CN106056100B - A kind of vehicle assisted location method based on lane detection and target following - Google Patents
A kind of vehicle assisted location method based on lane detection and target following Download PDFInfo
- Publication number
- CN106056100B CN106056100B CN201610486724.0A CN201610486724A CN106056100B CN 106056100 B CN106056100 B CN 106056100B CN 201610486724 A CN201610486724 A CN 201610486724A CN 106056100 B CN106056100 B CN 106056100B
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- line
- image
- target
- 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
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
- G08G1/133—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams within the vehicle ; Indicators inside the vehicles or at stops
- G08G1/137—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams within the vehicle ; Indicators inside the vehicles or at stops the indicator being in the form of a map
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of vehicle assisted location method based on lane detection and target following, belongs to field of intelligent transportation technology.This method is accurately positioned mainly for the specific lane where vehicle.On the basis of lane detection and multiple target vehicle tracking, using near two lane lines of the vertical central axes of image as this vehicle lane line, using road image bottom edge midpoint as origin, target vehicle and origin are connected with straight line, judge whether the straight line and this vehicle lane line have intersection point, the relative positional relationship for determining target vehicle Yu this lane, the specific lane in conjunction with where relative positional relationship and lane line determine vehicle realize that the lane grade of vehicle positions in conjunction with specific lane information and GPS information.The present invention can make up for it the shortcomings that GPS system can not be accurately positioned the specific lane in this vehicle place, drives for lane grade positioning and auxiliary and provides relatively reliable and accurate data.
Description
Technical field
The invention belongs to field of intelligent transportation technology, and it is a kind of fixed based on lane detection and the vehicle of target following auxiliary to be related to
Position method.
Background technique
Automated driving system utilizes multiple sensors, perceives vehicle-periphery, and the road obtained according to sensory perceptual system
Lane information, vehicle location and status information and obstacle information construct local map, plan local path, and real-time control
The steering and speed for controlling vehicle, so that vehicle can be travelled reliably and securely on road.It can hold people from single
It is freed in long driving-activity, reduces influence of the driving behavior difference to traffic flow stability, be conducive to improve existing road
The vehicle pass-through rate of road network alleviates traffic congestion, and ride safety of automobile on the other hand can be improved, and reduces traffic accident rate and changes
It is apt to traffic safety, reduces energy consumption and environmental pollution, makes the transition to China's energy and reduce pollution, alleviation traffic congestion has great meaning
Justice.
Lane location where vehicle is a pith of automatic Pilot, and especially currently own vehicle increasingly increases,
More and more complicated urban traffic environment brings new challenge to the lives and properties of people.Only due to current GPS positioning system
Highway where vehicle and highway direction can be positioned, the accurate positioning in lane where vehicle can not be carried out.Currently, in order to
The vehicle location for realizing the required accuracy, requires the correction from outside vehicle source.Such as there are relative positioning or difference
Have that price is higher the shortcomings that DGPS, wide area enhancement system etc., such system, the received information in some areas does not cause with new
With practical crossing difference, can not be accurate to vehicle it is specific where which lane positioning.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of vehicle auxiliary positioning based on lane detection and target following
Video tracking and GPS are combined realization lane location by method, this method, improve lane location precision, are intelligent vehicle
Decision system provides more road environment information, the homing capability of enhanced navigation equipment.
In order to achieve the above objectives, the invention provides the following technical scheme:
A kind of vehicle assisted location method based on lane detection and target following, method includes the following steps:
S1: detection lane line and determining this vehicle lane line, input video sequence pre-process image, utilize Hough
Transformation detects lane line with straight line fitting, and taking the left and right sides lane line near the vertical central axes of image is this vehicle lane line, just
Area-of-interest where step prediction next frame lane;
S2: vehicle is detected with trained auto model in advance, vehicle is tracked using Kalman filtering algorithm, utilizes breast tooth
Sharp algorithm (Hungarian Algorithm) is associated with the same target of adjacent two frame;Calculate front vehicles on the image with lane
Vehicle region is removed from the lane line area-of-interest of tentative prediction, redefines next frame vehicle by the overlapping region of line
Diatom area-of-interest;
S3: calculating the relative positional relationship of front vehicles and this lane, in conjunction with relative positional relationship and the lane detected
Line determines the lane information of this vehicle, location information of this vehicle on map is determined using GPS positioning system, by location information and vehicle
The lane grade positioning to vehicle is realized in information fusion in road.
