CN106056100A - Vehicle auxiliary positioning method based on lane detection and object tracking - Google Patents

Vehicle auxiliary positioning method based on lane detection and object tracking Download PDF

Info

Publication number
CN106056100A
CN106056100A CN201610486724.0A CN201610486724A CN106056100A CN 106056100 A CN106056100 A CN 106056100A CN 201610486724 A CN201610486724 A CN 201610486724A CN 106056100 A CN106056100 A CN 106056100A
Authority
CN
China
Prior art keywords
vehicle
track
lane
lane line
car
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
Application number
CN201610486724.0A
Other languages
Chinese (zh)
Other versions
CN106056100B (en
Inventor
朱浩
胡劲松
张斌
李银国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN201610486724.0A priority Critical patent/CN106056100B/en
Publication of CN106056100A publication Critical patent/CN106056100A/en
Application granted granted Critical
Publication of CN106056100B publication Critical patent/CN106056100B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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 invention relates to a vehicle auxiliary positioning method based on lane detection and object tracking, belonging to technical field of intelligent traffic. The method aims to accurately position the specific lane of a vehicle. Based on the lane line detection and multi-target vehicle tracking, the two lane lines closest to the vertical axis of an image are taken as the lane lines of the vehicle and the target vehicle is connected with the original point via a straight line by taking the midpoint of the bottom edge of the road image as the original point, and whether the straight line is intersected with the lane lines of the vehicle is determined to determine the relative position relation of the target vehicle and the lane, and through the combination of the relative position relation and the lane lines, the specific lane of the vehicle can be determined, and the lane level positioning of the vehicle can be realized through the combination of the specific lane information and the GPS information. According to the invention, the defect that a GPS system cannot accurately position the specific lane of the vehicle is made up, and more reliable and accurate data is provided for the lane level positioning and auxiliary driving.

