CN105809106B - Vehicle formation based on machine vision is with detection method of speeding - Google Patents
Vehicle formation based on machine vision is with detection method of speeding Download PDFInfo
- Publication number
- CN105809106B CN105809106B CN201610099028.4A CN201610099028A CN105809106B CN 105809106 B CN105809106 B CN 105809106B CN 201610099028 A CN201610099028 A CN 201610099028A CN 105809106 B CN105809106 B CN 105809106B
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- standard
- real
- time
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
The invention discloses the vehicle formations based on machine vision with detection method of speeding, fleet arranges according to ranks, column direction is arranged according to ground control line, a reference direction is arranged in every a line, vehicle along the most end of reference direction is benchmark vehicle, to camera before the front end installation of each car body in fleet, lateral camera is arranged close to the side of control vehicle in each car body, target is arranged in the other side;Hit exactly ground control line in image to camera before adjustment, adjusting lateral camera hits exactly target in image;In start time, standard forward sight picture and standard side view picture are obtained, and standard groove and standard target are set, standard groove is overlapped with guide line, standard target is overlapped with control vehicle target;During vehicle follow gallop, the distance and deflecting angle and target deviation distance of calculating guide line deviation standard groove finally calculate the fore-and-aft distance of the practical bias of guide line and vehicle and control vehicle, are adjusted to vehicle heading.
Description
Technical field
The present invention relates to vehicle formations with driving field of speeding, and in particular to the vehicle formation based on machine vision is detected with speeding
Method.
Background technique
In recent years, the formation control problem of vehicle is had been to be concerned by more and more people.This is primarily due to generation
The development of the economy and science and technology of boundary's range, vehicle are increasing, and highway system vehicle flowrate also sharply increases, along with such as traffic
The appearance of the unfavorable phenomenon such as crowded, traffic accident, environmental pollution, causes serious personal injury and economic loss.In addition, at certain
A little special dimensions, it is such as low in visibility, under the severe running environment such as with a varied topography, it will appear the fleet of vehicle composition often with each
Kind specified formation mode, the case where tasks such as detecting, go on patrol, rescuing by the completion that cooperates with each other, therefore for the formation of vehicle
Control problem research also becomes the key issues of research.
Line up in vehicle with speeding when driving, for vehicle of speeding, not only needs longitudinally keeping and benchmark vehicle
It is parallel, while needing to guarantee that vehicle driving direction cannot deviate guide line, i.e., with binding character existing for vehicle of speeding.Together
When, since the change of travel condition of vehicle will correct hysteresis quality with the presence of reaction process, in addition, for entire fleet,
The state change of any vehicle can all be passed to other vehicles.Therefore accurate measurement vehicle and guidance in real time are needed
The relative positional relationship of line, the same control vehicle arranged.Vehicle it is advanced, fall behind, adjust and be to maintain in time after offset direction
The key of vehicle follow gallop formation.
When fleet advances, as shown in Fig. 1, the first train of vehicles of the right is the control vehicle of each row, it is responsible for two tasks:
First is that guaranteeing that running speed is constant, second is that guaranteeing accurately to travel along guide line, error is no more than ± 0.05 meter;Two train of vehicles of the left side
Two tasks: first is that the control vehicle that dresses right, guarantees to be no more than ± 0.05 meter with control vehicle longitudinal bias, second is that guaranteeing along guidance
Line accurately travels, and error is no more than ± 0.05 meter;Two tasks of the second train of vehicles of the left side: it first is that dressing control vehicle to the left, protects
Card is no more than ± 0.05 meter with benchmark vehicle longitudinal bias, second is that guaranteeing accurately to travel along guide line, error is no more than ± 0.05
Rice.
Summary of the invention
In view of this, the present invention provides the vehicle formations based on machine vision with detection method of speeding, for keeping vehicle
Travel speed and position meet with formation of speeding requirement.
In order to achieve the above object, the technical solution of the present invention is as follows: the vehicle formation based on machine vision is with the side of detection of speeding
Method, fleet arrange according to ranks, and column direction is arranged according to ground control line, and a reference direction is arranged in every a line, along benchmark side
To most end vehicle be benchmark vehicle, include the following steps:
Step 1, the front end installation of each car body is preceding to camera in fleet, and each car body is set close to the side of control vehicle
Set lateral camera, other side setting target.