Further, the step S1 is specifically included:
S11: assuming that the road image of input video sequence is u × v, part 1/3 on image being removed, and with u/2 is
Line divides the image into left and right two parts region of interest ROI 1 and ROI2;
S12: gray processing processing is carried out to image and median filtering denoises, then carries out edge inspection using Canny algorithm
It surveys, then image carries out Hough transform to treated, the lane line in detection image;The lane line for taking the rightmost side in ROI1 is
This lane left-lane line, taking the lane line of the leftmost side in ROI2 is this lane right-lane line;
S13: using the slope of lane line, intercept, slope variation rate and intercept change rate as state variable, karr is utilized
Graceful filter forecasting goes out the preliminary area-of-interest of the next frame lane line.
Further, the step S2 is specifically included:
S21: the vehicle in the auto model detection image of DPM algorithm (Deformable Parts Model) training is used
?;
S22: utilizing Kalman prediction vehicle location, gives the state vector V of target vehicletIt is as follows
Vt=[xt yt wt ht Δxt Δyt ψt]T
ψt∈{-1,0,1}
Wherein xt, ytIndicate the top left co-ordinate of vehicle target framework in the picture, wt, htIndicate the width and height of the frame,
Δxt, Δ ytIndicate adjacent two frames xt, ytChange rate, ψtIndicate position of the vehicle relative to this lane;
S23: data correlation uses Hungary Algorithm (Hungarian Algorithm): first with vehicle relative to this
The position in lane is to the vehicle classification detected, to the vehicle in same lane respectively with former frame with each vehicle in lane
Euclidean distance, and the confidence level matrix inputted using the distance matrix as Hungary Algorithm are calculated, according to of Hungary Algorithm
Data correlation is realized with result;
S24: wherein the finding process of confidence level is: assuming that t moment tracking number of targets is Nt, the t+1 moment detects number of targets
For Mt+1, and have learned that lane where each vehicle;Euclidean distance is calculated separately to each vehicle of adjacent moment in same lane, it is assumed that have n
Lane, in the lane n, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itIndicate the image coordinate of i-th of target in the t moment lane, jt+1It indicates in the t+1 moment lane
The image coordinate of j-th of target, | | indicate Euclidean distance calculation method;
S25: a bipartite graph G is defined1(D, T:E), wherein each edge E has a non-negative confidence level CijIndicate detection knot
The similarity of fruit and tracking target, is indicated with Euclidean distance, is solved most by Hungary Algorithm (Hungarian Algorithm)
Excellent matching;
S26: judging the region of vehicle in the picture and lane area-of-interest lap, calculates vehicle region r1With vehicle
Road area-of-interest r2Lap, formula is as follows:
Overlap=r1∩r2;
S27: new lane line area-of-interest is r2-overlap。
Further, the step S3 is specifically included:
S31: the relative positional relationship of front vehicles and this lane is calculated, it is assumed that the detection framework of one of target vehicle
For (x, y, w, h), wherein x, the pixel coordinate in the y representational framework upper left corner, w, h indicate wide and high;It takes a little
WithLinear equation is established, if the straight line and left-lane line straight line intersection, which is located on the left of this vehicle lane, is denoted as
State -1;If the straight line does not intersect with lane line, which is located in this vehicle lane, is denoted as state 0;If the straight line and the right side
Lane line straight line intersection, then the vehicle is located on the right side of this vehicle lane, is denoted as state 1;
S32: in conjunction with the flag state of institute's measuring car diatom and target vehicle on every lane, the vehicle in lane where determining this vehicle
Road sequence, lane sequence is merged with location information of the GPS on map, final to realize lane grade positioning.