Description

A kind of vehicle assisted location method based on lane detection Yu target following
Technical field
The invention belongs to technical field of intelligent traffic, it is a kind of fixed with the vehicle auxiliary of target following based on lane detection to relate to Method for position.
Background technology
Automated driving system utilizes multiple sensors, perception vehicle-periphery, and the road obtained according to sensory perceptual system Lane information, vehicle location and status information and obstacle information, build local map, plan local path, and control in real time Control turning to and speed of vehicle, so that vehicle can reliably and securely travel on road.It can hold people from single Long driving-activity frees, reduces the impact on traffic flow stability of the driving behavior difference, be conducive to improving existing road The vehicle pass-through rate of road network alleviates traffic congestion, on the other hand can improve ride safety of automobile, reduces road accident rate and changes It is apt to traffic safety, reduces energy resource consumption and environmental pollution, the minimizing transition pollution of China's energy, alleviation traffic congestion are had great meaning Justice.
Location, track, vehicle place is a pith of automatic Pilot, and the most currently having vehicle by oneself increases day by day, The most complicated urban traffic environment brings new challenge to the lives and properties of people.Due to current GPS alignment system only Vehicle place highway and highway direction can be positioned, it is impossible to carry out being accurately positioned of track, vehicle place.At present, in order to Realize the vehicle location of required precision, be required for the correction from outside vehicle source.Such as there are relative localization or difference DGPS, WAAS etc., the shortcoming of this type of system has price higher, and the information that some areas receive is not with newly causing With actual crossing difference, it is impossible to be accurate to the location in any bar track, the concrete place of vehicle.
Summary of the invention
In view of this, it is an object of the invention to provide a kind of vehicle auxiliary positioning based on lane detection Yu target following Method, the method video tracking and GPS are combined realize track location, improve track positioning precision, for intelligent vehicle Decision system provides more road environment information, the homing capability of enhanced navigation equipment.
For reaching above-mentioned purpose, the present invention provides following technical scheme:
A kind of vehicle assisted location method based on lane detection Yu target following, the method comprises the following steps:
S1: detect lane line and determine this car lane line, input video sequence, image is carried out pretreatment, utilizes Hough Conversion detects lane line with fitting a straight line, and taking the left and right sides lane line near the vertical axis of image is this car lane line, just The area-of-interest at step prediction place, next frame track；
S2: with the good auto model detection vehicle of training in advance, utilize Kalman filtering algorithm to follow the tracks of vehicle, utilize breast tooth Profit algorithm (Hungarian Algorithm) associates the same target of adjacent two frames；Calculate front vehicles on image with track The overlapping region of line, removes vehicle region from the lane line area-of-interest of preliminary forecasting, redefines next frame car Diatom area-of-interest；
S3: calculate the relative position relation of front vehicles and this track, in conjunction with relative position relation and the track detected Line determines the lane information of this car, utilizes GPS alignment system to determine this car positional information on map, by positional information and car Road information fusion realizes the level location, track to vehicle.
Further, described step S1 specifically includes:
S11: the road image assuming input video sequence is u × v, image upper part 1/3 is removed, and with u/2 be Image is divided into left and right two parts region of interest ROI 1 and ROI2 by line；
S12: image carries out gray processing process and medium filtering denoising, then utilizes Canny algorithm to carry out edge inspection Survey, then the image after processing is carried out Hough transform, the lane line in detection image；Taking the lane line of the rightmost side in ROI1 is This track left-lane line, taking the lane line of the leftmost side in ROI2 is this track right lane line；
S13: using slope, intercept, slope variation rate and the intercept rate of change of lane line as state variable, utilize karr Graceful filter forecasting goes out the preliminary area-of-interest of this lane line of next frame.
Further, described step S2 specifically includes:
S21: the auto model using DPM algorithm (Deformable Parts Model) to train detects the car in image ?；
S22: utilize Kalman prediction vehicle location, state vector V of given target vehicletAs follows
Vt=[xt yt wt htΔitΔjtψt]T
ψt∈{-1,0,1}
Wherein xt, ytRepresent the top left co-ordinate of vehicle target framework in the picture, wt, htRepresent width and the height of this framework, Δxt, Δ ytRepresent adjacent two frame xt, ytRate of change, ψ represents the vehicle position relative to this track；
S23: data association uses Hungary Algorithm (HungarianAlgorithm): first with vehicle relative to this car The position in the road vehicle classification to detecting, to the vehicle being in same track respectively with former frame with each car meter in track Calculate Euclidean distance, and the confidence level matrix inputted using this distance matrix as Hungary Algorithm, according to the coupling of Hungary Algorithm Result realizes data association；
