CN206623754U - Lane detection device - Google Patents

Lane detection device Download PDF

Info

Publication number
CN206623754U
CN206623754U CN201720132215.8U CN201720132215U CN206623754U CN 206623754 U CN206623754 U CN 206623754U CN 201720132215 U CN201720132215 U CN 201720132215U CN 206623754 U CN206623754 U CN 206623754U
Authority
CN
China
Prior art keywords
camera
vehicle
car
mounted terminal
lane
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
Application number
CN201720132215.8U
Other languages
Chinese (zh)
Inventor
周小成
张丹
罗赛
姜岩
彭进展
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.)
Uisee Technologies Beijing Co Ltd
Original Assignee
Uisee Technologies Beijing Co Ltd
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 Uisee Technologies Beijing Co Ltd filed Critical Uisee Technologies Beijing Co Ltd
Priority to CN201720132215.8U priority Critical patent/CN206623754U/en
Application granted granted Critical
Publication of CN206623754U publication Critical patent/CN206623754U/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The utility model discloses a kind of lane detection device, the device includes:Camera, car-mounted terminal and camera controller;Wherein, the camera is installed in the camera controller, and the camera data are connected to the car-mounted terminal, and the image in the range of the present viewing field gathered in real time is sent to the car-mounted terminal by the camera;The car-mounted terminal is coupled with the camera controller, and control signal is sent to the camera controller according to the lane detection result in described image;The camera controller is arranged on vehicle, and the camera controller includes driving part, and the driving part can adjust position and/or the angle of the camera according to control signal dynamic.The utility model adjusts position and/or the angle of camera by dynamic, to cause lane center to be located among camera view, so as to ensure that the accuracy of lane detection and validity.