Step 2 carries out static demarcating to camera and lateral camera to preceding, is adjusted to camera installation site,
Image is passed back according to camera to be adjusted camera installation site, so that it is returned ground in image to camera before adjustment and is drawn
Conducting wire is hit exactly in image, and adjusting lateral camera hits exactly target in its passback image in image.
Step 3 obtains original image, respectively original forward sight image and primary side by forward direction camera and lateral camera
Visible image is demarcated to preceding to camera and lateral camera according to original forward sight image, original side elevation image respectively, including
Model intrinsic parameter, time for exposure, white balance, tone and saturation parameters.
Step 4, in vehicle follow gallop start time, obtain the forward sight picture and side view picture of start time.
Standard groove is set on the forward sight picture of start time, and adjustment standard scribe line position is overlapped with guide line.
Standard target is set on the side view picture of start time, and adjustment standard target is overlapped with target on control vehicle.
Thus standard forward sight picture and standard side view picture are obtained;
Step 5, during vehicle follow gallop, current vehicle is adjusted as follows:
Forward direction camera and lateral camera obtain real-time forward sight picture and real-time side view picture respectively.
Real-time forward sight picture and standard forward sight picture are compared, if the guide line in forward sight picture deviates standard in real time
Groove then calculates guide line deviation distance and deflecting angle.
Real-time side view picture and standard side view picture are compared, if the target in forward sight picture deviates standard target in real time
Mark, then calculate target deviation distance.
The relationship that distance and actual range in figure are calculated using the parameter that step 3 is demarcated, thus by obtaining guide line
The fore-and-aft distance of practical bias and vehicle and control vehicle;
Column adjustment is carried out to vehicle heading according to above-mentioned guide line deflecting angle and guide line practical bias, according to vehicle
Capable adjustment is carried out to Vehicle Speed with the fore-and-aft distance of control vehicle, finally makes vehicle according to lane line and control vehicle institute
The queue of delimitation is advanced.
Further, real-time forward sight picture and standard forward sight picture are compared, if the guidance in forward sight picture in real time
Line deviates standard groove, then calculates the detailed process of guide line deviation distance and deflecting angle are as follows:
Step 501 is by extracting guiding in real time line, the linear equation a of guiding in real time line in real-time forward sight imageqox+bqoy+cqo
=0;Wherein x, y are the unknown quantity in the linear equation of guide line, aqo、bqoAnd cqoRespectively in the linear equation of guide line
Coefficient.
The position of step 502 standard groove is determined that the linear equation of standard groove is a by setup parameterqcx'+bqcy'+cqc
=0;Wherein x ', y ' are the unknown quantity in the linear equation of standard groove, aqc、bqcAnd cqcThe respectively straight line side of standard groove
Coefficient in journey.
Angle theta between step 503 current vehicle and guide line is
Offset d between current vehicle and guide lineqFor
Wherein (x0,y0) it is standard groove aqcx+bqcy+cqcThe midpoint of=0 line segment.
Further, the method in step 501, by extracting guiding in real time line in real-time forward sight image are as follows:
Standard groove in standard forward sight picture is mapped in real-time forward sight image by step 511, in real-time forward sight image
In, the minimum circumscribed rectangle of standard groove is acquired, and this square boundary expansion 50% is emerging as the image sense for extracting guide line
Interesting region ROI.
Step 512 successively carries out ROI down-sampled, Gaussian Blur, Canny edge extracting, obtains guide line edge graph.
Step 513 carries out Hough transformation to guide line edge graph, extracts the straight line in edge graph.
Step 514 screens resulting straight line, retains the straight line for meeting setting slope range and length range.
Step 515 does least square fitting to the linear equation parameter remained, obtains optimal linear equation estimation
As guiding in real time line.
Further, real-time side view picture and standard side view picture are compared, if real-time in forward sight picture in real time
Target deviates standard target, then calculates target deviation distance, method particularly includes:
Step 54 extracts initial target target position (x in real-time side view pictureco,yco)。
Step 55 is known (x for standard target positioncc,ycc), then fore-and-aft distance
Further, initial target target is extracted in step 54 in real-time side view picture method particularly includes:
Standard target is mapped in real-time side view picture by step 541, is acquired standard target in real-time side view picture and is marked on a map
The minimum circumscribed rectangle of case, and this square boundary is expanded 50% as the interesting image regions for extracting target.