The beneficial effects of the present invention are: present invention utilizes lane detections and vehicle tracking, compared with prior art
Improve the accuracy and efficiency of vehicle and lane line tracking under complex environment;It closes the relative position for establishing vehicle and lane line
System, reduces vehicle and lane line tracks mutual interference, while association algorithm is only to the vehicle target in same lane
It is matched, improves the accuracy and efficiency of vehicle tracking.The relationship for finally utilizing vehicle and lane line, is realized locating for this vehicle
The determination in lane, vehicle place highway can only be positioned and vehicle which lane on highway can not be determined by compensating for GPS system
Disadvantage provides relatively reliable precise information for vehicle drive.
Detailed description of the invention
In order to keep the purpose of the present invention, technical scheme and beneficial effects clearer, the present invention provides following attached drawing and carries out
Illustrate:
Fig. 1 is the method flow diagram of the embodiment of the present invention;
Fig. 2 is that the lane line in lane where the vehicle of the embodiment of the present invention determines figure;
Fig. 3 is the bipartite graph matching figure of the embodiment of the present invention;
Fig. 4 is that the front vehicles of the embodiment of the present invention and the relative positional relationship in vehicle place lane determine and scheme;
Fig. 5 is that the lane location of the embodiment of the present invention determines method.
Specific embodiment
Below in conjunction with attached drawing, a preferred embodiment of the present invention will be described in detail.
Fig. 1 is the method flow diagram of the embodiment of the present invention, as shown in Figure 1, provided by the invention be based on lane detection and mesh
Mark the vehicle assisted location method of tracking, comprising the following steps:
Step 1: detection lane line and determining this vehicle lane line, between video camera is mounted on intelligent vehicle front dead center, camera shooting
Machine it is horizontally toward identical as direction of traffic.In the video sequence of video camera acquisition, by road image vertical central axes point
At left and right two parts, image preprocessing is carried out respectively, detects lane line using Canny and Hough transform, is taken perpendicular near image
The left and right sides lane line of straight central axes is this vehicle lane line.Fig. 2 is the lane in lane where the vehicle of the embodiment of the present invention
Line determines figure.Area-of-interest in conjunction with where Kalman filtering tentative prediction goes out next frame lane line, detailed process is as follows:
11) road image for assuming input video sequence is u × v, part 1/3 on image is removed, and using u/2 as middle line
Divide the image into left and right two parts region of interest ROI 1 and ROI2;
12) gray processing processing is carried out to image and median filtering denoises, then carry out edge inspection using Canny algorithm
It surveys, then image carries out Hough transform to treated, straight line fitting extracts the lane line in image.Take the rightmost side in ROI1
Lane line be this lane left-lane line, take the leftmost side in ROI2 lane line be this lane right-lane line;
13) go out the area-of-interest of the next frame lane line using Kalman prediction: by taking right lane as an example, with (kr,
br) indicate lane line straight line slope and intercept, with (Δ kr, Δ br) indicate slope and intercept change rate, so being defined as follows:
State variable are as follows: Xr(n)=(kr,br,Δkr,Δbr)
Observation vector: Zr=(kr,br)
P (n, n-1) is obtained by Kalman filtering algorithm:
P (n, n-1)=AP (n-1) AT+Q
Wherein A indicates that state-transition matrix, Q indicate the error co-variance matrix of system equation.
P (n) is obtained by Kalman filtering algorithm predictive equation:
P (n)=P (n, n-1)-K (n) × H (n) P (n, n-1)
P (n) indicates the uncertain region of area-of-interest, and P (n, n-1) indicates the n-1 moment to n moment uncertain region
Predicted value, K (n) indicates that gain matrix, H (n) indicate observing matrix, after entering tracking, then the range of interest of right-lane line:
14) t moment directly detects lane line out of t-1 frame obtains area-of-interest, if can not examine in this interest range
Lane line is measured, 11) step is repeated and starts to carry out lane detection.