Description

Lane detection device
Technical field
The utility model belongs to mobile unit technical field, and in particular to a kind of lane detection device.
Background technology
With the development of vehicle technology, Vehicular automatic driving turns into hot research field.Lane line prison based on camera Survey is an important research content in automatic Pilot field, and the warning of lane line center deviation and auxiliary in being driven such as auxiliary are driven Sail/it is unmanned in lane line center keep function etc., all rely on lane detection result.Lane line based on camera The elementary object of detection technique is that the image photographed according to camera detects lane line in real time, obtains car and lane line accordingly Relative position, so as to obtain car whether run-off-road line center, to instruct follow-up planning and control so that vehicle can be kept Travel at lane line center or reasonably evaded.
In the prior art, whether based on the monocular cam still lane detection skill based on binocular depth camera Art, it is required for various to camera progress after camera is fixedly mounted and determines the camera technical parameter such as the angle of pitch, focal length Demarcation, and calibrating parameters corresponding to generation, to pass through the lane line in calibrating parameters also original image during follow-up traveling With the real physical relation of vehicle.
It is this in the prior art to be based on fixing camera but inventor has found during the utility model is realized There are the following problems for the lane detection of position:First, when vehicle is travelling on the road surface for having fluctuating to jolt, due to lane line Corresponding relation between vehicle is changed, and the lane detection based on preset parameter demarcation may export the car of mistake Diatom testing result, although lane detection algorithm and follow-up planning control algorithm can be this by technical finesses such as filtering Situation, but all can not fundamentally solve this problem;Secondly as camera installation site and angle are fixed, camera Limited viewing angle, cause that situation of the lane line in right ahead can only be handled mostly in actual applications, when vehicle curvature compared with When being travelled on big bend, camera will lose detection target, follow lane line central row to sail so as to be unable to guiding vehicle.Make Above-mentioned 2nd problem can be alleviated to a certain extent with wide-angle lens, but the visual field of wide-angle lens is after all limited, and by Big deformation in wide-angle lens be present, can make it that lane detection algorithm is more complicated.
Therefore, how when vehicle is travelled on rough road and the larger road of curvature correct track is detected Line, become for technical problem urgently to be resolved hurrily at present.
Utility model content
The purpose of this utility model is, there is provided a kind of lane detection device, with solve existing fixing camera without Method on the larger road of rough road and curvature detect correct lane line the problem of.
In order to solve the above technical problems, in one side of the present utility model, there is provided a kind of lane detection device, should Device includes:Camera, car-mounted terminal and camera controller;Wherein,
The camera is installed in the camera controller, and the camera data are connected to the car-mounted terminal, Image in the range of the present viewing field gathered in real time is sent to the car-mounted terminal by the camera;
The car-mounted terminal and the camera controller couple, according to the lane detection result in described image to The camera controller sends control signal;
The camera controller is arranged on vehicle, and the camera controller includes driving part, the driving Part can adjust position and/or the angle of the camera according to control signal dynamic.
Alternatively, the camera be arranged on together with the camera controller top of the vehicle, afterbody, it is interior after In at visor and at outside rear-view mirror at least one at.
Alternatively, the camera controller is head.
Alternatively, at least one guide rail is provided with the vehicle, the head is movably disposed at described at least one On individual guide rail.
Alternatively, camera stabilizers are provided with the camera, the camera controller and/or the vehicle Part.
Alternatively, the camera includes the combination of monocular cam, binocular camera or multi-cam.
Alternatively, described device also includes:
Control unit for vehicle, the control unit for vehicle couple with the car-mounted terminal, and the car-mounted terminal is according to institute The lane detection result stated in image sends vehicle performance signal to the control unit for vehicle;The control unit for vehicle bag Car drive is included, the car drive manipulates the state of the vehicle according to the vehicle performance signal dynamics.
Alternatively, described device also includes:
Tip element, the Tip element couple with the car-mounted terminal, receive the prompting letter that the car-mounted terminal is sent Cease to carry out acousto-optic hint.
Alternatively, described device also includes:
Communication unit, the communication unit couples with the car-mounted terminal, and is set on demand with other vehicles, road monitoring At least one of standby, server and mobile terminal establish communication connection.
Alternatively, described device also includes:
Display unit, the display unit couple with the car-mounted terminal, receive the display letter that the car-mounted terminal is sent Cease to show described image and/or auxiliary driving information.
In the technical scheme of the utility model embodiment, using adjustable position and/or the camera of angle, by dynamic State control measures cause lane center target point to be located among camera view, so as to ensure that the accurate of lane detection Property and validity.
Brief description of the drawings
, below will be to embodiment in order to illustrate more clearly of the utility model embodiment or technical scheme of the prior art Or the required accompanying drawing used is briefly described in description of the prior art, it should be apparent that, drawings in the following description are Some embodiments of the utility model, for those of ordinary skill in the art, on the premise of not paying creative work, Other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is structural representation when being installed in the utility model one embodiment built in lane detection device;
Structural representation when Fig. 2 is the external installation in lane detection device part in the utility model one embodiment;
Fig. 3 is the schematic flow sheet of the method for detecting lane lines based on dynamic control in the utility model one embodiment;
Fig. 4 is the modular structure signal of the lane detection device based on dynamic control in the utility model one embodiment Figure;
Fig. 5 is the structural representation of mobile unit in the utility model one embodiment.
Embodiment
It is below in conjunction with the accompanying drawings and specific real to make those skilled in the art more fully understand the technical solution of the utility model Mode is applied to be described in further detail the utility model.
In the prior art, vehicle-mounted camera is usually fixed on target vehicle, and the position of camera and angle are consolidated It is fixed, while the calibrating parameters that lane detection algorithm uses are also based on these fixed installation positions.But which is actual only It is suitable for the situation that vehicle travels on straight road surface, when vehicle is on the road surface for having fluctuating to jolt or in the larger bend of curvature During upper traveling, the corresponding relation between lane line and vehicle can change, or even lane line can disappear from camera view, Now the calibrating parameters based on fixing camera may result in the lane detection result of mistake or even can not enter driveway line Detection.At present, can not effectively be solved the above problems by way of wide-angle camera expands detection zone.
In the technical scheme of the utility model embodiment, using adjustable position and/or the camera of angle, by dynamic State control measures cause lane center target point to be located among camera view, so as to ensure that the accurate of lane detection Property and validity.
Embodiment one:
As shown in Figure 1 and Figure 2, in embodiment of the present utility model, a kind of lane detection device includes:Camera 101st, the (not shown in figure 1) of car-mounted terminal 102 and the (not shown in figure 1) of camera controller 103;Wherein,
The camera 101 is installed in the camera controller 103, and the data of camera 101 are connected to described Image in the range of the present viewing field gathered in real time is sent to the car-mounted terminal by car-mounted terminal 102, the camera 101 102;
The car-mounted terminal 102 couples with the camera controller 103, according to the lane detection in described image As a result control signal is sent to the camera controller 103;
The camera controller 103 is arranged on vehicle 1, and the camera controller 103 includes driving part, institute Position and/or the angle of the camera 101 can be adjusted according to control signal dynamic by stating driving part.
Based on the lane detection device, as shown in figure 3, a kind of disclosed in the utility model embodiment be based on dynamic control Method for detecting lane lines include:
S1, the image in the range of real-time acquisition camera present viewing field;
S2, lane line is identified in described image and detects the center line of the lane line whether in described image Heart district domain;
S3, to lane line or detect that the center line of the lane line is not located at the center of described image unidentified During domain, position and/or the angle of the camera are adjusted according to the result of the identification and/or detection dynamic, so that institute The center line for stating lane line is located at the central area of the camera view scope.
Wherein, the camera in the utility model embodiment is vehicle-mounted camera, and the vehicle-mounted camera can be monocular The combination of camera, binocular camera or more camera, single camera can use conventional camera lens, wide-angle lens, long lens Head or varifocal mirror are first-class, and camera sensing device can be CCD (Charge-coupled Device, charge coupled device) or CMOS Sensors such as (Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductors), camera Type can be polychrome camera (such as RGB color camera) or monochromatic camera (such as black and white camera, infrared camera, R/G/B monochromes camera) etc., this camera concrete form not as the limitation to the utility model embodiment.
Alternatively, the vehicle-mounted camera is arranged on the top of vehicle, afterbody, inside rear-view mirror, at outside rear-view mirror or appoint Anticipate possible installation site, so that the vehicle-mounted camera comprises at least part road conditions within sweep of the eye.This practicality is new Camera in type embodiment can its position of adjust automatically and/or angle, alternatively, pass through drive division that can be programmed Part, such as electro-motor etc. carry out position and/or the angle of camera described in adjust automatically.In one embodiment of the present utility model In, the camera is arranged on head, and the position of the fine-tuning camera of head and/or rotation adjust the shooting The angle of head;Alternatively, the head is movably disposed at least one guide rail, described in mobile on the guide rail Head significantly adjusts the position of the camera.In one embodiment of the present utility model, the camera is taken the photograph for stabilization As head;In another embodiment of the present utility model, the head and/or the guide rail are provided with stabilizer, can keep described Stability of the camera during vehicle travels and/or adjusts, for example damping and/or can keep the dynamic of the camera Balance.In addition, for the camera with zoom capabilities, it can also pass through the adjustment to camera focal length/multiplication factor so that car The center line of diatom is located at the central area of camera view scope.
In Fig. 1 example, camera 101 is binocular camera, and it is installed on the back of the inside rear-view mirror 104 of vehicle 1;Its In, the binocular camera further comprises shadow shield 105 and binocular lattice 106, and the shadow shield 105 is from binocular camera Lower section is extended, and is mainly used in blocking reflection light from below, while provide a base for the visual field of binocular camera Directrix;The binocular lattice 106 is arranged on the centre of two cameras, is mainly used in being formed in the visual field of binocular camera One separated region 106a, calculating is distinguished, identifies and handles to cause binocular image to be more easy to.
In Fig. 2 example, camera 101 and camera controller 103 pass through installed in the top of vehicle 1 and hide setting Connecting line and car body in car-mounted terminal 102 establish connection.Mode shown in Fig. 2 can obtain the bigger visual field and adjustment is empty Between, but equipment life and trafficability may be caused necessarily to influence simultaneously.Only it is used as in the embodiment of the present invention and images above The example of head arrangement, specific camera structure and arrangement are not construed as the limitation that the present invention is embodied.
Alternatively, the lane detection device in the embodiment of the present invention also includes:Control unit for vehicle, the wagon control Unit and the car-mounted terminal couple, the car-mounted terminal according to the lane detection result in described image to the vehicle Control unit sends vehicle performance signal;The control unit for vehicle includes car drive, and the car drive is according to institute State the state that vehicle performance signal dynamics manipulate the vehicle.
Alternatively, described device also includes:Tip element, the Tip element couple with the car-mounted terminal, receive institute Prompt message that car-mounted terminal sends is stated to carry out acousto-optic hint.
Alternatively, described device also includes:Communication unit, the communication unit couple with the car-mounted terminal, and on demand Communicated to connect with the foundation of at least one of other vehicles, road monitoring equipment, server and mobile terminal.
Alternatively, described device also includes:Display unit, the display unit couple with the car-mounted terminal, receive institute Display information that car-mounted terminal sends is stated to show described image and/or auxiliary driving information.
Embodiment two:
In one embodiment of the present utility model, the identification of driveway line and inspection are mainly entered by image procossing mode Survey.Under normal circumstances, the color of lane line, the position of shape and its appearance in the picture are relatively fixed, by being adopted to camera The image of collection, which is handled to separate, identifies most of track line index.Typically, image procossing and image recognition The step of include:Pretreatment, gray proces, rim detection, image segmentation and feature extraction etc., related algorithm and specific implementation are Through maturation, it will not be repeated here, the detailed process of image procossing and image recognition is not construed as to the utility model embodiment Limitation.
It should be noted that in the prior art to simplify lane detection, normally only in ROI (the region of of image Interest, area-of-interest) in be identified and detect.In one embodiment of the present utility model, further to utilize The position of testing result control adjustment camera and/or angle, preferred pair image is integrally identified and detected, especially not In the case of recognizing lane line, emphasis detection further may be carried out to the object of image both sides of the edge.
Wherein, in order to prevent head and/or camera from frequently moving, the steady of head service life and camera detection is influenceed Qualitative, in embodiment of the present utility model, the central area of image/field range is a scope area with one fixed width Domain.Ideally, the center line of lane line is overlapped certainly most useful for wagon control with the center line of image/field range Mode, but this can control to system and bring great pressure, therefore do not Qiang Zhiyaoqiu that two center lines overlap, as long as lane line Center line is located at i.e. acceptable in the certain area of the approximate centerline of image/field range.Therefore in implementation of the present utility model In example, the range threshold of a central area is provided with, in the distance of lane line center line and the center line of image/field range And/or the deviation of angle in the range threshold when, that is, think that the center line of lane line is located at the center of image/field range Domain, now without carrying out or can terminate the adjustment to camera position and/or angle;Only when lane line center line and image/ When the distance of the center line of field range or the deviation of angle exceed the range threshold, just start to perform the adjustment behaviour of camera Make.