Step 542 successively carries out down-sampled, Gaussian Blur, Canny edge extracting for the interesting image regions of target,
Obtain target edge graph.
Step 543 to target edge graph extract profile, using Hu not displacement as matching characteristic progress template matching.
Step 544 obtains optimal match point coordinate as real-time target target position (xco,yco)。
The utility model has the advantages that
Method designed by the present invention, which can satisfy, keeps the travel speed of vehicle and position to meet in vehicle follow gallop task
With the requirement for formation of speeding, deviation is acquired by the comparison to guide line and control vehicle target, vehicle adjust with speeding, had
High, easy to use, measurement accuracy the is high advantage of real-time.
Detailed description of the invention
Fig. 1 fleet traveling schematic diagram;
Fig. 2 camera scheme of installation;
Fig. 3 master scale line and standard target display pattern schematic diagram.
Specific embodiment
The present invention will now be described in detail with reference to the accompanying drawings and examples.
Vehicle formation based on machine vision is with detection method of speeding, and fleet arranges according to ranks, and column direction draws according to ground
A reference direction is arranged in conducting wire setting, every a line, and the vehicle along the most end of reference direction is benchmark vehicle, as shown in Figure 1, including
Following steps:
Step 1, the front end installation of each car body is preceding to camera in fleet, and the side of each car body reference direction is arranged
Target is arranged in lateral camera, the other side;As shown in Figure 2.
Step 2 carries out static demarcating to camera and lateral camera to preceding, is adjusted to camera installation site,
Image is passed back according to camera to be adjusted camera installation site, so that it is returned ground in image to camera before adjustment and is drawn
Conducting wire is hit exactly in image, and adjusting lateral camera knows that control vehicle subscript calibration in its passback image in image center.
Step 3 obtains original image, respectively original forward sight image and primary side by forward direction camera and lateral camera
Visible image is demarcated to preceding to camera and lateral camera according to original forward sight image, original side elevation image respectively, including
Model intrinsic parameter, time for exposure, white balance, tone and saturation parameters.
Step 4, in vehicle follow gallop start time, obtain the forward sight picture and side view picture of start time.
Standard groove is set on the forward sight picture of start time, and adjustment standard scribe line position is overlapped with guide line;
Standard target is set on the side view picture of start time, and adjustment standard target is overlapped with target on control vehicle;Such as
Shown in Fig. 3.
Thus standard forward sight picture and standard side view picture are obtained.
Step 5, during vehicle follow gallop, current vehicle is adjusted as follows:
Forward direction camera and lateral camera obtain real-time forward sight picture and real-time side view picture respectively.
Real-time forward sight picture and standard forward sight picture are compared, if the guide line in forward sight picture deviates standard in real time
Groove then calculates guide line deviation distance and deflecting angle;Detailed process are as follows:
Step 501 is by extracting guiding in real time line, the linear equation a of guiding in real time line in original forward sight imageqox+bqoy+cqo
=0;Wherein x, y are the unknown quantity in the linear equation of guide line, aqo、bqoAnd cqoRespectively in the linear equation of guide line
Coefficient.
Method by extracting guiding in real time line in real-time forward sight image are as follows:
Standard groove in standard forward sight picture is mapped in real-time forward sight image by step 511, in real-time forward sight image
In, the minimum circumscribed rectangle of standard groove is acquired, and this square boundary expansion 50% is emerging as the image sense for extracting guide line
Interesting region ROI.
Step 512 successively carries out ROI down-sampled, Gaussian Blur, Canny edge extracting, obtains guide line edge graph.
Step 513 carries out Hough transformation to guide line edge graph, extracts the straight line in edge graph.
Step 514 screens resulting straight line, retains the straight line for meeting setting slope range and length range.
Step 515 does least square fitting to the linear equation parameter remained, obtains optimal linear equation estimation
As guiding in real time line.