Step 2: target vehicle detection is carried out with preparatory trained model, tracks vehicle using Kalman filtering algorithm,
The same target of adjacent two frame is associated with using Hungary Algorithm (Hungarian Algorithm), specifically includes the following steps:
21) using in the auto model detection video sequence of DPM algorithm (Deformable Parts Model) training
Vehicle, obtains the location information of vehicle in the picture, and location information is described with rectangular frame;
22) Kalman prediction vehicle location is utilized, the state vector V of target vehicle is giventIt is as follows:
Vt=[xt yt wt ht Δxt Δyt ψt]T
ψt∈{-1,0,1}
Wherein xt, yt, wt, htIt is frame of the target vehicle in the plane of delineation, Δ xt, Δ ytIndicate adjacent two frames xt, yt's
Change rate, ψtIndicate position of the vehicle relative to this lane;
23) data correlation uses Hungary Algorithm (Hungarian Algorithm): first with vehicle relative to this vehicle
The position in road is to the vehicle classification detected, to the vehicle in same lane respectively with former frame with each vehicle meter in lane
Euclidean distance is calculated, and using the distance matrix as the input of Hungary Algorithm, number is realized according to the matching result of Hungary Algorithm
According to association.
24) wherein the finding process of confidence level is: assuming that t moment tracking number of targets is Nt, the t+1 moment detects number of targets and is
Mt+1, and have learned that lane where each vehicle.Euclidean distance is calculated separately to each vehicle of adjacent moment in same lane, it is assumed that have n item
Lane, in the lane n, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itIndicate the image coordinate of i-th of target in the t moment lane, jt+1It indicates in the t+1 moment lane
The image coordinate of j-th of target, | | indicate Euclidean distance calculation method.
25) a bipartite graph G is defined1(D, T:E), wherein each edge E has a non-negative confidence level CijIndicate detection knot
The similarity of fruit and tracking target, is indicated with Euclidean distance here, is solved by Hungary Algorithm (Hungarian Algorithm)
Optimum Matching out, wherein Hungary Algorithm matching process is as shown in Figure 3.
Step 3: vehicle region being removed from lane detection interest region, redefines lane line region of interest
Domain, specifically includes the following steps:
31) judge the region of vehicle in the picture and lane area-of-interest lap, calculate vehicle region r1With vehicle
Road area-of-interest r2Lap, formula is as follows:
Overlap=r1∩r2;
32) new lane line area-of-interest is r2-overlap。
Step 4: calculating positional relationship and label of each vehicle in front relative to this lane and determined in conjunction with institute's measuring car diatom
The lane sequence in lane where this vehicle, specifically includes the following steps:
41) relative positional relationship of front vehicles and this lane is calculated, it is assumed that the detection framework of one of target vehicle
For (x, y, w, h), wherein x, the pixel coordinate in the y representational framework upper left corner, w, h indicate wide and high.It takes a little
WithLinear equation is established, if straight line intersection on the left of the straight line and lane line, which is located on the left of this vehicle lane, note
For state -1;If the straight line does not have phase alternating current with lane line, which is located in this vehicle lane, is denoted as state 0;If the straight line
With straight line intersection on the right side of lane line, then the vehicle is located on the right side of this vehicle lane, is denoted as state 1, deterministic process is as shown in Figure 4.
42) present invention sets lane and arranges by the sequence turned left from the right side, is equipped with 4 lanes, then lane sequence is past from the right side
Left is 1 lane, 2 lanes, 3 lanes, 4 lanes respectively.Assuming that all detect vehicle on every lane, take on every lane near
The target vehicle of this nearly vehicle makes a decision, and the status indication of the vehicle is obtained, if the status indication collection of this 4 target vehicles is combined into R.If
R ∈ { -1, -1, -1,0 }, then this vehicle is on 1 lane, as shown in Fig. 5 (a).If R ∈ { -1, -1,0,1 }, then this vehicle is in 2 vehicles
On road, as shown in Fig. 5 (b).If R ∈ { -1,0,1,1 }, then this vehicle is on 3 lanes, as shown in Fig. 5 (c).If R ∈ 0,1,1,
1 }, then this vehicle is on 4 lanes, as shown in Fig. 5 (d).Method is analogized in due order in the lane of other quantity.