Embodiment three:
It is described to be adjusted according to the result of the identification and/or detection dynamic in one embodiment of the present utility model The position of the whole camera and/or angle include a variety of decision making approach and adjustable strategies.
Typically, when recognizing lane line in the picture, but detect that the center line of the lane line is not located at the figure During the central area of picture, according to the adjustment corresponding to the deviation situation of the center line of described image of the center line of the lane line Camera.Such as when the deviation and/or first for having the first displacement between the center line and the center line of image for detecting lane line During the deviation of angle, second displacement is moved in the position that camera is adjusted to the opposite direction of the first offset deviation, and/or to first The angle rotation second angle of the opposite direction adjustment camera of angular deviation.Wherein, the first displacement is corresponding with second displacement The corresponding relation of relation, first angle and second angle is calculated according to camera parameter and calibrating parameters etc..
And when not recognizing lane line in the picture, then need persistently to search in the adjustable range of camera, directly Camera present viewing field scope is appeared in the lane line consistent or consistent with vehicle heading with headstock direction Interior (being confirmed by collection image recognition), then further according to the center line of lane line and the deviation situation of the center line of image is corresponding adjusts Whole camera (adjustment mode i.e. described above).Alternatively, way of search includes:
From current location, adjustment camera scans for;
Or by camera rotate to it is consistent or consistent with vehicle heading with headstock direction after, then adjust Whole camera scans for;
Or according to first Lane detection situation, camera is adjusted since the position and direction of track heading line off Scan for;
Or the track line position predicted according to electronic map scans for adjust camera.
Override is answered to search for improve efficiency, reliability and security, the position that lane line most possibly be present;But simultaneously The adjustment for being considered as camera is to rely on mechanical part, excessively should not be acted frequently and significantly, search procedure should try one's best guarantor Hold brief and smooth.Therefore, in embodiment of the present utility model, preferably the first of driveway line is entered by rotating horizontally camera Step search;Further, according to vehicle-state, first Lane detection situation, onboard sensor and/or electronic map etc. come Determine direction of rotation (being clockwise or counterclockwise).For example during vehicle right-hand bend, preferentially rotate (i.e. clockwise) to search to the right Rope;Or its straight line when travelling, the rightmost side that is in first field-of-view image before the heading line off of track, then it is preferential to the right (i.e. Rotate clockwise) to search for;Or (include but is not limited to first lane line during its straight line traveling, according to certain means The information such as positioning, electronic map or other sensors after identification) determine that vehicle is in leftmost side track, then it is preferential to the right (i.e. Rotate clockwise) to search for.The privileged direction of rotating camera can also be according to more information come comprehensive descision and decision-making, herein No longer enumerate, relevant technical staff in the field should be appreciated that the specific determination means of direction of rotation are not construed as to this reality With the limitation of new embodiment.
In addition, relevant technical staff in the field is appreciated that horizontal rotation search is simply more easily searched in theory Mode, in certain extreme cases, for example road big rise and fall, car accident, lane line are blocked or lane line interrupts etc., It can be scanned for by the way of Omnidirectional rotation and/or dollying head, specific way of search is not construed as to this herein The limitation of utility model embodiment.
Example IV:
Generally, the image of vehicle-mounted camera shooting typically understands some deformations, most typically, subject (such as lane line) The problem of near big and far smaller is had, if the deformation using wide-angle lens then objects in images can be more serious, thus it is simple according to taking the photograph As head gather image directly carry out judge and decision-making may some deviations, can not exactly for automatic Pilot or auxiliary drive Offer control signal is provided, certain safety problem can be triggered on the contrary.
In one embodiment of the present utility model, first to camera collection image corrected and handled after be used further to The decision-making that the detection of lane line and automatic Pilot/auxiliary drive, to provide more accurate, safe and reliable vehicle control signal.Tool Body, in the embodiment of the present utility model, after being corrected to the image of camera collection again in described image identification and/ Or detection lane line.Typically, the correction is the correction to trapezoidal subject image, i.e., the subject image being taken in echelon Corrected by the stretching to both ends and/or contraction as rectangle object image.Further, the figure gathered for wide-angle lens Picture, after the correction for first carrying out wide-angle distortion, then carry out correction of the trapezoidal subject image to rectangle object image.Due to different shootings Deformation caused by head and camera lens is not quite similar, and specific correction mode is not construed as to the utility model embodiment herein Limitation.
In one embodiment of the present utility model, although the image after correction can be effective for the knowledge of lane line Not with detection, but in order to be more accurately controlled to vehicle, further, also handled by orthographic projection by the related letter of vehicle Breath, which all switches to, carries out comprehensive analysis and decision-making in same orthographic projection plane.Typically, after according to shooting and/or correction Image (can also combine other sensors gathered data and electronic map etc.) is changed, by vehicle, camera and subject Deng being transformed into orthographic projection plane (top view i.e. viewed from above), then judge that vehicle travels shape in orthographic projection plane State, camera posture and relation of vehicle/camera and object (distance, angle etc.) etc., so as to decide whether Adjust and specifically how to control vehicle-state and/or camera posture.
In embodiment of the present utility model, by being corrected to the image that camera is shot, eliminate in image Deformation so that Lane detection and the result of detection are more accurately and reliably.In addition, pass through orthographic projection conversion process so that vehicle Relation with lane line make it that follow-up decision is more accurate effective closer to actual real conditions.
In embodiment of the present utility model, orthographic projection conversion and follow-up control decision need accurate data message Support, data message includes but is not limited to speed, the offset of travel direction, camera relative initial position/angle, camera Highly, track line position, lane line direction and lane line curvature etc., further can also with recognize object, other biography Sensor and/or the information data of other vehicles collection combine, such as road sign, milestone, Obstacle Position, GPS location, vehicle-mounted thunder Up to this truck position etc. in data, the rear car visual field., can be exactly in orthographic projection plane by the combinatorial operation of these data messages In obtain current time vehicle position in the road, camera direction, camera position, lane line position in the road and Other object situations etc. in road, the image so as to be gathered according to camera accurately control vehicle come reasonable and carried out It is necessary motor-driven, realize that the reliable automatic Pilot of highly effective and safe/auxiliary drives.