The position of step 502 standard groove is determined that the linear equation of standard groove is a by setup parameterqcx'+bqcy'+cqc
=0;Wherein x ', y ' are the unknown quantity in the linear equation of standard groove, aqc、bqcAnd cqcThe respectively straight line side of standard groove
Coefficient in journey;
Angle theta between step 503 current vehicle and guide line is
Offset d between current vehicle and guide lineqFor
Wherein (x0,y0) it is standard groove aqcx+bqcy+cqcThe midpoint of=0 line segment.
Real-time side view picture and standard side view picture are compared, if target deviates standard target in real time, calculate target
Mark deviation distance;Method particularly includes:
Step 54 extracts real-time target target position (x in real-time side elevation imageco,yco).It is extracted in real-time side elevation image
Initial target target method particularly includes:
Standard target is mapped in real-time side elevation image by step 541, is acquired standard target in real-time side elevation image and is marked on a map
The minimum circumscribed rectangle of case, and this square boundary is expanded 50% as extraction target target interesting image regions.
Step 542 successively carries out down-sampled, Gaussian Blur, Canny edge extracting for the interesting image regions of target,
Obtain target edge graph.
Step 543 to target edge graph extract profile, using Hu not displacement as matching characteristic progress template matching.
Step 544 obtains optimal match point coordinate as initial target target position (xco,yco)。
Step 55 is known (x for standard target positioncc,ycc), then fore-and-aft distance
The relationship that distance and actual range in figure are calculated using the parameter that step 3 is demarcated, thus by obtaining guide line
The fore-and-aft distance of practical bias and vehicle and control vehicle;
Column adjustment is carried out to vehicle heading according to above-mentioned guide line deflecting angle and guide line practical bias, according to vehicle
Capable adjustment is carried out to vehicle heading with the fore-and-aft distance of control vehicle, finally makes vehicle according to lane line and control vehicle institute
The queue of delimitation is advanced.
In conclusion the above is merely preferred embodiments of the present invention, being not intended to limit the scope of the present invention.
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention
Within protection scope.
Claims (3)
1. the vehicle formation based on machine vision is with detection method of speeding, which is characterized in that fleet arranges according to ranks, and column direction is pressed
It is arranged according to ground control line, a reference direction is arranged in every a line, and the vehicle along the most end of reference direction is benchmark vehicle, including such as
Lower step:
Step 1, the front end installation of each car body is preceding to camera in fleet, and side is arranged close to the side of control vehicle in each car body
To camera, the other side, target is set;
Step 2 carries out static demarcating to the forward direction camera and lateral camera, is adjusted to camera installation site,
Image is passed back according to camera to be adjusted camera installation site, adjust the forward direction camera make its return image in
Face guide line is hit exactly in image, and adjusting the lateral camera hits exactly target in its passback image in image;
Step 3 obtains original image, respectively original forward sight image and primary side by the forward direction camera and lateral camera
Visible image is demarcated to preceding to camera and lateral camera according to original forward sight image, original side elevation image respectively, including
Model intrinsic parameter, time for exposure, white balance, tone and saturation parameters;
Step 4, in vehicle follow gallop start time, obtain the forward sight picture and side view picture of start time;
Standard groove is set on the forward sight picture of start time, and adjustment standard scribe line position is overlapped with guide line;
Standard target is set on the side view picture of start time, and adjustment standard target is overlapped with target on control vehicle;
Thus standard forward sight picture and standard side view picture are obtained;
Step 5, during vehicle follow gallop, current vehicle is adjusted as follows:
Forward direction camera and lateral camera obtain real-time forward sight picture and real-time side view picture respectively;
Real-time forward sight picture and standard forward sight picture are compared, if the guide line in forward sight picture deviates standard quarter in real time
Line then calculates guide line deviation distance and deflecting angle;
Real-time side view picture and standard side view picture are compared, if the target in forward sight picture deviates standard target in real time,
Then calculate target deviation distance;
The relationship of distance and actual range in figure is calculated using the parameter that step 3 is demarcated, it follows that guide line is actually inclined
From amount and the fore-and-aft distance of vehicle and control vehicle;
Wherein, the detailed process of guide line deviation distance and deflecting angle is calculated are as follows:
Step 501 is by extracting guiding in real time line, the linear equation a of the guiding in real time line in real-time forward sight imageqox+bqoy+cqo
=0;Wherein x, y are the unknown quantity in the linear equation of guide line, aqo、bqoAnd cqoRespectively in the linear equation of guide line
Coefficient;
The position of step 502 standard groove is determined that the linear equation of standard groove is a by setup parameterqcx'+bqcy'+cqc=0;
Wherein x ', y ' are the unknown quantity in the linear equation of standard groove, aqc、bqcAnd cqcRespectively in the linear equation of standard groove
Coefficient;
Angle theta between step 503 current vehicle and guide line is
Offset d between current vehicle and guide lineqFor
Wherein (x0,y0) it is standard groove aqcx+bqcy+cqcThe midpoint of=0 line segment;
Method in the step 501, by extracting guiding in real time line in real-time forward sight image are as follows:
Standard groove in standard forward sight picture is mapped in real-time forward sight image by step 511, in real-time forward sight image, is asked
The minimum circumscribed rectangle of standard groove is obtained, and this square boundary is expanded 50% as the interesting image regions for extracting guide line
ROI;
Step 512 successively carries out ROI down-sampled, Gaussian Blur, Canny edge extracting, obtains guide line edge graph;
Step 513 carries out Hough transformation to guide line edge graph, extracts the straight line in edge graph;
Step 514 screens resulting straight line, retains the straight line for meeting setting slope range and length range;
Step 515 does least square fitting to the linear equation parameter remained, obtains optimal linear equation estimation and is
Guiding in real time line;
Column adjustment is carried out to vehicle heading according to above-mentioned guide line deflecting angle and guide line practical bias, according to vehicle with
The fore-and-aft distance of control vehicle carries out capable adjustment to Vehicle Speed, finally vehicle is delimited according to lane line and control vehicle
Queue advance.
2. the vehicle formation according to claim 1 based on machine vision is with detection method of speeding, it is characterised in that: described to incite somebody to action
Real-time side view picture is compared with standard side view picture, if the real-time target in forward sight picture deviates standard target in real time,
Target deviation distance is calculated, method particularly includes:
Step 54 extracts initial target target position (x in real-time side view pictureco,yco);
Step 55 is known (x for standard target positioncc,ycc), then fore-and-aft distance
3. the vehicle formation according to claim 2 based on machine vision is with detection method of speeding, it is characterised in that: the step
Initial target target is extracted in rapid 54 in real-time side view picture method particularly includes:
Standard target is mapped in real-time side view picture by step 541, acquires standard target pattern in real-time side view picture
Minimum circumscribed rectangle, and this square boundary is expanded 50% as the interesting image regions for extracting target;
Step 542 successively carries out down-sampled, Gaussian Blur, Canny edge extracting for the interesting image regions of target, obtains
Target edge graph;
Step 543 to target edge graph extract profile, using Hu not displacement as matching characteristic progress template matching;
Step 544 obtains optimal match point coordinate as real-time target target position (xco,yco)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610099028.4A CN105809106B (en) | 2016-02-23 | 2016-02-23 | Vehicle formation based on machine vision is with detection method of speeding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610099028.4A CN105809106B (en) | 2016-02-23 | 2016-02-23 | Vehicle formation based on machine vision is with detection method of speeding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105809106A CN105809106A (en) | 2016-07-27 |
CN105809106B true CN105809106B (en) | 2019-02-26 |
Family
ID=56466385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610099028.4A Active CN105809106B (en) | 2016-02-23 | 2016-02-23 | Vehicle formation based on machine vision is with detection method of speeding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105809106B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107336251A (en) * | 2016-09-20 | 2017-11-10 | 苏州小璐机器人有限公司 | A kind of control method and system of robot queue |
CN106873589B (en) * | 2017-02-16 | 2020-03-20 | 北理慧动(常熟)车辆科技有限公司 | Intelligent vehicle autonomous following method |
CN107727105B (en) * | 2017-04-11 | 2020-03-24 | 西安艾润物联网技术服务有限责任公司 | Motorcade navigation method and device |
CN107333042A (en) * | 2017-07-26 | 2017-11-07 | 西安康发光电信息系统有限公司 | A kind of neat system of vehicle baseline mark |
CN107357296B (en) * | 2017-08-18 | 2021-02-02 | 西安鸣士机电开发有限公司 | Automatic deviation rectifying system and method for seedling raising machine and seedling raising machine |
CN110750877B (en) * | 2019-09-27 | 2024-05-03 | 西安理工大学 | Vehicle following behavior prediction method under Apollo platform |
CN110991452B (en) * | 2019-12-03 | 2023-09-19 | 深圳市捷顺科技实业股份有限公司 | Parking space frame detection method, device, equipment and readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203293984U (en) * | 2012-11-23 | 2013-11-20 | 深圳华一汽车科技有限公司 | Lane departure warning system based on machine vision |
CN103842774A (en) * | 2011-11-02 | 2014-06-04 | 爱信艾达株式会社 | Lane guidance display system, lane guidance display method, and lane guidance display program |
CN103996053A (en) * | 2014-06-05 | 2014-08-20 | 中交第一公路勘察设计研究院有限公司 | Lane departure alarm method based on machine vision |
CN105336217A (en) * | 2015-12-09 | 2016-02-17 | 东华大学 | Driving safety prewarning system based on machine vision and Android platform |
-
2016
- 2016-02-23 CN CN201610099028.4A patent/CN105809106B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103842774A (en) * | 2011-11-02 | 2014-06-04 | 爱信艾达株式会社 | Lane guidance display system, lane guidance display method, and lane guidance display program |
CN203293984U (en) * | 2012-11-23 | 2013-11-20 | 深圳华一汽车科技有限公司 | Lane departure warning system based on machine vision |
CN103996053A (en) * | 2014-06-05 | 2014-08-20 | 中交第一公路勘察设计研究院有限公司 | Lane departure alarm method based on machine vision |
CN105336217A (en) * | 2015-12-09 | 2016-02-17 | 东华大学 | Driving safety prewarning system based on machine vision and Android platform |
Non-Patent Citations (1)
Title |
---|
《基于NMF的道路识别算法在野外环境感知中的应用》;朱昊 等;《红外与激光工程》;20100531;第39卷;全文 |
Also Published As
Publication number | Publication date |
---|---|
CN105809106A (en) | 2016-07-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105809106B (en) | Vehicle formation based on machine vision is with detection method of speeding | |
CN105676253B (en) | Longitudinal register system and method based on urban road graticule map in a kind of automatic Pilot | |
CN107730520B (en) | Lane line detection method and system | |
WO2023124383A1 (en) | Vehicle speed measurement method, collision early-warning method, and electronic 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 | |
CN106530794B (en) | The automatic identification and calibration method and system of carriage way | |
CN102207389B (en) | Vehicle position recognition system | |
DE112014000532B4 (en) | Curve modeling device, curve modeling method and vehicle navigation device | |
CN105955259A (en) | Monocular vision AGV accurate positioning method and system based on multi-window real-time range finding | |
US7016517B2 (en) | Travel road detector | |
CN109849922A (en) | A method of the view-based access control model information for intelligent vehicle is merged with GIS information | |
US9885578B2 (en) | Curve-shape modeling device, vehicle information processing system, curve-shape modeling method, and non-transitory tangible computer readable medium for the same | |
CN106875448A (en) | A kind of vehicle-mounted monocular camera external parameter self-calibrating method | |
US11023744B2 (en) | Road parameter calculator | |
CN104508708B (en) | Road environment identifying device | |
US20200278210A1 (en) | Lane network data generation apparatus and storage medium | |
WO2020083103A1 (en) | Vehicle positioning method based on deep neural network image recognition | |
DE102013105046A9 (en) | Target track selection method by means of navigation input in road change scenarios | |
US20210182575A1 (en) | Device and method for generating travel trajectory data in intersection, and vehicle-mounted device | |
DE112007001076T5 (en) | Vehicle position measuring device | |
DE102007019309A1 (en) | Road information acquisition system, method and program | |
CN106156723A (en) | A kind of crossing fine positioning method of view-based access control model | |
CN106969765A (en) | The method represented for the in-flight track of calculating aircraft | |
EP2416303A2 (en) | Cruise assist system | |
CN113791414B (en) | Scene recognition method based on millimeter wave vehicle-mounted radar view |
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 |