S24: wherein the process of asking for of confidence level is: assuming that t follows the tracks of number of targets is Nt, the t+1 moment detects number of targets For Mt+1, and have learned that track, each car place；The each vehicle of adjacent moment in same track is calculated Euclidean distance respectively, it is assumed that have n Bar track, by as a example by n track, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itThe image coordinate of the i-th target in expression this track of t, jt+1In representing this track of t+1 moment The image coordinate of jth target, | | represent Euclidean distance computational methods；
S25: define a bipartite graph G1(D, T:E), wherein each edge E has the confidence level C of a non-negativeijRepresent detection knot Fruit and the similarity following the tracks of target, represented with Euclidean distance, solved by Hungary Algorithm (Hungarian Algorithm) Excellent coupling；
S26: judge vehicle region in the picture and track area-of-interest lap, calculates vehicle region r1With car Road area-of-interest r2Lap, formula is as follows:
Overlap=r1∩r2；
S27: new lane line area-of-interest is r2-overlap。
Further, described step S3 specifically includes:
S31: calculate the relative position relation of front vehicles and this track, it is assumed that the detection framework of one of them target vehicle For (x, y, w, h), the pixel coordinate in wherein x, the y representational framework upper left corner, w, h represent wide and high；Take a littleWithSetting up linear equation, if this straight line and left-lane line straight line intersection, then this vehicle is positioned on the left of this car track, is designated as shape State-1；If this straight line does not intersect with lane line, then this vehicle is positioned at this car track, is designated as state 0；If this straight line and right car Diatom straight line intersection, then this vehicle is positioned on the right side of this car track, is designated as state 1；
S32: combine institute's measuring car diatom and the flag state of target vehicle on every track, determine the car in track, this car place Road order, merges track order with GPS positional information on map, finally realizes level location, track.
The beneficial effects of the present invention is: present invention utilizes lane detection and vehicle tracking, compared with prior art Improve accuracy and efficiency that under complex environment, vehicle is followed the tracks of with lane line；Set up vehicle position relative with lane line to close System, decreases vehicle and follows the tracks of interference each other with lane line, and association algorithm is only to the vehicle target in same track simultaneously Mate, improve accuracy and the efficiency of vehicle tracking.Finally utilize the relation of vehicle and lane line, it is achieved residing for this car The determination in track, compensate for GPS system and can only position vehicle place highway and cannot determine vehicle which bar track on highway Shortcoming, provides relatively reliable precise information for vehicle drive.
Accompanying drawing explanation
In order to make the purpose of the present invention, technical scheme and beneficial effect clearer, the present invention provides drawings described below to carry out Illustrate:
Fig. 1 is the method flow diagram of the embodiment of the present invention；
Fig. 2 is that the lane line in the track, vehicle place 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 determines figure with the relative position relation in track, vehicle place；
Fig. 5 is that the location, track of the embodiment of the present invention determines method.
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
Fig. 1 is the method flow diagram of the embodiment of the present invention, as it is shown in figure 1, the present invention provide based on lane detection and mesh The vehicle assisted location method that mark is followed the tracks of, comprises the following steps:
Step 1: detect lane line and determine this car lane line, video camera being arranged between intelligent vehicle front dead center, shooting Machine horizontally toward identical with direction of traffic.In the video sequence of camera acquisition, road image is divided with vertical axis Become left and right two parts, carry out Image semantic classification respectively, utilize Canny to detect lane line with Hough transform, take and erect near image The left and right sides lane line of direct attack axis is this car lane line.Fig. 2 is the track in the track, vehicle place of the embodiment of the present invention Line determines figure.Go out the area-of-interest at next frame lane line place in conjunction with Kalman filtering preliminary forecasting, detailed process is as follows:
11) road image assuming input video sequence is u × v, image upper part 1/3 is removed, and with u/2 as center line Image is divided into left and right two parts region of interest ROI 1 and ROI2；
12) image is carried out gray processing process and medium filtering denoising, then utilize Canny algorithm to carry out edge inspection Surveying, then the image after processing is carried out Hough transform, fitting a straight line extracts the lane line in image.Take the rightmost side in ROI1 Lane line be this track left-lane line, taking the lane line of the leftmost side in ROI2 is this track right lane line；
13) Kalman prediction is utilized to go out the area-of-interest of this lane line of next frame: as a example by right lane, with (kr, br) represent the slope of lane line straight line and intercept, with (Δ kr, Δ br) represent slope and intercept rate of change, so being defined as follows: State variable is: 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 represents that state-transition matrix, Q represent 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) represents the uncertain region of area-of-interest, and P (n, n-1) represents that the n-1 moment is to n moment uncertain region Predictive value, K (n) represents gain matrix, and H (n) represents observing matrix, after entering tracking, then the range of interest of right lane line:
14) t directly detects lane line in the area-of-interest that t-1 frame draws, if cannot examine in this AOI Measuring lane line, repeat 11) step proceeds by lane detection.
Step 2: the model good by training in advance carries out target vehicle detection, utilizes Kalman filtering algorithm to follow the tracks of vehicle, Utilize Hungary Algorithm (Hungarian Algorithm) to associate the same target of adjacent two frames, specifically include following steps:
21) use in the auto model detection video sequence that DPM algorithm (Deformable Parts Model) is trained Vehicle, obtains vehicle positional information in the picture, and positional information rectangular frame describes；
22) Kalman prediction vehicle location is utilized, state vector V of given target vehicletAs follows:
Vt=[xt yt wt htΔitΔjtψt]T
ψt∈{-1,0,1}
Wherein xt, yt, wt, htIt is target vehicle framework in the plane of delineation, Δ xt, Δ ytRepresent adjacent two frame xt, yt's Rate of change, ψ represents the vehicle position relative to this track；
23) data association uses Hungary Algorithm (Hungarian Algorithm): first with vehicle relative to this car The position in the road vehicle classification to detecting, to the vehicle being in same track respectively with former frame with each car meter in track Calculate Euclidean distance, and using this distance matrix as the input of Hungary Algorithm, realize number according to the matching result of Hungary Algorithm According to association.
24) wherein the process of asking for of confidence level is: assuming that t follows the tracks of number of targets is Nt, the t+1 moment detects number of targets and is Mt+1, and have learned that track, each car place.The each vehicle of adjacent moment in same track is calculated Euclidean distance respectively, it is assumed that have n bar Track, by as a example by n track, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itThe image coordinate of the i-th target in expression this track of t, jt+1In representing this track of t+1 moment The image coordinate of jth target, | | represent Euclidean distance computational methods.
25) one bipartite graph G of definition1(D, T:E), wherein each edge E has the confidence level C of a non-negativeijRepresent detection knot Fruit and the similarity following the tracks of target, represented with Euclidean distance here, solved by Hungary Algorithm (Hungarian Algorithm) Going out Optimum Matching, wherein Hungary Algorithm matching process is as shown in Figure 3.
Step 3: vehicle region is removed from lane detection interest region, redefines lane line region of interest Territory, specifically includes following steps:
31) judge vehicle region in the picture and track area-of-interest lap, calculate vehicle region r1With car Road area-of-interest r2Lap, formula is as follows:
Overlap=r1∩r2；
32) new lane line area-of-interest is r2-overlap。
Step 4: calculate front each vehicle relative to the position relationship in this track labelling, in conjunction with institute's measuring car diatom, determine The track order in track, this car place, specifically includes following steps:
41) relative position relation of front vehicles and this track is calculated, it is assumed that the detection framework of one of them target vehicle For (x, y, w, h), the pixel coordinate in wherein x, the y representational framework upper left corner, w, h represent wide and high.Take a littleWithSetting up linear equation, if straight line intersection on the left of this straight line and lane line, then this vehicle is positioned on the left of this car track, is designated as State-1；If this straight line and lane line do not have phase alternating current, then this vehicle is positioned at this car track, is designated as state 0；If this straight line with Straight line intersection on the right side of lane line, then this vehicle is positioned on the right side of this car track, is designated as state 1, it is judged that process is as shown in Figure 4.
42) present invention set track by turn left from the right side order arrangement, be provided with 4 tracks, then track order from the right side past Part on the left side is not 1 track, 2 tracks, 3 tracks, 4 tracks.Assume all to detect on every track vehicle, take on every track and to lean on most The target vehicle of this car nearly makes a decision, and obtains the status indication of this car, if the status indication collection of these 4 target vehicles is combined into R.If {-1 ,-1 ,-1,0}, then this car is on 1 track R ∈, as shown in Fig. 5 (a).If R is ∈, {-1 ,-1,0,1}, then this car is in 2 cars On road, as shown in Fig. 5 (b).If R is ∈, {-1,0,1,1}, then this car is on 3 tracks, as shown in Fig. 5 (c).If R ∈ 0,1,1, 1}, then this car is on 4 tracks, as shown in Fig. 5 (d).The track of other quantity method in due order is analogized.
Step 5: utilize GPS to determine the travel direction of vehicle place highway and vehicle, in conjunction with concrete lane information and GPS Information, finally realizes the level location, track of vehicle.
Finally illustrate, preferred embodiment above only in order to technical scheme to be described and unrestricted, although logical Cross above preferred embodiment the present invention to be described in detail, it is to be understood by those skilled in the art that can be In form and it is made various change, without departing from claims of the present invention limited range in details.