Wherein, to make calculating fast accurate, the same data message of vehicle and camera can use detection demarcation in advance Mode is set.Specifically, in whole system initial start, that is, before camera carries out IMAQ, will first take the photograph As head is adjusted to the initial position of acquiescence, checked in advance by more complete facility and means and measurement obtain each item data, As the related calibrating parameters of camera, then in the course of the work, real-time calling calibrating parameters participate in calculating and/or school Just, to ensure data accuracy.
Embodiment five:
Because lane detection is that automatic Pilot/auxiliary drives one of most basic technological means, therefore in the utility model Embodiment in, primary and foremost purpose be by lane line as far as possible be maintained at camera view center, with ensure can carry out it is maximally effective Lane detection.Secondly, then it is the result according to lane detection, judges whether the state of vehicle and position are normal, carries out It is necessary to remind and/or control to ensure driving safety.Again, then it is to be closed according to road conditions, vehicle-state and position The decision-making and planning of reason so that vehicle can be travelled persistently under various road conditions in a manner of optimum automatically, realize real nothing Need the unmanned of manual intervention.
Wherein, it is contemplated that the adjustment of camera is mainly based upon mechanical component, from IMAQ to lane detection, again to Control decision, finally arrive startup adjustment or even be adjusted in place certain time delay, to avoid camera from can not when being adjusted in place Newest road conditions are adapted to, such as when vehicle is quickly through inner curve, it is likely that camera is not adjusted in place vehicle also just again Enter to come off into the straightaway;Or to avoid excessively continually adjusting camera, such as when the continuous fluctuating of road presence or inner curve, this reality With in new embodiment also by optimizing the adjustment of camera to the prediction of road conditions and vehicle condition.
In embodiment of the present utility model, included by the prediction to road conditions and vehicle condition to optimize the adjustment of camera:
According to current vehicle condition (include but is not limited to speed and travel direction etc.) and present road situation (including but not It is limited to track line position, direction and curvature etc.), predict motion rail of the vehicle in the road in following a period of time Mark;
According to when preceding camera state (include but is not limited to position, angle etc.) and the movement locus, predicting not Come position and duration that a period of time inside lane line deviates the camera view central area;
Deviate the position of the camera view central area according to the lane line, predict and be adjusted to the camera The time that position needs;
According to the duration and the time for being adjusted in place needs, judge to reach the lane line in the vehicle When deviateing the position of the camera view central area, if need to adjust camera.
Further, can be analysed in depth above by prediction come the method optimized and revised by the way of iteration, that is,:If Judge that the situation of the camera, the vehicle and/or the road is changed during above-mentioned prediction, then will change Situation information afterwards substitutes into above-mentioned prediction, to obtain new information of forecasting.
Optionally, in addition, when predicting multiple adjacent locations and may occur repeatedly to adjust, in the range threshold of adjustment It is interior, it is preferential to be carried out by the way of make it that the total adjustment amount repeatedly adjusted is minimum.Still optionally further, can be by suitably putting The wide range threshold reduces total adjustment amount.
Wherein, the present road situation, can also be further in addition to the image gathered according to the camera is identified According to electronic map, GIS (Geographic Information System, GIS-Geographic Information System) information, other sensors, The information of the offer such as other vehicles and/or artificial experience (includes but is not limited to Lane Narrows, track is widened, lane line changes, limits Fast information, information of overtaking other vehicles, indicator lamp information, congestion control information, accident information, mark information etc.) carry out comprehensive analysis, so as to come Prediction obtains more accurate vehicle movement track.
By look-ahead, the adjustment that embodiment of the present utility model can be to camera is effectively optimized, so as to The efficiency and reliability of camera adjustment is ensure that, avoids influence of the time delay to system reliability of adjustment.Meanwhile this practicality New embodiment can also be by reducing invalid adjustment and reducing frequently adjustment come the life-span of prolonged mechanical component.
Embodiment six:
Based on above-described embodiment, as shown in fig.4, in one implementation of the utility model. with the above method correspondingly In example, a kind of lane detection device based on dynamic control is also provided, including:
Image capture module 10, for the image in the range of real-time acquisition camera present viewing field;
Lane detection module 11, it is for identifying lane line in described image and detecting the center line of the lane line It is no positioned at the central area of described image;
Camera control module 12, for lane line or detecting the center line of the lane line not position unidentified When the central area of described image, the position of the camera is adjusted according to the result of the identification and/or detection dynamic Put and/or angle, so that the center line of the lane line is located at the central area of the camera view scope.
Alternatively, described device also includes:
Search module, for when not recognizing lane line in described image, in the adjustable range of the camera Interior lasting search, it is consistent with headstock direction until being recognized in the image gathered in the range of the camera present viewing field Or the lane line consistent with vehicle heading.
Alternatively, the camera control module includes:
Deviation control module, lane line is recognized in described image for working as, but detect the center of the lane line When line is not located at the central area of described image, according to the deviation feelings of the center line of the lane line and the center line of described image Condition accordingly adjusts the camera.
Alternatively, the deviation control module includes:
Separate-blas estimation module, for detecting first between the center line of the lane line and the center line of described image Deviation and/or first angle deviation are moved,
Position adjusting type modules, the position for adjusting the camera to the opposite direction of first offset deviation are moved Second displacement,
And/or
Angle adjustment module, the angle for adjusting the camera to the opposite direction of the first angle deviation rotate Second angle.
Alternatively, the search module includes:
Instant search module, scanned for for adjusting the camera from current location;
Or search module in the same direction, for the camera to be rotated into or and vehicle consistent with headstock direction After travel direction is consistent, then adjusts the camera and scan for;
Or disappearance position search module, for according to first Lane detection situation, from the position of track heading line off and Direction, which starts to adjust the camera, to be scanned for;
Or forecasting search module, the camera is adjusted for the track line position predicted according to electronic map and is entered Row search.
Alternatively, in the search module, the adjustment camera is scanned for as horizontal suitable/rotate counterclockwise institute Camera is stated to scan for.
Alternatively, described device also includes:
Image flame detection module, after the described image for being gathered to the camera is corrected, then in described image Identification and/or detection lane line.
Alternatively, described device also includes:
Abnormal judge module, for the result according to the identification and/or the detection, judge state and the position of vehicle It is whether normal;
Vehicle control module, for when judging to occur abnormal, sending prompting message and/or sending control signal manipulation The state of the vehicle.
