terminal sensing and system, by the perception of dissimilar behavior of changing to judge track, current place.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of vehicle on highway lane recognition method based on intelligent terminal sensing, utilize built-in sensors (acceleration transducer and the GPS sensor) image data of intelligent terminal, the dither noise in data is removed by low-pass filter, then the coordinate system of intelligent terminal is alignd with vehicle axis system, and the lines quantity of crossing over when judging the behavior of changing that vehicle is current according to the acceleration information that intelligent terminal detects and change.
The described behavior of changing comprises: single changes, change continuously in the same way and oppositely change continuously.Single change to represent within the short time isolated, do not limit direction, do not limit and cross over changing of lines quantity.Change continuously and represent compact within the short time, its waveform changing of superposition occurs.Can also be divided into according to the adjacent orientation consistency changing behavior and change continuously in the same way and oppositely change continuously.
The described acceleration information detected according to intelligent terminal judges to refer to: the transverse acceleration of a car depends on radius and travel speed, and radius is determined by the angle of bearing circle.To the right during lane change, first bearing circle rotates clockwise, and vehicle rolls away from from current lane and turns to track, the right.Now, vehicle has positive acceleration in X-axis.Then bearing circle rotates counterclockwise, and revises the differential seat angle between vehicle and road.Now, vehicle produces negative acceleration in X-axis.Whole process generates one section of acceleration sinusoidal signal model from top to bottom.When the transverse acceleration that intelligent terminal built-in sensors collects exceedes acceleration rate threshold δ, be then judged as that one from t
1start to t
2the crest of the half-wave terminated or trough.
Described acceleration rate threshold refers to: in order to distinguish the noise in the behavior of changing and straight-line travelling, set up threshold value δ to be distinguished.When only having the transverse acceleration numerical value obtained when acceleration transducer be greater than δ or be less than-δ, this acceleration is then judged as " acceleration of non-noise ".When certain instantaneous acceleration is then judged as " acceleration of non-noise ", the half-wave at its place is then judged as the half-wave of non-noise.
The present invention relates to a kind of system realizing said method, comprise: data acquisition module, data preprocessing module, track change detection module and lane identification module, wherein: data acquisition module utilizes built-in sensors (acceleration transducer and the GPS sensor) image data of intelligent terminal, the coordinate system of data preprocessing module alignment intelligent terminal and vehicle, and remove the dither noise in data by low-pass filter, track change detection module according to acceleration information during vehicle lane change judge vehicle current change behavior, result positioned vehicle in the rank of track that lane identification module detects based on track change.
Technique effect
Compared with prior art, the vehicle of running on expressway when not relying on external unit (as camera or reference base station), can position with higher accuracy by the present invention in the rank of track.The present invention, by analyzing the data that vehicle gathers in mobile terminal sensor, obtains the data pattern of different modes of changing, thus exchange road behavior detects, and finally determines track, vehicle current place.
Accompanying drawing explanation
Fig. 1 is behavior of changing schematic diagram dissimilar in embodiment;
Fig. 2 is the relation schematic diagram of vehicle lane-changing behavior and intelligent terminal acceleration transducer data;
Fig. 3 is for intelligent terminal acceleration transducer is at the vehicle schematic diagram data that gathers in changing of single to the right;
Fig. 4 is for intelligent terminal acceleration transducer is at the vehicle schematic diagram data that gathers in changing of single left;
The schematic diagram data that Fig. 5 gathers in vehicle changes to the right in the same way continuously for intelligent terminal acceleration transducer;
The schematic diagram data that Fig. 6 gathers in vehicle oppositely changes to right after to left continuously for intelligent terminal acceleration transducer;
Fig. 7 is the schematic diagram of vehicle each parameter in the behavior of changing;
Fig. 8 is the general performance schematic diagram of native system in embodiment scene;
Fig. 9 is the accuracy rate schematic diagram that behavior is changed in the judgement of native system in embodiment scene;
Figure 10 is the general performance schematic diagram of native system on dissimilar highway;
Figure 11 is to the relation schematic diagram after collection data analysis between accuracy and threshold value;
Figure 12 is the relation schematic diagram that native system uses between self study threshold value accuracy and threshold value.