Claims (4)

1. a vehicle assisted location method based on lane detection Yu target following, it is characterised in that: the method includes following Step:
S1: detect lane line and determine this car lane line, input video sequence, image is carried out pretreatment, utilizes Hough transform Detecting lane line with fitting a straight line, taking the left and right sides lane line near the vertical axis of image is this car lane line, the most in advance Survey the area-of-interest at place, next frame track；
S2: with the good auto model detection vehicle of training in advance, utilize Kalman filtering algorithm to follow the tracks of vehicle, utilize Hungary to calculate Method (Hungarian Algorithm) associates the same target of adjacent two frames；Calculate front vehicles on image with lane line Overlapping region, removes vehicle region from the lane line area-of-interest of preliminary forecasting, redefines next frame lane line Area-of-interest；
S3: calculate the relative position relation of front vehicles and this track, true with the lane line detected in conjunction with relative position relation The lane information of Ding Benche, utilizes GPS alignment system to determine this car positional information on map, is believed with track by positional information Breath merges the realization level location, track to vehicle.
A kind of vehicle assisted location method based on lane detection Yu target following the most according to claim 1, its feature It is: described step S1 specifically includes:
S11: the road image assuming input video sequence is u × v, image upper part 1/3 is removed, and will for center line with u/2 Image is divided into left and right two parts region of interest ROI 1 and ROI2；
S12: image carries out gray processing process and medium filtering denoising, then utilizes Canny algorithm to carry out rim detection, then Image after processing is carried out Hough transform, the lane line in detection image；Taking the lane line of the rightmost side in ROI1 is this track Left-lane line, taking the lane line of the leftmost side in ROI2 is this track right lane line；
S13: using slope, intercept, slope variation rate and the intercept rate of change of lane line as state variable, utilize Kalman to filter Ripple dopes the preliminary area-of-interest of this lane line of next frame.
A kind of vehicle assisted location method based on lane detection Yu target following the most according to claim 2, its feature It is: described step S2 specifically includes:
S21: the auto model using DPM algorithm (Deformable Parts Model) to train detects the vehicle in image；
S22: utilize Kalman prediction vehicle location, state vector V of given target vehicletAs follows
Vt=[xt yt wt ht Δit Δjt ψt]T
ψt∈{-1,0,1}
Wherein xt, ytRepresent the top left co-ordinate of vehicle target framework in the picture, wt, htRepresent width and height, the Δ x of this frameworkt, ΔytRepresent adjacent two frame xt, ytRate of change, ψ represents the vehicle position relative to this track；
S23: data association uses Hungary Algorithm (Hungarian Algorithm): first with vehicle relative to this track The position vehicle classification to detecting, the vehicle being in same track is calculated with each car in track with former frame respectively Euclidean distance, and the confidence level matrix inputted as Hungary Algorithm using this distance matrix, tie according to the coupling of Hungary Algorithm The existing data association of fruit；
S24: wherein the process of asking for of confidence level is: assuming that t follows the tracks of number of targets is Nt, it is M that the t+1 moment detects number of targetst+1, And have learned that track, each car place；The each vehicle of adjacent moment in same track is calculated Euclidean distance respectively, it is assumed that have n bar car Road, by as a example by n track, formula is as follows:
Cij=| it-jt+1| i, j=1,2,3 ...
Wherein itThe image coordinate of the i-th target in expression this track of t, jt+1Represent the jth in this track of t+1 moment The image coordinate of target, | | represent Euclidean distance computational methods；
S25: define a bipartite graph G1(D, T:E), wherein each edge E has the confidence level C of a non-negativeijRepresent testing result with Follow the tracks of the similarity of target, represent with Euclidean distance, solve optimum by Hungary Algorithm (Hungarian Algorithm) Join；
S26: judge vehicle region in the picture and track area-of-interest lap, calculates vehicle region r1Feel with track Interest region r2Lap, formula is as follows:
Overlap=r1∩r2；
S27: new lane line area-of-interest is r2-overlap。
A kind of vehicle assisted location method based on lane detection Yu target following the most according to claim 3, its feature It is: described step S3 specifically includes:
S31: calculate the relative position relation of front vehicles and this track, it is assumed that the detection framework of one of them target vehicle is (x, y, w, h), the pixel coordinate in wherein x, the y representational framework upper left corner, w, h represent wide and high；Take a littleWithSetting up linear equation, if this straight line and left-lane line straight line intersection, then this vehicle is positioned on the left of this car track, is designated as shape State-1；If this straight line does not intersect with lane line, then this vehicle is positioned at this car track, is designated as state 0；If this straight line and right car Diatom straight line intersection, then this vehicle is positioned on the right side of this car track, is designated as state 1；
S32: combine institute's measuring car diatom and the flag state of target vehicle on every track, determine that the track in track, this car place is suitable Sequence, merges track order with GPS positional information on map, finally realizes level location, track.
CN201610486724.0A 2016-06-28 2016-06-28 A kind of vehicle assisted location method based on lane detection and target following Active CN106056100B (en)

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 true CN106056100A (en) 2016-10-26
CN106056100B 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)

Cited By (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529443A (en) * 2016-11-03 2017-03-22 温州大学 Method for improving detection of lane based on Hough transform
CN106652445A (en) * 2016-11-15 2017-05-10 成都通甲优博科技有限责任公司 Road traffic accident judging method 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
CN107562837A (en) * 2017-08-24 2018-01-09 电子科技大学 A kind of maneuvering Target Tracking Algorithm based on road network
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
CN108413971A (en) * 2017-12-29 2018-08-17 驭势科技（北京）有限公司 Vehicle positioning technology based on lane line and application
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
CN108615242A (en) * 2018-05-04 2018-10-02 重庆邮电大学 A kind of highway guardrail tracking
CN108804995A (en) * 2018-03-23 2018-11-13 李春莲 Device distribution Platform of Image Recognition
CN109029438A (en) * 2017-06-12 2018-12-18 广州英卓电子科技有限公司 A kind of vehicle positioning method in finite region
CN109147316A (en) * 2018-07-23 2019-01-04 重庆邮电大学 A kind of city lane car statistics method based on V2X communication and high accuracy positioning
CN109215059A (en) * 2018-10-16 2019-01-15 西安建筑科技大学 Local data's correlating method of moving vehicle tracking in a kind of video of taking photo by plane
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
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
CN109540157A (en) * 2018-11-12 2019-03-29 广东星舆科技有限公司 A kind of onboard navigation system and control method
CN109583418A (en) * 2018-12-13 2019-04-05 武汉光庭信息技术股份有限公司 A kind of lane line deviation automatic correcting method and device based on parallel relation
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
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
CN109858307A (en) * 2017-11-30 2019-06-07 高德软件有限公司 A kind of Lane detection method and apparatus
CN109872341A (en) * 2019-01-14 2019-06-11 中建三局智能技术有限公司 A kind of throwing object in high sky detection method based on computer vision and system
CN109886215A (en) * 2019-02-26 2019-06-14 常熟理工学院 The cruise of low speed garden unmanned vehicle and emergency braking system based on machine vision
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
CN110077399A (en) * 2019-04-09 2019-08-02 魔视智能科技(上海)有限公司 A kind of vehicle collision avoidance method merged based on roadmarking, wheel detection
CN110110029A (en) * 2019-05-17 2019-08-09 百度在线网络技术（北京）有限公司 Method and apparatus for matching lane
CN110458050A (en) * 2019-07-25 2019-11-15 清华大学苏州汽车研究院（吴江） Vehicle based on Vehicular video cuts detection method and device
CN110595490A (en) * 2019-09-24 2019-12-20 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
CN110796102A (en) * 2019-10-31 2020-02-14 重庆长安汽车股份有限公司 Vehicle target sensing system and method
CN110809766A (en) * 2017-06-28 2020-02-18 华为技术有限公司 Advanced driver assistance system and method
WO2020119567A1 (en) * 2018-12-12 2020-06-18 阿里巴巴集团控股有限公司 Data processing method, apparatus, device and machine readable medium
WO2020172842A1 (en) * 2019-02-28 2020-09-03 深圳市商汤科技有限公司 Vehicle intelligent driving control method and apparatus, electronic device and storage medium
CN112289022A (en) * 2020-09-29 2021-01-29 西安电子科技大学 Black smoke vehicle detection judgment and system based on space-time background comparison
CN112441022A (en) * 2019-09-02 2021-03-05 华为技术有限公司 Lane center line determining method and device
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
TWI723679B (en) * 2019-12-13 2021-04-01 宏碁股份有限公司 Lane positioning system and lane positioning method
CN112965503A (en) * 2020-05-15 2021-06-15 东风柳州汽车有限公司 Multi-path camera fusion splicing method, device, equipment and storage medium
CN113128317A (en) * 2020-01-15 2021-07-16 宏碁股份有限公司 Lane positioning system and lane positioning method
CN113792634A (en) * 2021-09-07 2021-12-14 北京易航远智科技有限公司 Target similarity score calculation method and system based on vehicle-mounted camera
CN114212079A (en) * 2022-02-18 2022-03-22 国汽智控(北京)科技有限公司 ACC-based vehicle control method, device and system
CN115033731A (en) * 2022-07-04 2022-09-09 小米汽车科技有限公司 Image retrieval method, image retrieval device, electronic equipment and storage medium
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
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
WO2022257695A1 (en) * 2021-06-09 2022-12-15 腾讯科技（深圳）有限公司 Positioning method and related apparatus

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008645A (en) * 2014-06-12 2014-08-27 湖南大学 Lane line predicating and early warning method suitable for city road
WO2015150256A1 (en) * 2014-04-04 2015-10-08 Delphi Technologies, Inc. Method for lane detection
CN105022397A (en) * 2014-04-25 2015-11-04 谷歌公司 Methods and systems for object detection using multiple sensors

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015150256A1 (en) * 2014-04-04 2015-10-08 Delphi Technologies, Inc. Method for lane detection
CN105022397A (en) * 2014-04-25 2015-11-04 谷歌公司 Methods and systems for object detection using multiple sensors
CN104008645A (en) * 2014-06-12 2014-08-27 湖南大学 Lane line predicating and early warning method suitable for city road

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
CHANG HUANG 等: "Robust Object Tracking by Hierarchical Association of Detection Responses", 《ECCV 2008》 *
ZUWHAN KIM: "Robust Lane Detection and Tracking in Challenging Scenarios", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 *
彭湃 等: "一种适用于城市道路检测及偏离报警的方法", 《电子测量与仪器学报》 *
彭红 等: "基于扩展卡尔曼滤波器的车道线检测算法", 《光电子·激光》 *

Cited By (61)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529443A (en) * 2016-11-03 2017-03-22 温州大学 Method for improving detection of lane based on Hough transform
CN106529443B (en) * 2016-11-03 2019-09-06 温州大学 The method for improving Hough variation detection lane line
CN106652445A (en) * 2016-11-15 2017-05-10 成都通甲优博科技有限责任公司 Road traffic accident judging method and device
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
CN109029438A (en) * 2017-06-12 2018-12-18 广州英卓电子科技有限公司 A kind of vehicle positioning method in finite region
CN110809766B (en) * 2017-06-28 2022-08-09 华为技术有限公司 Advanced driver assistance system and method
CN110809766A (en) * 2017-06-28 2020-02-18 华为技术有限公司 Advanced driver assistance system and method
CN107562837A (en) * 2017-08-24 2018-01-09 电子科技大学 A kind of maneuvering Target Tracking Algorithm based on road network
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
CN108413971A (en) * 2017-12-29 2018-08-17 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
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
CN108804995A (en) * 2018-03-23 2018-11-13 李春莲 Device distribution Platform of Image Recognition
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
CN108615242A (en) * 2018-05-04 2018-10-02 重庆邮电大学 A kind of highway guardrail tracking
CN109147316A (en) * 2018-07-23 2019-01-04 重庆邮电大学 A kind of city lane car statistics method based on V2X communication and high accuracy positioning
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
CN109215059A (en) * 2018-10-16 2019-01-15 西安建筑科技大学 Local data's correlating method of moving vehicle tracking in a kind of video of taking photo by plane
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
CN109540157A (en) * 2018-11-12 2019-03-29 广东星舆科技有限公司 A kind of onboard navigation system and control method
WO2020119567A1 (en) * 2018-12-12 2020-06-18 阿里巴巴集团控股有限公司 Data processing method, apparatus, device and machine readable medium
CN109583418A (en) * 2018-12-13 2019-04-05 武汉光庭信息技术股份有限公司 A kind of lane line deviation automatic correcting method and device based on parallel relation
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
CN109872341A (en) * 2019-01-14 2019-06-11 中建三局智能技术有限公司 A kind of throwing object in high sky detection method based on computer vision and system
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
CN109886215A (en) * 2019-02-26 2019-06-14 常熟理工学院 The cruise of low speed garden unmanned vehicle and emergency braking system based on machine vision
WO2020172842A1 (en) * 2019-02-28 2020-09-03 深圳市商汤科技有限公司 Vehicle intelligent driving control method and apparatus, electronic device and storage medium
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
CN110077399A (en) * 2019-04-09 2019-08-02 魔视智能科技(上海)有限公司 A kind of vehicle collision avoidance method merged based on roadmarking, wheel detection
CN110110029A (en) * 2019-05-17 2019-08-09 百度在线网络技术（北京）有限公司 Method and apparatus for matching lane
CN110458050A (en) * 2019-07-25 2019-11-15 清华大学苏州汽车研究院（吴江） Vehicle based on Vehicular video cuts detection method and device
CN112441022A (en) * 2019-09-02 2021-03-05 华为技术有限公司 Lane center line determining method and device
WO2021042856A1 (en) * 2019-09-02 2021-03-11 华为技术有限公司 Method and device for determining lane centerline
CN110595490A (en) * 2019-09-24 2019-12-20 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
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
CN110796102A (en) * 2019-10-31 2020-02-14 重庆长安汽车股份有限公司 Vehicle target sensing system and method
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
CN113128317A (en) * 2020-01-15 2021-07-16 宏碁股份有限公司 Lane positioning system and lane positioning method
CN112965503B (en) * 2020-05-15 2022-09-16 东风柳州汽车有限公司 Multi-path camera fusion splicing method, device, equipment and storage medium
CN112965503A (en) * 2020-05-15 2021-06-15 东风柳州汽车有限公司 Multi-path camera fusion splicing method, device, equipment 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
CN112289022A (en) * 2020-09-29 2021-01-29 西安电子科技大学 Black smoke vehicle detection judgment 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
WO2022257695A1 (en) * 2021-06-09 2022-12-15 腾讯科技（深圳）有限公司 Positioning method and related apparatus
CN113792634A (en) * 2021-09-07 2021-12-14 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
CN114212079A (en) * 2022-02-18 2022-03-22 国汽智控(北京)科技有限公司 ACC-based vehicle control method, device and system
CN115033731A (en) * 2022-07-04 2022-09-09 小米汽车科技有限公司 Image retrieval method, image retrieval device, electronic equipment and storage medium
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

Also Published As

Publication number Publication date
CN106056100B (en) 2019-03-08

Similar Documents

Publication Publication Date Title
CN106056100B (en) A kind of vehicle assisted location method based on lane detection and target following
CN104166400B (en) Multi-sensor fusion-based visual navigation AGV system
CN107025432B (en) A kind of efficient lane detection tracking and system
CN107031623B (en) A kind of road method for early warning based on vehicle-mounted blind area camera
CN105946853B (en) The system and method for long range automatic parking based on Multi-sensor Fusion
Tao et al. Lane marking aided vehicle localization
CN104008645B (en) One is applicable to the prediction of urban road lane line and method for early warning
CN101929867B (en) Clear path detection using road model
CN106778593A (en) A kind of track level localization method based on the fusion of many surface marks
CN109460709A (en) The method of RTG dysopia analyte detection based on the fusion of RGB and D information
CN106256606A (en) A kind of lane departure warning method based on vehicle-mounted binocular camera
CN103324913A (en) Pedestrian event detection method based on shape features and trajectory analysis
CN104318258A (en) Time domain fuzzy and kalman filter-based lane detection method
CN109490890A (en) A kind of millimetre-wave radar towards intelligent vehicle and monocular camera information fusion method
CN104700414A (en) Rapid distance-measuring method for pedestrian on road ahead on the basis of on-board binocular camera
CN106651953A (en) Vehicle position and gesture estimation method based on traffic sign
CN108230254A (en) A kind of full lane line automatic testing method of the high-speed transit of adaptive scene switching
CN110379168A (en) A kind of vehicular traffic information acquisition method based on Mask R-CNN
CN107389084A (en) Planning driving path planing method and storage medium
CN106156723A (en) A kind of crossing fine positioning method of view-based access control model
CN101944176A (en) Exist the more excellent clear path of means of transportation sign to detect
CN110197173B (en) Road edge detection method based on binocular vision
CN102252859B (en) Road train straight-line running transverse stability automatic identification system
CN103487034A (en) Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target
Shunsuke et al. GNSS/INS/on-board camera integration for vehicle self-localization in urban canyon

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