Alternatively, described device also includes:
Orthographic projection processing module, for being changed according to described image, institute is carried out in orthographic projection plane after conversion State the decision-making judged with the control signal.
Alternatively, described device also includes:
Aid in adjusting module, for by the prediction to road conditions and vehicle condition, come aid in carrying out the position of the camera and/ Or the dynamic adjustment of angle.
Alternatively, the auxiliary adjusting module includes:
Trajectory prediction module, for according to current vehicle condition and present road situation, predicting institute in following a period of time State movement locus of the vehicle in the road;
Deviate prediction module, work as preceding camera state and the movement locus for basis, when predicting described following one section Between inside lane line deviate position and the duration of the camera view central area;
Time-consuming prediction module, for deviateing the position of the camera view central area, prediction according to the lane line The camera is adjusted in place to the time of needs;
Decision-making module is adjusted, for according to the duration and the time for being adjusted in place needs, judging described When vehicle reaches the position of the lane line deviation camera view central area, if need to adjust camera.
Alternatively, described device also includes:
Module is optimized and revised, for when predicting multiple adjacent locations and may occur repeatedly to adjust, in the camera It is preferential to be adjusted by the way of make it that the total adjustment amount repeatedly adjusted is minimum in the range threshold of adjustment.
Embodiment seven:
In one of the present utility model is implemented, a kind of nonvolatile computer storage media, the calculating are additionally provided Machine storage medium is stored with computer executable instructions, and the computer executable instructions can perform in above-mentioned any means embodiment Described method.
Or in one of the present utility model is implemented, additionally provide a kind of computer program product, the computer Product includes computer executable instructions, and the computer executable instructions can perform described in above-mentioned any means embodiment Method.
Embodiment eight:
In one embodiment of the present utility model, for performing the above-mentioned method for detecting lane lines based on dynamic control A kind of hardware configuration of mobile unit is as shown in figure 5, the mobile unit includes:
Camera 530, head 540, one or more processors 510 and memory 520, with a processor in Fig. 5 Exemplified by 510.
Memory 520 is used as a kind of non-volatile computer readable storage medium storing program for executing, available for storage non-volatile software journey Sequence, non-volatile computer executable program and module, as in the utility model previous embodiment based on dynamic control Programmed instruction/module corresponding to method for detecting lane lines.Processor 510 is stored in non-easy in memory 520 by operation The property lost software program, instruction and module, various function application and data processing so as to execute server.
Memory 520 can include storing program area and storage data field, wherein, storing program area can store operation system Application program required for system, at least one function;Storage data field can store the use according to the device based on double card online Data created etc..In addition, memory 520 can include high-speed random access memory, non-volatile deposit can also be included Reservoir, for example, at least a disk memory, flush memory device or other non-volatile solid state memory parts.In some implementations In example, memory 520 is optional including that can pass through relative to the remotely located memory of processor 510, these remote memories Network connection is to the mobile unit.The example of above-mentioned network includes but is not limited to internet, intranet, LAN, movement Communication network and combinations thereof.
Camera 530 is arranged on the head 540, and the camera 530 is used to gather in the range of present viewing field in real time Image.The camera 530 communicates to connect with the memory 520 and one or more of processors 510, the communication link Connecing can be connected by bus, radio communication or other modes, in Fig. 5 exemplified by being connected by bus.
The head 540 couples with one or more of processors, and the signal adjusted according to the dynamic drives adjustment The position of the camera and/or angle.
One or more functional module is stored in the memory 520, when by one or more of processors During 510 execution, the method for detecting lane lines based on dynamic control in above-mentioned any means embodiment is performed.
The said goods can perform the method that the utility model embodiment is provided, and possess the corresponding functional module of execution method And beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to the side that the utility model embodiment is provided Method.
The mobile unit of the utility model embodiment is preferably realized with vehicle-mounted control device, but is integrated in vehicle centre console Vehicle-mounted control device is not unique form of implementation of the utility model embodiment.Substantially, the electronics relatively independent with vehicle is set It is standby to may be equally applied to embodiment of the present utility model, if its can carry out with vehicle control system it is appropriate interact (including but It is not limited to receive prompting message, receives vehicle control signal etc.).Therefore the mobile unit of the utility model embodiment can be with Exist in a variety of forms, include but is not limited to:
(1) general-purpose computations terminal:The common apparatus of basic computer process ability is provided, processor is generally included and deposits Reservoir, corresponding function is completed by reading and running computer instruction and is performed.This Terminal Type includes:Personal computer, list Piece machine, embedded device, and it is various for industry, business or civilian small/micro computer etc..
(2) server:The equipment for providing the service of calculating, the composition of server are total including processor, hard disk, internal memory, system Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, therefore in processing energy Power, stability, reliability, security, scalability, manageability etc. require higher.
(3) mobile communication equipment:The characteristics of this kind equipment is that possess mobile communication function, and to provide speech, data Communicate as main target.This Terminal Type includes:Smart mobile phone (such as iPhone), multimedia handset, feature mobile phone, and it is low Hold mobile phone etc..
(4) super mobile personal computer equipment:This kind equipment belongs to the category of personal computer, there is calculating and processing work( Can, typically also possess mobile Internet access characteristic.This Terminal Type includes:PDA, MID and UMPC equipment etc., such as iPad.
(5) portable entertainment device:This kind equipment can show and play content of multimedia.The kind equipment includes:Audio, Video player (such as iPod), handheld device, e-book, and intelligent toy and portable car-mounted navigation equipment.
(6) other electronic installations with data interaction function.
In summary, in the technical scheme of the utility model embodiment, using the shooting of adjustable position and/or angle Head, it is located at by dynamic regulation means come lane center target point among camera view, so as to ensure that lane line The accuracy and validity of detection.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs In some or all of module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying creativeness Work in the case of, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation Method described in some parts of example or embodiment.
Finally it should be noted that:Above example is only to illustrate the technical solution of the utility model, rather than its limitations; Although the utility model is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that: It can still modify to the technical scheme described in foregoing embodiments, or which part technical characteristic is carried out etc. With replacement;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the utility model technology The spirit and scope of scheme.