Embodiment
The present embodiment application scenarios is: choose KIAK5 and HTCDesireG7, HondaAccord and HuaweiHonor3C, VolvoS60L and ZTEU809, MazdaAtenza and HTCEVO3D, AudiA4L and SAMSUNGNexus4 as experiment use vehicle and mobile phone, wherein: every portion vehicle have all been loaded drive recorder, so that using content of shooting as the True Data demarcated.The data gathered are driven naturally from five middle of the month of 5 drivers.
The present embodiment utilizes the intelligent terminal of built-in sensors (acceleration transducer and GPS sensor) to carry out data acquisition, the dither noise in data is removed by low-pass filter, then mobile phone coordinate system is alignd with vehicle axis system, and the lines quantity of crossing over when judging the behavior of changing that vehicle is current according to the acceleration information that intelligent terminal detects and change, as shown in Figure 1.
Described single change to represent within the short time isolated, do not limit direction, do not limit and cross over changing of lines quantity.Detection method, comprises the following steps:
Step one: in order to distinguish the noise in the behavior of changing and straight-line travelling, set up threshold value δ to be distinguished.When only having the transverse acceleration numerical value obtained when acceleration transducer be greater than δ or be less than-δ, this acceleration is then judged as " acceleration of non-noise ".When certain instantaneous acceleration is then judged as " acceleration of non-noise ", the half-wave at its place is then judged as the half-wave of non-noise, and the start time of half-wave and end time are respectively t
1, t
2.
Step 2: when detecting that the half-wave of non-noise is in [t
1, t
2] time, at hemiwave time identical afterwards, i.e. [t
2, t
2+ (t
2-t
1)] whether interior detection exist the half-wave of reverse non-noise.If exist, then two continuous print half-waves constitute a single and change.If two and half waves line of propagation are " upper under ", Ze Huan road to the right, as shown in Figure 3; Otherwise, Ze Huan road left, as shown in Figure 4.
Described changing continuously refers to that changing of superposition occurs compact within the short time, its waveform.Can also be divided into according to the adjacent orientation consistency changing behavior and change continuously in the same way and oppositely change continuously.
The described detection method of changing continuously in the same way, comprises the following steps:
I: the rear half-wave of the first Ge Huan road behavior in changing continuously in the same way and the front half-wave of the second Ge Huan road behavior are offset, and therefore waveform is become discontiguous two half-waves by noise segmentation, as shown in Figure 5.Change detection method expansion to its detection method by single to get.
Ii: when detecting that the half-wave of non-noise is in [t
0, t
1] time, at hemiwave time identical afterwards, i.e. [t
1, t
1+ (t
1-t
0)] whether interior detection exist the half-wave of reverse non-noise.If exist, then two continuous print half-waves constitute a single and change.If do not exist, continue at [t
2, t
2+ (t
1-t
0)] whether interior detection exist the half-wave of reverse non-noise, wherein: t
1≤ t
2≤ t
1+ (t
1-t
0).If exist, then these two divided half-waves constitute one and change continuously in the same way.
The described detection method of oppositely changing continuously, comprises the following steps:
I: in oppositely changing continuously, the rear half-wave of the first Ge Huan road behavior superposes with the front half-wave of the second Ge Huan road behavior, therefore waveform be the sine wave of " going up extremely lower supreme " or " lower supreme extremely under ", as shown in Figure 6.
II: to its detection method based on following thought: the area of middle half-wave approximates greatly the area sum of both sides half-wave.Its reason is that the integration of transverse acceleration is that transverse velocity is poor, and the transverse velocity before and after changing continuously is all close to zero, and its difference is also zero, and therefore positive half-wave area and negative half-wave area should cancel each other.
III: the sine wave of " upper to lower supreme " or " lower supreme under " when detecting, each half-wave is the half-wave of non-noise, and when waveform area meets above-mentioned requirements, this sine wave is judged as and oppositely changes continuously, and direction is an elder generation right back left side or first left and then right.
The described detection method of oppositely changing continuously is based on following thought: the area of middle half-wave approximates greatly the area sum of both sides half-wave.Its reason is that the integration of transverse acceleration is that transverse velocity is poor, and the transverse velocity before and after changing continuously is all close to zero, and its difference is also zero, and therefore positive half-wave area and negative half-wave area should cancel each other.The sine wave of " upper to lower supreme " or " lower supreme under " when detecting, each half-wave is the half-wave of non-noise, and when waveform area meets above-mentioned requirements, this sine wave is judged as and oppositely changes continuously, and direction is an elder generation right back left side or first left and then right.