Step 5: the driving direction of highway and vehicle where determining vehicle using GPS, in conjunction with specific lane information and GPS
Information, the final lane grade positioning for realizing vehicle.
Finally, it is stated that preferred embodiment above is only used to illustrate the technical scheme of the present invention and not to limit it, although logical
It crosses above preferred embodiment the present invention is described in detail, however, those skilled in the art should understand that, can be
Various changes are made to it in form and in details, without departing from claims of the present invention limited range.
Claims (2)
1. a kind of vehicle assisted location method based on lane detection and target following, it is characterised in that: this method includes following
Step:
S1: detection lane line and determining this vehicle lane line, input video sequence pre-process image, utilize Hough transform
Lane line is detected with straight line fitting, taking the left and right sides lane line near the vertical central axes of image is this vehicle lane line, preliminary pre-
Survey the area-of-interest where next frame lane;
S2: vehicle is detected with trained auto model in advance, vehicle is tracked using Kalman filtering algorithm, is calculated using Hungary
Method (Hungarian Algorithm) is associated with the same target of adjacent two frame;Calculate front vehicles on the image with lane line
Vehicle region is removed from the lane line area-of-interest of tentative prediction, redefines next frame lane line by overlapping region
Area-of-interest;
S3: calculating the relative positional relationship of front vehicles and this lane, true in conjunction with relative positional relationship and the lane line that detects
The lane information of Ding Benche determines location information of this vehicle on map using GPS positioning system, and location information and lane are believed
The lane grade positioning to vehicle is realized in breath fusion;
The step S1 is specifically included:
S11: assuming that the road image of input video sequence is u × v, part 1/3 on image being removed, and will by middle line of u/2
Image is divided into left and right two parts region of interest ROI 1 and ROI2;
S12: carrying out gray processing processing to image and median filtering denoise, and then carries out edge detection using Canny algorithm, then
To treated, image carries out Hough transform, the lane line in detection image;The lane line for taking the rightmost side in ROI1 is this lane
Left-lane line, taking the lane line of the leftmost side in ROI2 is this lane right-lane line;
S13: it using the slope of lane line, intercept, slope variation rate and intercept change rate as state variable, is filtered using Kalman
Wave predicts the preliminary area-of-interest of the next frame lane line;
The step S2 is specifically included:
S21: the vehicle in the auto model detection image of DPM algorithm (Deformable Parts Model) training is used;
S22: utilizing Kalman prediction vehicle location, gives the state vector V of target vehicletIt is as follows
Vt=[xt yt wt ht Δxt Δyt ψt]T
ψt∈{-1,0,1}
Wherein xt, ytIndicate the top left co-ordinate of vehicle target framework in the picture, wt, htIndicate the width and high, Δ x of the framet,
ΔytIndicate adjacent two frames xt, ytChange rate, ψtIndicate position of the vehicle relative to this lane;
S23: data correlation uses Hungary Algorithm (Hungarian Algorithm): first with vehicle relative to this lane
Position to the vehicle classification detected, the vehicle in same lane is calculated with former frame with each vehicle in lane respectively
Euclidean distance, and the confidence level matrix inputted using the distance matrix as Hungary Algorithm, according to the matching knot of Hungary Algorithm
Fruit shows data correlation;
S24: wherein the finding process of confidence level is: assuming that t moment tracking number of targets is Nt, it is M that the t+1 moment, which detects number of targets,t+1,
And have learned that lane where each vehicle;Euclidean distance is calculated separately to each vehicle of adjacent moment in same lane, it is assumed that have n vehicle
Road, in the lane n, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itIndicate the image coordinate of i-th of target in the t moment lane, jt+1Indicate j-th in the t+1 moment lane
The image coordinate of target, | | indicate Euclidean distance calculation method;
S25: a bipartite graph G is defined1(D, T:E), wherein each edge E has a non-negative confidence level CijIndicate testing result with
The similarity for tracking target, is indicated with Euclidean distance, solves optimal by Hungary Algorithm (Hungarian Algorithm)
Match;
S26: judging the region of vehicle in the picture and lane area-of-interest lap, calculates vehicle region r1Feel with lane
Interest region r2Lap, formula is as follows:
Overlap=r1∩r2;
S27: new lane line area-of-interest is r2-overlap。
2. a kind of vehicle assisted location method based on lane detection and target following according to claim 1, feature
Be: the step S3 is specifically included:
S31: the relative positional relationship of front vehicles and this lane is calculated, it is assumed that the detection framework of one of target vehicle is
(x, y, w, h), wherein x, the pixel coordinate in the y representational framework upper left corner, w, h indicate wide and high;It takes a littleWithLinear equation is established, if the straight line and left-lane line straight line intersection, which is located on the left of this vehicle lane, is denoted as
State -1;If the straight line does not intersect with lane line, which is located in this vehicle lane, is denoted as state 0;If the straight line and the right side
Lane line straight line intersection, then the vehicle is located on the right side of this vehicle lane, is denoted as state 1;
S32: in conjunction with the flag state of institute's measuring car diatom and target vehicle on every lane, the lane in lane is suitable where determining this vehicle
Sequence merges lane sequence with location information of the GPS on map, final to realize lane grade positioning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610486724.0A CN106056100B (en) | 2016-06-28 | 2016-06-28 | A kind of vehicle assisted location method based on lane detection and target following |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610486724.0A CN106056100B (en) | 2016-06-28 | 2016-06-28 | A kind of vehicle assisted location method based on lane detection and target following |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106056100A CN106056100A (en) | 2016-10-26 |
CN106056100B true CN106056100B (en) | 2019-03-08 |
Family
ID=57165874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610486724.0A Active CN106056100B (en) | 2016-06-28 | 2016-06-28 | A kind of vehicle assisted location method based on lane detection and target following |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106056100B (en) |
Families Citing this family (42)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529443B (en) * | 2016-11-03 | 2019-09-06 | 温州大学 | The method for improving Hough variation detection lane line |
CN106652445B (en) * | 2016-11-15 | 2019-08-23 | 成都通甲优博科技有限责任公司 | A kind of road traffic accident method of discrimination and device |
CN107239762A (en) * | 2017-06-06 | 2017-10-10 | 电子科技大学 | Patronage statistical method in a kind of bus of view-based access control model |
CN109029438B (en) * | 2017-06-12 | 2023-05-05 | 广州英卓电子科技有限公司 | Vehicle positioning method in limited area |
WO2019001698A1 (en) * | 2017-06-28 | 2019-01-03 | Huawei Technologies Co., Ltd. | Advanced driver assistance system and method |
CN107562837B (en) * | 2017-08-24 | 2020-05-12 | 电子科技大学 | Maneuvering target tracking algorithm based on road network |
CN109858307A (en) * | 2017-11-30 | 2019-06-07 | 高德软件有限公司 | A kind of Lane detection method and apparatus |
CN108171154A (en) * | 2017-12-27 | 2018-06-15 | 邦鼓思电子科技(上海)有限公司 | A kind of method that target detection is combined with lane detection in automatic Pilot |
CN108413971B (en) * | 2017-12-29 | 2021-12-14 | 驭势科技(北京)有限公司 | Vehicle positioning technology based on lane line and application |
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 |
CN108804995B (en) * | 2018-03-23 | 2019-04-16 | 新昌县夙凡软件科技有限公司 | Toilet facility distributed image identifying platform |
CN108615242B (en) * | 2018-05-04 | 2021-07-27 | 重庆邮电大学 | High-speed guardrail tracking method |
CN109147316B (en) * | 2018-07-23 | 2022-05-03 | 重庆邮电大学 | Urban lane vehicle statistical method based on V2X communication and high-precision positioning |
CN109215059B (en) * | 2018-10-16 | 2021-06-29 | 西安建筑科技大学 | Local data association method for tracking moving vehicle in aerial video |
CN109359596A (en) * | 2018-10-18 | 2019-02-19 | 上海电科市政工程有限公司 | A kind of highway vehicle localization method fast and accurately |
CN109540157B (en) * | 2018-11-12 | 2021-02-02 | 广东星舆科技有限公司 | Vehicle-mounted navigation system and control method |
CN111311902B (en) * | 2018-12-12 | 2022-05-24 | 斑马智行网络(香港)有限公司 | Data processing method, device, equipment and machine readable medium |
CN109583418B (en) * | 2018-12-13 | 2021-03-12 | 武汉光庭信息技术股份有限公司 | Lane line deviation self-correction method and device based on parallel relation |
CN109443374A (en) * | 2018-12-26 | 2019-03-08 | 联创汽车电子有限公司 | Lane line emerging system and its fusion method |
CN109872341B (en) * | 2019-01-14 | 2020-11-24 | 中建三局智能技术有限公司 | High-altitude parabolic detection method and system based on computer vision |
CN109815900A (en) * | 2019-01-24 | 2019-05-28 | 深圳市路畅智能科技有限公司 | A kind of vehicle method for self-locating and system based on auxiliary positioning line |
CN109816980A (en) * | 2019-02-20 | 2019-05-28 | 东软睿驰汽车技术(沈阳)有限公司 | The method and relevant apparatus in lane locating for a kind of determining vehicle |
CN109886215B (en) * | 2019-02-26 | 2021-10-19 | 常熟理工学院 | Low-speed park unmanned vehicle cruise and emergency braking system based on machine vision |
JP2022520544A (en) * | 2019-02-28 | 2022-03-31 | シェンチェン センスタイム テクノロジー カンパニー リミテッド | Vehicle intelligent driving control methods and devices, electronic devices and storage media |
CN109927722A (en) * | 2019-03-01 | 2019-06-25 | 武汉光庭科技有限公司 | The method and system that the lane of view-based access control model and combined inertial nevigation is kept in automatic Pilot |
CN110077399B (en) * | 2019-04-09 | 2020-11-06 | 魔视智能科技(上海)有限公司 | Vehicle anti-collision method based on road marking and wheel detection fusion |
CN110110029B (en) * | 2019-05-17 | 2021-08-24 | 百度在线网络技术(北京)有限公司 | Method and device for lane matching |
CN110458050B (en) * | 2019-07-25 | 2023-06-06 | 清华大学苏州汽车研究院(吴江) | Vehicle cut-in detection method and device based on vehicle-mounted video |
CN112441022B (en) * | 2019-09-02 | 2023-02-03 | 华为技术有限公司 | Lane center line determining method and device |
CN110595490B (en) * | 2019-09-24 | 2021-12-14 | 百度在线网络技术(北京)有限公司 | Preprocessing method, device, equipment and medium for lane line perception data |
CN110796102B (en) * | 2019-10-31 | 2023-04-14 | 重庆长安汽车股份有限公司 | Vehicle target sensing system and method |
TWI723679B (en) * | 2019-12-13 | 2021-04-01 | 宏碁股份有限公司 | Lane positioning system and lane positioning method |
CN113128317B (en) * | 2020-01-15 | 2024-03-26 | 宏碁股份有限公司 | Lane positioning system and lane positioning method |
CN111580522A (en) * | 2020-05-15 | 2020-08-25 | 东风柳州汽车有限公司 | Control method for unmanned vehicle, and storage medium |
CN112289022B (en) * | 2020-09-29 | 2022-02-25 | 西安电子科技大学 | Black smoke vehicle detection and judgment method and system based on space-time background comparison |
CN112562324A (en) * | 2020-11-27 | 2021-03-26 | 惠州华阳通用电子有限公司 | Automatic driving vehicle crossing passing method and device |
CN115451982A (en) * | 2021-06-09 | 2022-12-09 | 腾讯科技(深圳)有限公司 | Positioning method and related device |
CN113792634B (en) * | 2021-09-07 | 2022-04-15 | 北京易航远智科技有限公司 | Target similarity score calculation method and system based on vehicle-mounted camera |
CN115223131A (en) * | 2021-11-09 | 2022-10-21 | 广州汽车集团股份有限公司 | Adaptive cruise following target vehicle detection method and device and automobile |
CN114212079B (en) * | 2022-02-18 | 2022-05-20 | 国汽智控(北京)科技有限公司 | ACC-based vehicle control method, device and system |
CN115033731B (en) * | 2022-07-04 | 2023-07-18 | 小米汽车科技有限公司 | Image retrieval method, device, electronic equipment and storage medium |
CN115320553A (en) * | 2022-08-30 | 2022-11-11 | 桂林电子科技大学 | Front vehicle positioning judgment method of AEB system under curve-oriented condition |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10115026B2 (en) * | 2014-04-04 | 2018-10-30 | Delphi Technologies, Inc. | Method for lane detection |
US9098753B1 (en) * | 2014-04-25 | 2015-08-04 | Google Inc. | Methods and systems for object detection using multiple sensors |
CN104008645B (en) * | 2014-06-12 | 2015-12-09 | 湖南大学 | One is applicable to the prediction of urban road lane line and method for early warning |
-
2016
- 2016-06-28 CN CN201610486724.0A patent/CN106056100B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN106056100A (en) | 2016-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106056100B (en) | A kind of vehicle assisted location method based on lane detection and target following | |
CN107031623B (en) | A kind of road method for early warning based on vehicle-mounted blind area camera | |
CN104166400B (en) | Multi-sensor fusion-based visual navigation AGV system | |
CN107025432B (en) | A kind of efficient lane detection tracking and system | |
CN106256606B (en) | A kind of lane departure warning method based on vehicle-mounted binocular camera | |
CN104318258B (en) | Time domain fuzzy and kalman filter-based lane detection method | |
Nieto et al. | Road environment modeling using robust perspective analysis and recursive Bayesian segmentation | |
CN104700414B (en) | A kind of road ahead pedestrian's fast ranging method based on vehicle-mounted binocular camera | |
CN106156723B (en) | A kind of crossing fine positioning method of view-based access control model | |
CN101929867B (en) | Clear path detection using road model | |
Wu et al. | Applying a functional neurofuzzy network to real-time lane detection and front-vehicle distance measurement | |
CN109460709A (en) | The method of RTG dysopia analyte detection based on the fusion of RGB and D information | |
CN102867416B (en) | Vehicle part feature-based vehicle detection and tracking method | |
CN107463890B (en) | A kind of Foregut fermenters and tracking based on monocular forward sight camera | |
CN106778593A (en) | A kind of track level localization method based on the fusion of many surface marks | |
CN106682586A (en) | Method for real-time lane line detection based on vision under complex lighting conditions | |
Sivaraman et al. | Combining monocular and stereo-vision for real-time vehicle ranging and tracking on multilane highways | |
Wang et al. | Bionic vision inspired on-road obstacle detection and tracking using radar and visual information | |
CN103324913A (en) | Pedestrian event detection method based on shape features and trajectory analysis | |
CN107389084A (en) | Planning driving path planing method and storage medium | |
CN101963509A (en) | Clear path detection through road modeling | |
CN115372958A (en) | Target detection and tracking method based on millimeter wave radar and monocular vision fusion | |
Shunsuke et al. | GNSS/INS/on-board camera integration for vehicle self-localization in urban canyon | |
CN102252859B (en) | Road train straight-line running transverse stability automatic identification system | |
CN104751151A (en) | Method for identifying and tracing multiple lanes in real time |
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 |