Claims (10)

1. a kind of lane detection device, it is characterised in that the device includes:Camera, car-mounted terminal and camera controller; Wherein,
The camera is installed in the camera controller, and the camera data are connected to the car-mounted terminal, described Image in the range of the present viewing field gathered in real time is sent to the car-mounted terminal by camera;
The car-mounted terminal and the camera controller couple, according to the lane detection result in described image to described Camera controller sends control signal;
The camera controller is arranged on vehicle, and the camera controller includes driving part, the driving part Position and/or the angle of the camera can be adjusted according to control signal dynamic.
2. device according to claim 1, it is characterised in that the camera is set together with the camera controller In at the top of the vehicle, afterbody, inside rear-view mirror and at outside rear-view mirror at least one at.
3. device according to claim 1, it is characterised in that the camera controller is head.
4. device according to claim 3, it is characterised in that at least one guide rail, the cloud are provided with the vehicle Platform is movably disposed at least one guide rail.
5. device according to claim 1, it is characterised in that the camera, the camera controller and/or described The stable part of camera is provided with vehicle.
6. device according to claim 1, it is characterised in that the camera includes monocular cam, binocular camera Or the combination of multi-cam.
7. device according to claim 1, it is characterised in that described device also includes:
Control unit for vehicle, the control unit for vehicle couple with the car-mounted terminal, and the car-mounted terminal is according to the figure Lane detection result as in sends vehicle performance signal to the control unit for vehicle;The control unit for vehicle includes car Driver, the car drive manipulate the state of the vehicle according to the vehicle performance signal dynamics.
8. device according to claim 1, it is characterised in that described device also includes:
Tip element, the Tip element and the car-mounted terminal couple, receive prompt message that the car-mounted terminal sends with Carry out acousto-optic hint.
9. device according to claim 1, it is characterised in that described device also includes:
Communication unit, the communication unit and the car-mounted terminal couple, and on demand with other vehicles, road monitoring equipment, clothes Business at least one of device and mobile terminal establish communication connection.
10. device according to claim 1, it is characterised in that described device also includes:
Display unit, the display unit and the car-mounted terminal couple, receive display information that the car-mounted terminal sends with Show described image and/or auxiliary driving information.
CN201720132215.8U 2017-02-14 2017-02-14 Lane detection device Active CN206623754U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201720132215.8U CN206623754U (en) 2017-02-14 2017-02-14 Lane detection device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201720132215.8U CN206623754U (en) 2017-02-14 2017-02-14 Lane detection device