The detection method of described lines quantity of crossing over when changing, comprises the following steps:
It is a bit of that instantaneous route in ①Jiang Huan road process is regarded as in positive round, utilizes a=ω
2r=v
2/ r=ω v calculates real-time angular velocity omega, and wherein: a is horizontal centripetal acceleration, v is the real-time tangential direction speed obtained from intelligent terminal GPS sensor, and r is this radius of circle.
2. diagonal angle rate integrating obtains angle between Current vehicle and track
t
1and T
2it is the start and end time of track change.
3. angle between Current vehicle and track is utilized
obtain the component velocity of vehicle in the vertical direction of track, the displacement in the vertical direction of integration acquisition track is carried out to component velocity
4. leap lines quantity is obtained with displacement divided by lane width.
Due to highway, often to have to a certain degree bending, accelerating curve entirety can be made to offset up or down, make threshold value accurately can not judge the half-wave of non-noise, cause the inefficacy of above-mentioned algorithm.Therefore, the impact that employing method elimination highway curvature is brought is needed.The method is as follows:
Definition " roadway characteristic curve " is: when vehicle travels on road with the state of relative rectilinear (Ji Buhuan road), from the transverse acceleration curve that intelligent terminal acceleration transducer reads.
Extract characteristic curve by a window, that is: work as t
n-t
m>=τ
time,
wherein: t
mfor initial time, t
nfor the end time, τ
timefor shortest time restriction, δ is the restriction of peak acceleration difference, is also simultaneously algorithm threshold value used.Shortest time restriction limits the relative rectilinear state of common guarantee certain hour, as shown in rectangle frame in Fig. 8 with peak acceleration difference.Calculate acceleration mean value in the window as " roadway characteristic " in this period.
Original waveform is deducted " roadway characteristic curve " route originally travelled along crankcase ventilaton can be thought to be modified to linearly road driving.
Except road curvature, when bend shape belongs to positive round a part of, a small amount of bend in highway also can be used to judgement and change behavior, is specially:
1) r
1/ r
2=v
1 2a
2/ v
2 2a
1, wherein: r
1, v
1, a
1be respectively radius-of-curvature when entering bend, tangential direction speed, centripetal acceleration, r
2, v
2, a
2be respectively radius-of-curvature when coming off the curve, tangential direction speed, centripetal acceleration.
2) then according to r
1/ r
2can determine whether vehicle there occurs in turning process with the direction of bend to change, and change the direction of behavior.
Because different drivers has different driving habitses, different vehicles has different performances, and different mobile phone sensor has different sensitivity, and described acceleration rate threshold needs the adjustment carrying out self study.Method of adjustment is as follows:
1) when vehicle is at straight line and when one-way road road travels, increased acceleration threshold value gradually of starting from scratch, anyly changes behavior until can not detect, is designated as δ
i.If r
iat threshold value δ
iunder the precision that detects of the track change that calculates based on test data set, r
i=(n
lc-n
ror)/n
lc, wherein: n
lcthe quantity that track change occurs, n
rorbe the quantity detecting error, test data set is retained in the last sensing data collected on a highway in intelligent terminal.
Described straight line and one-way road road refer to: when vehicle is at this road driving, vehicle can not change behavior.This kind of road can occur on ground in single track road, parking lot, community etc.
2) δ is recycled
n=(δ
n-1r
n-1+ δ
ir
i)/(r
n-1+ r
i) all local thresholds in normalization historical record and its accuracy, obtain the acceleration rate threshold that the overall situation is suitable for.
The present embodiment judges the service quality of native system according to following three evaluation indexes:
Judge the accuracy rate of behavior of changing: when a behavior of changing really occurs, the proportion that it is accurately judged by system.
Judge the vacation just rate of behavior of changing: when system judges to change, the actual proportion not changing behavior.
The accuracy rate of lane identification: change behavior for measuring point with vehicle, the proportion that track, system positioned vehicle place is correct.
For the whole structure of native system in above-described embodiment scene as shown in Figure 9.Wherein: from average, judge that the accuracy rate of behavior of changing is 91.49%, the vacation judging behavior of changing just rate is 4.76%, and the accuracy rate of lane identification is 86.94%.Therefore, the present invention can carry out rank location, track with higher accuracy rate to the vehicle on highway.
Accuracy rate in behavior is changed as shown in Figure 9 dissimilar for native system.Wherein: from average, judge that the accuracy rate that single changes behavior is 97.08%, judge that the accuracy rate of behavior of changing continuously is 91.02%, the accuracy rate that quantity is changed in judgement is 95.3%.Due in real driving conditions, it is the highest that single changes the frequency occurred, and the accuracy rate that therefore higher judgement single changes behavior can produce the accuracy rate of higher judgement Zong Huan road behavior.
The average effect of native system on the highway in different track as shown in Figure 10.Highway is classified according to its track quantity by we: two pass highway, three road highways, four roads and above highway.As seen from the figure, although accuracy rate declines along with the increase of track quantity, the accuracy rate of overall lane identification still can remain on more than 85%, and this shows that native system has certain robustness.
In order to study the relation between threshold value and accuracy, the data collected are carried out to the test of different threshold value.As shown in figure 11, five cars have different suitable threshold values respectively.Adopt self study adjustment threshold value and based on behavior of the changing accuracy rate of these roads relation as shown in figure 12.In order to make pattern more clear, only for vehicle 4 and vehicle 5, can find out, learning by oneself point at the peak value place of curve is the most intensive, and the threshold value namely adjusted by self study can closely desirable standardization.Other three cars also can realize so high similarity.
Above-mentioned concrete enforcement can carry out local directed complete set to it by those skilled in the art in a different manner under the prerequisite not deviating from the principle of the invention and aim; protection scope of the present invention is as the criterion with claims and can't help above-mentioned concrete enforcement and limit, and each implementation within the scope of it is all by the constraint of the present invention.
Claims (9)
1. the vehicle on highway lane recognition method based on intelligent terminal sensing, it is characterized in that, utilize the built-in sensors image data of intelligent terminal, the dither noise in data is removed by low-pass filter, then the coordinate system of intelligent terminal is alignd with vehicle axis system, and the lines quantity of crossing over when judging the behavior of changing that vehicle is current according to the acceleration information that intelligent terminal detects and change; The described behavior of changing comprises: single changes, change continuously in the same way and oppositely change continuously.
2. method according to claim 1, it is characterized in that, the described acceleration information detected according to intelligent terminal judges to refer to: exceed acceleration rate threshold with the transverse acceleration that built-in sensors collects, the position of the half-wave in acceleration sequential chart residing during the acceleration of i.e. non-noise, namely the half-wave of non-noise carries out changing judgement.
3. method according to claim 1 and 2, it is characterized in that, the described acceleration information detected according to intelligent terminal judges to be specially: to the right during lane change, first bearing circle rotates clockwise, vehicle rolls away from from current lane and turns to track, the right, and now vehicle has positive acceleration in X-axis; Then bearing circle rotates counterclockwise, and revise the differential seat angle between vehicle and road, now vehicle produces negative acceleration in X-axis; Whole process generates one section of acceleration sinusoidal signal model from high to low, when the transverse acceleration that intelligent terminal built-in sensors collects exceedes acceleration rate threshold δ, then judge be one from t
1start to t
2the crest of the half-wave terminated or trough.
4. method according to claim 3, is characterized in that, described single changes, and judges in the following manner: when detecting that the half-wave of non-noise is in [t
1, t
2] time, at hemiwave time identical afterwards, i.e. [t
2, t
2+ (t
2-t
1)] whether interior detection exist the half-wave of reverse non-noise: if exist, then two continuous print half-waves constitute a single and change, if two and half waves line of propagation be " upper extremely under ", Ze Huan road is to the right; Otherwise Ze Huan road left.
5. method according to claim 3, is characterized in that, described changes in the same way continuously, judges in the following manner: when detecting that the half-wave of non-noise is in [t
0, t
1] time, at hemiwave time identical afterwards, i.e. [t
1, t
1+ (t
1-t
0)] whether interior detection exist the half-wave of reverse non-noise: if exist, then two continuous print half-waves constitute a single and change, otherwise continue at [t
2, t
2+ (t
1-t
0)] whether interior detection exist the half-wave of reverse non-noise, wherein: t
1≤ t
2≤ t
1+ (t
1-t
0).If exist, then these two divided half-waves constitute one and change continuously in the same way.
6. method according to claim 3, is characterized in that, described oppositely changes continuously, judges in the following manner:
I: in oppositely changing continuously, the rear half-wave of the first Ge Huan road behavior superposes with the front half-wave of the second Ge Huan road behavior, therefore waveform be the sine wave of " going up extremely lower supreme " or " lower supreme extremely under ";
II: the sine wave of " upper to lower supreme " or " lower supreme under " when detecting, each half-wave is the half-wave of non-noise, and the area that waveform area meets middle half-wave is when approximating greatly the area sum of both sides half-wave, this sine wave is judged as and oppositely changes continuously, and direction is a first right back left side or first left and then right.
7. method according to claim 1, is characterized in that, described lines quantity of crossing over when changing, and detects in the following manner:
The lines quantity of crossing over when changing
Step one, to be regarded as by the instantaneous route in the process of changing in positive round a bit of, utilizes a=ω
2r=v
2/ r=ω v calculates real-time angular velocity omega, and wherein: a is horizontal centripetal acceleration, v is the real-time tangential direction speed obtained from intelligent terminal GPS sensor, and r is this radius of circle;
Step 2, diagonal angle rate integrating obtain angle between Current vehicle and track
Step 3, utilize angle between Current vehicle and track
obtain the component velocity of vehicle in the vertical direction of track, the displacement in the vertical direction of integration acquisition track is carried out to component velocity;
Step 4, displacement obtained divided by lane width and crosses over lines quantity.
8. method according to claim 7, is characterized in that, described lines quantity of crossing over when changing, and the impact that the method for employinging elimination highway curvature is brought when detecting, is specially:
1) extract characteristic curve by a window, that is: work as t
n-t
m>=τ
time,
wherein: t
mfor initial time, t
nfor the end time, τ
timefor shortest time restriction, δ is the restriction of peak acceleration difference;
2) original waveform is deducted roadway characteristic curve, the route being about to originally travel along crankcase ventilaton is modified to linearly road driving;
Described roadway characteristic curve refers to: when vehicle is with relative rectilinear, when the state in Ji Buhuan road travels on road, from the transverse acceleration curve that intelligent terminal acceleration transducer reads.
9. method according to claim 2, is characterized in that, described acceleration rate threshold, is adjusted, be specially by the mode of self study:
1) when vehicle is at straight line and when one-way road road travels, increased acceleration threshold value gradually of starting from scratch, anyly changes behavior until can not detect, is designated as δ
i.If r
iat threshold value δ
iunder the precision that detects of the track change that calculates based on test data set, r
i=(n
1c-n
ror)/n
1c, wherein: n
1cthe quantity that track change occurs, n
rorbe the quantity detecting error, test data set is retained in the last sensing data collected on a highway in intelligent terminal;
2) δ is recycled
n=(δ
n-1r
n-1+ δ
1r
1)/(r
n-1+ r
i) all local thresholds in normalization historical record and its accuracy, obtain the acceleration rate threshold that the overall situation is suitable for;
Described straight line and one-way road road refer to: when vehicle is at this road driving, vehicle can not change behavior.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510927456.7A CN105374212B (en) | 2015-12-14 | 2015-12-14 | The vehicle on highway lane recognition method and system sensed based on intelligent terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510927456.7A CN105374212B (en) | 2015-12-14 | 2015-12-14 | The vehicle on highway lane recognition method and system sensed based on intelligent terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105374212A true CN105374212A (en) | 2016-03-02 |
CN105374212B CN105374212B (en) | 2017-07-18 |
Family
ID=55376363
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510927456.7A Active CN105374212B (en) | 2015-12-14 | 2015-12-14 | The vehicle on highway lane recognition method and system sensed based on intelligent terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105374212B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105823479A (en) * | 2016-03-04 | 2016-08-03 | 上海畅星软件有限公司 | Driving behavior analysis method |
CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
CN106556405A (en) * | 2016-10-28 | 2017-04-05 | 南京邮电大学 | A kind of lane detection method based on intelligent mobile phone sensor |
CN108268033A (en) * | 2016-12-30 | 2018-07-10 | 百度(美国)有限责任公司 | The method and system to operate automatic driving vehicle is instructed using the lane changing based on figure |
CN108470142A (en) * | 2018-01-30 | 2018-08-31 | 西安电子科技大学 | Lane location method based on inverse perspective projection and track distance restraint |
CN110299027A (en) * | 2019-07-12 | 2019-10-01 | 山东交通学院 | It is a kind of based on the vehicle lane change of track data and map datum monitoring and safe early warning method |
CN111439263A (en) * | 2018-12-29 | 2020-07-24 | 沈阳美行科技有限公司 | Vehicle lane change recognition method and device, electronic equipment and storage medium |
CN112949465A (en) * | 2021-02-26 | 2021-06-11 | 上海商汤智能科技有限公司 | Vehicle continuous lane change recognition method, device, equipment and storage medium |
CN113232658A (en) * | 2021-06-28 | 2021-08-10 | 驭势(上海)汽车科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
WO2021217485A1 (en) * | 2020-04-29 | 2021-11-04 | 华为技术有限公司 | Vehicle lane-changing behavior recognition method and apparatus |
CN113805210A (en) * | 2021-09-17 | 2021-12-17 | 北谷电子有限公司 | TBOX positioning optimization system, method, electronic device and storage medium |
CN115240426A (en) * | 2022-07-26 | 2022-10-25 | 东软睿驰汽车技术(沈阳)有限公司 | Automatic positioning method, device and equipment for lane change data and storage medium |
CN116403407A (en) * | 2023-05-31 | 2023-07-07 | 山东高速信息集团有限公司 | Method, equipment and medium for dynamically configuring and inducing lanes of highway toll station |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002269678A (en) * | 2001-03-06 | 2002-09-20 | Natl Inst For Land & Infrastructure Management Mlit | Detection data input check system in road side processing device |
CN101923782A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Method for acquiring transportation traffic speed based on geomagnetic sensing technology |
CN104359493A (en) * | 2014-11-18 | 2015-02-18 | 浙江工商大学 | High-precision direction correction method under vehicle-mounted condition of smart phone |
CN104463244A (en) * | 2014-12-04 | 2015-03-25 | 上海交通大学 | Aberrant driving behavior monitoring and recognizing method and system based on smart mobile terminal |
CN104464375A (en) * | 2014-11-20 | 2015-03-25 | 长安大学 | Method for recognizing vehicle high-speed turning |
-
2015
- 2015-12-14 CN CN201510927456.7A patent/CN105374212B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002269678A (en) * | 2001-03-06 | 2002-09-20 | Natl Inst For Land & Infrastructure Management Mlit | Detection data input check system in road side processing device |
CN101923782A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Method for acquiring transportation traffic speed based on geomagnetic sensing technology |
CN104359493A (en) * | 2014-11-18 | 2015-02-18 | 浙江工商大学 | High-precision direction correction method under vehicle-mounted condition of smart phone |
CN104464375A (en) * | 2014-11-20 | 2015-03-25 | 长安大学 | Method for recognizing vehicle high-speed turning |
CN104463244A (en) * | 2014-12-04 | 2015-03-25 | 上海交通大学 | Aberrant driving behavior monitoring and recognizing method and system based on smart mobile terminal |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105823479A (en) * | 2016-03-04 | 2016-08-03 | 上海畅星软件有限公司 | Driving behavior analysis method |
CN105823479B (en) * | 2016-03-04 | 2018-08-17 | 上海畅星软件有限公司 | Driving behavior analysis method |
CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
CN106556405A (en) * | 2016-10-28 | 2017-04-05 | 南京邮电大学 | A kind of lane detection method based on intelligent mobile phone sensor |
CN108268033A (en) * | 2016-12-30 | 2018-07-10 | 百度(美国)有限责任公司 | The method and system to operate automatic driving vehicle is instructed using the lane changing based on figure |
CN108268033B (en) * | 2016-12-30 | 2021-09-21 | 百度(美国)有限责任公司 | Method and system for operating an unmanned vehicle using graph-based lane change guidance |
CN108470142B (en) * | 2018-01-30 | 2021-09-03 | 西安电子科技大学 | Lane positioning method based on inverse perspective projection and lane distance constraint |
CN108470142A (en) * | 2018-01-30 | 2018-08-31 | 西安电子科技大学 | Lane location method based on inverse perspective projection and track distance restraint |
CN111439263B (en) * | 2018-12-29 | 2022-05-20 | 沈阳美行科技股份有限公司 | Vehicle lane change recognition method and device, electronic equipment and storage medium |
CN111439263A (en) * | 2018-12-29 | 2020-07-24 | 沈阳美行科技有限公司 | Vehicle lane change recognition method and device, electronic equipment and storage medium |
CN110299027B (en) * | 2019-07-12 | 2021-12-14 | 山东交通学院 | Vehicle lane change monitoring and safety early warning method based on track data and map data |
CN110299027A (en) * | 2019-07-12 | 2019-10-01 | 山东交通学院 | It is a kind of based on the vehicle lane change of track data and map datum monitoring and safe early warning method |
WO2021217485A1 (en) * | 2020-04-29 | 2021-11-04 | 华为技术有限公司 | Vehicle lane-changing behavior recognition method and apparatus |
CN112949465A (en) * | 2021-02-26 | 2021-06-11 | 上海商汤智能科技有限公司 | Vehicle continuous lane change recognition method, device, equipment and storage medium |
CN113232658A (en) * | 2021-06-28 | 2021-08-10 | 驭势(上海)汽车科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
CN113232658B (en) * | 2021-06-28 | 2022-06-28 | 驭势(上海)汽车科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
CN113805210A (en) * | 2021-09-17 | 2021-12-17 | 北谷电子有限公司 | TBOX positioning optimization system, method, electronic device and storage medium |
CN115240426A (en) * | 2022-07-26 | 2022-10-25 | 东软睿驰汽车技术(沈阳)有限公司 | Automatic positioning method, device and equipment for lane change data and storage medium |
CN115240426B (en) * | 2022-07-26 | 2024-03-26 | 东软睿驰汽车技术(沈阳)有限公司 | Automatic positioning method, device and equipment for lane change data and storage medium |
CN116403407A (en) * | 2023-05-31 | 2023-07-07 | 山东高速信息集团有限公司 | Method, equipment and medium for dynamically configuring and inducing lanes of highway toll station |
CN116403407B (en) * | 2023-05-31 | 2023-09-01 | 山东高速信息集团有限公司 | Method, equipment and medium for dynamically configuring and inducing lanes of highway toll station |
Also Published As
Publication number | Publication date |
---|---|
CN105374212B (en) | 2017-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105374212A (en) | Intelligent terminal sensing-based highway vehicle lane identification method and system | |
RU2702850C1 (en) | Method of motion control and movement control device | |
US8085984B2 (en) | Image recognizing apparatus and method, and position determining apparatus, vehicle controlling apparatus and navigation apparatus using the image recognizing apparatus or method | |
CN100580735C (en) | Real-time dynamic traffic information processing method based on car detecting technique | |
CN101577049B (en) | Map-matching method based on filtering of parking point data of floating vehicles | |
CN104464375B (en) | It is a kind of to recognize the method that vehicle high-speed is turned | |
JP6659367B2 (en) | Object detection device and object detection method | |
CN100589143C (en) | Method and appaatus for judging the traveling state of a floating vehicle | |
WO2020042642A1 (en) | Vehicle positioning method and device, and autonomous vehicle | |
CN106871924A (en) | A kind of VMT Vehicle-Miles of Travel computational methods based on satellite positioning signal | |
CN104395944B (en) | The identification in orientation track | |
RU2766038C1 (en) | Method and apparatus for generating information on the traffic environment for a vehicle, and method for controlling movement for a vehicle | |
WO2020154599A1 (en) | Clustering event information for vehicle navigation | |
CN104750963A (en) | Intersection delay time estimation method and device | |
CN104504364A (en) | Real-time stop line recognition and distance measurement method based on temporal-spatial correlation | |
CN112034449B (en) | System and method for correcting vehicle running track based on physical space attribute | |
WO2022047372A1 (en) | Systems and methods for map-based real-world modeling | |
CN111081030B (en) | Method and system for judging traffic jam on expressway | |
CN113689718B (en) | Intelligent signal lamp and lane matching system and method | |
CN113227831B (en) | Guardrail estimation method based on multi-sensor data fusion and vehicle-mounted equipment | |
CN107886726A (en) | Road occupying/parking behavior detection method and device | |
Janda et al. | A road edge detection approach for marked and unmarked lanes based on video and radar | |
CN116229708A (en) | Perception test method of road side perception system on traffic target based on V2I | |
WO2020195166A1 (en) | Environment recognition device | |
Chipka et al. | Autonomous urban localization and navigation with limited information |
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 |