Publications (1)

Publication Number Publication Date
CN206623754U true CN206623754U (en) 2017-11-10

Family

ID=60213855

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201720132215.8U Active CN206623754U (en) 2017-02-14 2017-02-14 Lane detection device

Country Status (1)

Country Link
CN (1) CN206623754U (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109191536A (en) * 2018-10-31 2019-01-11 百度在线网络技术(北京)有限公司 The automatic calibration method and device of vehicle-mounted camera
CN109373974A (en) * 2018-02-07 2019-02-22 徐州艾特卡电子科技有限公司 A kind of autonomous driving vehicle context aware systems having active probe function
CN110146094A (en) * 2019-06-27 2019-08-20 成都圭目机器人有限公司 Robot localization navigation system and its implementation based on lane line
CN110196062A (en) * 2019-06-27 2019-09-03 成都圭目机器人有限公司 A kind of air navigation aid of one camera tracking lane line
CN110677583A (en) * 2019-09-29 2020-01-10 深圳市大拿科技有限公司 Vehicle-mounted image acquisition method and device, electronic equipment and computer storage medium
CN112235488A (en) * 2020-06-08 2021-01-15 威盛电子股份有限公司 Automatic correction method for vehicle-mounted lens and vehicle-mounted lens device
CN112238818A (en) * 2019-10-14 2021-01-19 北京新能源汽车技术创新中心有限公司 Control system, data processing method, and control method
CN114667729A (en) * 2020-01-08 2022-06-24 核心光电有限公司 Porous zoom digital camera and use method thereof

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109373974A (en) * 2018-02-07 2019-02-22 徐州艾特卡电子科技有限公司 A kind of autonomous driving vehicle context aware systems having active probe function
CN109191536A (en) * 2018-10-31 2019-01-11 百度在线网络技术(北京)有限公司 The automatic calibration method and device of vehicle-mounted camera
CN110146094A (en) * 2019-06-27 2019-08-20 成都圭目机器人有限公司 Robot localization navigation system and its implementation based on lane line
CN110196062A (en) * 2019-06-27 2019-09-03 成都圭目机器人有限公司 A kind of air navigation aid of one camera tracking lane line
CN110196062B (en) * 2019-06-27 2022-03-25 成都圭目机器人有限公司 Navigation method for tracking lane line by single camera
CN110677583A (en) * 2019-09-29 2020-01-10 深圳市大拿科技有限公司 Vehicle-mounted image acquisition method and device, electronic equipment and computer storage medium
CN112238818A (en) * 2019-10-14 2021-01-19 北京新能源汽车技术创新中心有限公司 Control system, data processing method, and control method
CN114667729A (en) * 2020-01-08 2022-06-24 核心光电有限公司 Porous zoom digital camera and use method thereof
CN114667729B (en) * 2020-01-08 2024-04-19 核心光电有限公司 Multi-hole zoom digital camera and using method thereof
CN112235488A (en) * 2020-06-08 2021-01-15 威盛电子股份有限公司 Automatic correction method for vehicle-mounted lens and vehicle-mounted lens device
TWI778368B (en) * 2020-06-08 2022-09-21 威盛電子股份有限公司 Automatic correction method of vehicle lens and vehicle lens device
US11580668B2 (en) 2020-06-08 2023-02-14 Via Technologies, Inc. Automatic correction method for onboard camera and onboard camera device

Similar Documents

Publication Publication Date Title
CN106740841B (en) Method for detecting lane lines, device and mobile unit based on dynamic control
CN206623754U (en) Lane detection device
US10513269B2 (en) Road profile along a predicted path
CN109733384B (en) Parking path setting method and system
CN109416257B (en) System and method for detecting traveling road of host vehicle, system for navigating host vehicle, and computer-readable medium
CN106981082B (en) Vehicle-mounted camera calibration method and device and vehicle-mounted equipment
CN109116846B (en) Automatic driving method, device, computer equipment and storage medium
US20150355641A1 (en) Lane changing apparatus and method of autonomous vehicle
US20200250984A1 (en) Pothole detection system
CN108107897B (en) Real-time sensor control method and device
JP7077910B2 (en) Bound line detection device and lane marking method
US20180107884A1 (en) Road marking recognition device
CN111028534A (en) Parking space detection method and device
CN114495568A (en) Parking method, parking equipment, storage medium and parking system
KR102275083B1 (en) Robotic systems and a returning method of robot for automatic charging
CN109297502A (en) Laser projection pointing method and device based on image procossing Yu GPS navigation technology
CN108363387B (en) Sensor control method and device
KR20230044785A (en) SYSTEM FOR ENFORCEMENT OF unauthorized PARKED VEHICLE BASED ON AUTONOMOUS DRIVING
CN109285202A (en) Vehicle track method and system for planning
CN115050203B (en) Map generation device and vehicle position recognition device
CN106155059A (en) The Intelligent unattended control loop of view-based access control model
US20240017748A1 (en) Device, method, and computer program for lane determination
CN116118782A (en) Vehicle-mounted unmanned aerial vehicle driving recording system, path planning method and computer equipment
JP7027749B2 (en) Landmark detection method and landmark detection device
CN116793373A (en) Parking lot vehicle positioning method and system

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant