CN108068817A - A kind of automatic lane change device and method of pilotless automobile - Google Patents
A kind of automatic lane change device and method of pilotless automobile Download PDFInfo
- Publication number
- CN108068817A CN108068817A CN201711272791.3A CN201711272791A CN108068817A CN 108068817 A CN108068817 A CN 108068817A CN 201711272791 A CN201711272791 A CN 201711272791A CN 108068817 A CN108068817 A CN 108068817A
- Authority
- CN
- China
- Prior art keywords
- image
- lane change
- information
- pilotless automobile
- central processing
- 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.)
- Pending
Links
- 230000008859 change Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 230000004888 barrier function Effects 0.000 claims description 7
- 238000005452 bending Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 210000000988 bone and bone Anatomy 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- 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
- G06V10/443—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 by matching or filtering
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of automatic lane change device and methods of pilotless automobile, including image acquisition device, image processor, central processing unit module and control execution system, road mark line on described image collector acquisition road surface, gathered data of the described image processor with image acquisition device data connection and for receiving image acquisition device, and the image information of image acquisition device is identified, and tell the function of markings, the central processing unit module sends decision instruction after carrying out comprehensive analysis processing to the signal that image processor transmits out with image processor data connection and according to pre-set program, and decision instruction is transferred to control execution system, whether controlling automobile lane change.The automatic lane change device and method of pilotless automobile is not on the premise of depending on driver and completing automatic lane change, initiative recognition Road, flexibly tackles different kinds of roads situation, and practicability is high.
Description
Technical field:
The present invention relates to a kind of automatic lane change device and methods of pilotless automobile, are related to unmanned technical field.
Background technology:
With popularization of the automobile in the whole world, a large amount of automobiles are necessarily required to substantial amounts of driver, in order to avoid the wave of human resources
Take, pilotless automobile rapidly develops, and there are mainly two types of automatic lane change methods for pilotless automobile at present:One kind be driver to
One lane change instruction of automobile, then completes lane change by automobile, and this method still relies on the judgement of driver, instruction, Wu Fashi
Now really unmanned, another kind is that automobile is travelled according to set traffic route, relies on navigation system and realizes on road
Lane change, since situation is complicated under natural conditions, and system real time requirement is also very high, so the real-time identification of traffic lines is aiding in
Effect is not highly desirable in navigation, still has many that cannot solve the problems, such as.
The content of the invention:
The technical problems to be solved by the invention are:A kind of initiative recognition Road is provided, flexibly tackles different kinds of roads situation
The automatic lane change device and method of pilotless automobile.
In order to solve the above-mentioned technical problem, the present invention is achieved by the following technical solutions:
A kind of pilotless automobile becomes duct device automatically, including image acquisition device, image processor, central processing unit module and
Execution system is controlled, described image collector gathers the road mark line on road surface, described image processor and image acquisition device
Data connection and the gathered data for receiving image acquisition device, and the image information of image acquisition device is identified, and point
The function of markings is discerned, the central processing unit module is with image processor data connection and according to pre-set program pair
The signal that image processor transmits out sends decision instruction after carrying out comprehensive analysis processing, and decision instruction is transferred to control and is held
Row system, whether controlling automobile lane change.
Preferably, described image collector is arranged to high-speed area array camera.
Preferably, the central processing unit module is arranged to vehicle-mounted ECD.
Preferably, navigation system is further included, and the navigation system and central processing unit module data connection, the navigation
System plans driving scheme according to the destination of input for automobile, and according to the information real-time update database collected.
Preferably, the navigation system includes cloud database, car-mounted terminal and the module of ground GPS base station three,
In, car-mounted terminal carries out information exchange with cloud database, ground GPS base station by the way of wireless telecommunications respectively.
Preferably, context aware systems are further included, the context aware systems and central processing unit module data connection,
The context aware systems include camera and millimetre-wave radar, for gather the relative distance of surrounding vehicles, relative velocity and
Barrier situation, and the information collected is transferred to central processing unit module.
Preferably, the control execution system includes brake monitor, steering controller, turns to lamp controller and throttle
Controller, the control perform the decision instruction that system is transmitted according to central processing unit module, pass through brake monitor, steering respectively
Controller turns to lamp controller and throttle control to change the speed of this vehicle and steering angle, completes lane change action.
Preferably, further include with central processing unit module loud speaker, the decision instruction of central processing unit module is passed through
Voice signal feeds back to occupant.
A kind of automatic lane change method of pilotless automobile, comprises the following steps,
Step 1 gathers road information by high-speed area array camera, the information collected is transmitted to image processor;
Step 2 will handle the image information received by image processor and carry out identifying processing, after identification is post-processed
Information is transmitted to vehicle-mounted ECU;
Step 3 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change;
Step 4 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change.
Preferably, the image-recognizing method in the step 2 includes, image is pre-processed, to the image of acquisition
Gray processing is carried out, and carries out appropriate Morphological scale-space.Based on image detection traffic marking, carried out using shape and marginal information
Quick detection.It is then based on style characteristic to extract, and necessary correction once is carried out to the image of deformation.Finally, pass through
Using distance estimating as similarity, the identification to image is completed, wherein, it concretely comprises the following steps:
Step 1, colored original image is converted into gray level image, the method for expressing of gray level image is by each picture of image
The brightness value of vegetarian refreshments carries out quantification treatment, and the brightness range of each pixel is usually divided between 0-255 totally 256 gray scales
Rank, 0 to represent the point completely black, and 255 represent that the point is entirely white, and principle is using the palette of 256 colors, the value of each single item RGB
It is identical, tonal range 0-255, gray value is formulated as:
Energy effective expression and the picture content of description region shape in figure are extracted with the method for mathematical morphology, such as border, bone
Frame and convex hull etc., after pretreatment, it is also necessary to which carrying out some includes expansion, burn into opening operation and closed operation processing;
Step 2, for the binaryzation of image by the way that the pixel with same alike result is classified as a region, being classified as different attribute is another
One region, when according to a certain attribute carry out image region segmentation when seek to set corresponding threshold value, if G=0,1 ...,
L-1 } be image intensity value set, L representative image grey levels, setting gray value B={ b0, b1 } is two of threshold value T ∈ G
Gray value and b0, b1 ∈ G carry out binaryzation to image f (x, y) using T as threshold value, obtain only 0 and 255 two gray level
Other image fT(x, y), expression are as follows:
The selection of threshold value herein utilizes minimum error method, and edge detection can be completed by the convolution of differential operator, calculated with derivative
The value that the region that son acts on image grey scale change can be made larger is drawn is higher, therefore, corresponding fringe region is set thresholding,
So as to extract the pixel at edge, edge extracting is carried out used here as Canny operators, the feature extraction of roadmarking utilizes throwing
Shadow, geometrical property, Fourier descriptors, chain code feature statement roadmarking contour shape, comprehensive utilization Hu not bending moment and
Bending moment does not identify target to Zernike as characteristic value.
Step 3, the identification of roadmarking utilizes Euclidean distance metrics exemplary feature and the phase of images to be recognized feature
Like property, the feature vector of roadmarking to be identified and the mark sheet of sample storehouse Plays are compared one by one, work as sample storehouse
In a certain traffic marking characteristic value and reticle image to be identified when matching, then it is the standard traffic mark to judge identified image
Line, and corresponding function signal is exported, conversely, identified image is not roadmarking.
Compared with prior art, usefulness of the present invention is:The automatic lane change device and method of pilotless automobile
On the premise of not depending on driver and completing automatic lane change, initiative recognition Road flexibly tackles different kinds of roads situation, thus has
There are higher practicability and economic benefit, be suitble to promote and apply.
Description of the drawings:
The present invention is further described below in conjunction with the accompanying drawings:
Fig. 1 show the functional-block diagram of the automatic lane change device and method of pilotless automobile in the present invention;
Fig. 2 show the operational process schematic diagram of navigation system in the present invention;
Fig. 3 is shown in the present invention based on cloud database navigation driving system structure chart;
Fig. 4 show the automatic lane change decision system of pilotless automobile in the specific embodiment of the invention;
Fig. 5 show pin hole ranging coordinate schematic diagram in the specific embodiment of the invention.
Specific embodiment:
The technical solution in the embodiment of the present invention will be clearly and completely described below, it is clear that described embodiment is only
It is the part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
All other embodiment that personnel are obtained without making creative work, belongs to the scope of protection of the invention:
A kind of pilotless automobile as shown in Figure 1 becomes duct device automatically, including image acquisition device, image processor 3, centre
Device module and control execution system 7 are managed, described image collector gathers the road mark line on road surface, described image processor
With image acquisition device data connection and for receiving the gathered data of image acquisition device, and to the image information of image acquisition device into
Row identification, and the function of markings is told, the central processing unit module is with image processor data connection and according to advance
The signal that the program of setting transmits out image processor carries out sending decision instruction after comprehensive analysis processing, and by decision instruction
Control execution system is transferred to, whether controlling automobile lane change, preferably, the control execution system includes braking
Controller, steering controller turn to lamp controller and throttle control, which performs system and passed according to central processing unit module
Defeated decision instruction, respectively by brake monitor, steering controller, turn to lamp controller and throttle control to change this vehicle
Speed and steering angle, complete lane change action, in the present embodiment, described image collector is arranged to high-speed area array camera 2, institute
It states central processing unit module and is arranged to vehicle-mounted ECD4.
As shown in Figure 2 and Figure 3, the pilotless automobile becomes duct device and further includes navigation system 6 automatically, the navigation system
System and central processing unit module data connection, the navigation system plan driving scheme according to the destination of input for automobile, and
According to the information real-time update database collected, in the present embodiment, the navigation system includes cloud database, vehicle-mounted end
End and the module of ground GPS base station three, wherein, car-mounted terminal uses wireless telecommunications with cloud database, ground GPS base station respectively
Mode carry out information exchange, concretely comprise the following steps,
(1) relevant informations such as vehicle destination, situation of remote, real time position are uploaded to cloud database by car-mounted terminal, and
Download the corresponding driving scheme information of high in the clouds transmission;Find that actual road conditions are different from high in the clouds download road conditions during driving, with actual road
Subject to condition, contexture by self is carried out, and the traffic information changed is sent to high in the clouds, updates cloud database;
(2) cloud database is the information and real-time road condition information uploaded according to car-mounted terminal, carries out driving planning, then by phase
The road conditions environment answered and driving scheme transmission to car-mounted terminal;
(3) ground GPS base station is using RTK technologies, and base station is calculated to the correction parameter of satellite distance, and by the parameter
It is sent to car-mounted terminal;
In practical applications, with reference to above- mentioned information interactive step, the concrete application step of the navigation system is,
Step 301:Start vehicle, destination is inputted by the interactive system of vehicle termination.
Step 302:Cloud database is connected, destination information, situation of remote and Ben Che are presently in location information etc.
Relevant information is uploaded to cloud database.
Step 303:According to vehicle upload information and road information and traffic information etc., calculated by cloud database
Planning, draws driving scheme, then scheme information is transmitted to car-mounted terminal.
Step 304:Vehicle gathers week in real time according to the cartographic information of download and driving scheme traveling using vehicle arrangement
Enclose environmental information and road information.
Step 305:The real time information collected is opposed with the environmental information and road information downloaded by cloud database
Than.
Step 306:Judge whether real time information is consistent with high in the clouds data, if information changes, perform step 307,
If content is consistent, step 309 is performed.
Step 307:By real-time information transmission to cloud database, original information is covered, updates the data storehouse.
Step 308:Vehicle is according to actual environment information and road information, contexture by self driving scheme, according still further to planning
Scheme travels.
Step 309:Judge to drive a vehicle and whether change, it is necessary to adjust traffic route in way, if changing, perform step
301, if not changing, perform step 310.
Step 310:According to the programme of download, continue to drive a vehicle.
In the present embodiment, the pilotless automobile becomes duct device and further includes context aware systems 1, the environment automatically
Sensory perceptual system and central processing unit module data connection, the context aware systems include camera and millimetre-wave radar, are used for
Relative distance, relative velocity and the barrier situation of surrounding vehicles are gathered, and the information collected is transferred to central processing unit
Module.
The pilotless automobile become automatically duct device further include with central processing unit module loud speaker 5, by central processing
The decision instruction of device module feeds back to occupant by voice signal.
A kind of automatic lane change method of pilotless automobile, comprises the following steps,
Step 1 gathers road information by high-speed area array camera, the information collected is transmitted to image processor;
Step 2 will handle the image information received by image processor and carry out identifying processing, after identification is post-processed
Information is transmitted to vehicle-mounted ECU;
Step 3 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change;
Step 4 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change.
Preferably, the image-recognizing method in the step 2 includes, and image is pre-processed, to adopting
The image of collection carries out gray processing, and carries out appropriate Morphological scale-space, based on image detection traffic marking, utilizes shape and edge
Information is used for quickly detecting.It is then based on style characteristic to extract, and necessary correction once is carried out to the image of deformation.Most
Afterwards, by estimating using distance as similarity, the identification to image is completed, wherein,
Step 1, colored original image is converted into gray level image, the method for expressing of gray level image is by each picture of image
The brightness value of vegetarian refreshments carries out quantification treatment, and the brightness range of each pixel is usually divided between 0-255 totally 256 gray scales
Rank, 0 to represent the point completely black, and 255 represent that the point is entirely white, and principle is using the palette of 256 colors, the value of each single item RGB
It is identical, tonal range 0-255, gray value is formulated as:
Energy effective expression and the picture content of description region shape in figure are extracted with the method for mathematical morphology, such as border, bone
Frame and convex hull etc., after pretreatment, it is also necessary to which carrying out some includes expansion, burn into opening operation and closed operation processing;
Step 2, for the binaryzation of image by the way that the pixel with same alike result is classified as a region, being classified as different attribute is another
One region.When according to a certain attribute carry out image region segmentation when seek to set corresponding threshold value.If G=0,1 ...,
L-1 } be image intensity value set, L representative image grey levels, setting gray value B={ b0, b1 } is two of threshold value T ∈ G
Gray value and b0, b1 ∈ G.Binaryzation is carried out to image f (x, y) using T as threshold value, obtains only 0 and 255 two gray level
Other image fT(x, y), expression are as follows:
The selection of threshold value herein utilizes minimum error method.Edge detection can be completed by the convolution of differential operator, be calculated with derivative
The value that the region that son acts on image grey scale change can be made larger is drawn is higher, therefore, corresponding fringe region is set thresholding,
So as to extract the pixel at edge, edge extracting is carried out used here as Canny operators.The feature extraction of roadmarking utilizes throwing
Shadow, geometrical property, Fourier descriptors, chain code feature statement roadmarking contour shape, comprehensive utilization Hu not bending moment and
Bending moment does not identify target to Zernike as characteristic value.
Step 3, the identification of roadmarking utilizes Euclidean distance metrics exemplary feature and the phase of images to be recognized feature
Like property, the feature vector of roadmarking to be identified and the mark sheet of sample storehouse Plays are compared one by one, work as sample storehouse
In a certain traffic marking characteristic value and reticle image to be identified when matching, then it is the standard traffic mark to judge identified image
Line, and corresponding function signal is exported, conversely, identified image is not roadmarking.
As shown in figure 4, the step of specific decision instruction is sent in practical applications, in the step three in the method
For,
Step 311, system gathers road mark line information first with high-speed area array camera, by image processor distinguishing mark line
Function signal;The relative velocity and distance of all around vehicle and this vehicle are measured with context aware systems, and monitors on road and is
It is no to have the information such as barrier, these information are then transferred to vehicle-mounted ECU and are analyzed and determined.
Step 312:The information collected is subjected to data analysis by vehicle-mounted ECU, judges lane line function and target track
On vehicle between distance whether be more than on safe distance and road whether have barrier.
Step 313:The relative distance of Ruo Benche and the vehicle on target track is both less than between vehicle the distance that drives safely, that
Acquisition information is continued to, until being both greater than safe distance with the relative distance of the vehicle on target track.
Step 314:After meeting lane change requirement originally, all information datas are subjected to fusion treatment by vehicle-mounted ECU, are passed through
Simulation calculates, and draws lane change decision scheme, i.e. lane change track and control data.
Step 315:Decision information is transferred to control execution system, steering angle angle, speed in decision scheme
This vehicle is manipulated, carries out lane change.
Step 316:If lane change process runs into barrier, lane line suddenly becomes solid line, the vehicle on target track
Speed suddenly change or other emergency cases then stop lane change and perform, carried out the information collected by master controller at once
Processing analysis, judges whether to continue lane change, can cut-through object etc., draw lane change decision scheme again, held by control
Row system performs decision-making action.
Step 317:If not running into barrier or other emergency cases, lane change is continued to, until reaching target track
Lane change is completed in position
Further, if during lane change, there are vehicle in front and back on this track, then need consider in lane change, Ben Che with
Whether its relative distance is consistently greater than safe distance, if being unsatisfactory for, is not available for lane change.If in addition, during lane change,
This vehicle will terminate lane change, when returning to this track, programme again, this track is become into target track, carries out simulation calculating
It performs again afterwards.
Further, during lane change, the distance analysis between vehicle has been used, to improve the security of environment sensing,
Methods of Distance Analysis wherein between vehicle is specific as follows:
The mathematical relationship established between two dimensional image coordinate and world coordinates needs to carry out linear calibration to video camera, uses here
Pin-hole imaging principle, the foundation of coordinate system are as shown in Figure 5.
Assuming that camera CCD be located at H on world coordinate system horizontal plane a bit, and have certain angle of inclination.In Fig. 5,
Ymin and Ymax represents the nearest and maximum distance of CCD verticals angle of view projection on the ground respectively, and Xmax represents CCD horizontal view angles
Farthest projector distance on the ground, α are then corresponding vertical angle of view with β, and γ is the projection on the ground of CCD horizontal view angles and seat
Mark system y-axis angle, according to the geometrical relationship of XOY coordinate systems, can obtain α, and the relational expression between β and γ is:
In x-y coordinate system, according to the value for α, β and the γ being calculated, it can extrapolate between camera and license plate image in x side
To the distance Lx and Ly with y directions, it is assumed that the size of license plate image is M × N, the seat of the arbitrary pixel point T in image coordinate system
It is designated as (i, j):
Lx and Ly is calculated, it is possible to the actual range L of two vehicles be calculated by Pythagorean theorem:
By the L being calculated and set safe distance L0(L0 has different in the lane changing way for turning round, turning around and keeping straight on etc.
Setting value)It is compared, and comparative result is transferred to vehicle-mounted ECU, corresponding decision is made by vehicle-mounted ECU.
The above-mentioned automatic lane change device and method of pilotless automobile on the premise of not depending on driver and completing automatic lane change,
Initiative recognition Road flexibly tackles different kinds of roads situation, practicability and high financial profit.
It is emphasized that:It the above is only presently preferred embodiments of the present invention, not the present invention made in any form
Limitation, any simple modification, equivalent change and modification that every technical spirit according to the invention makees above example,
In the range of still falling within technical solution of the present invention.
Claims (10)
1. a kind of pilotless automobile becomes duct device automatically, it is characterised in that:Including image acquisition device, image processor, center
Processor module and control execution system, described image collector gather the road mark line on road surface, described image processing
Gathered data of the device with image acquisition device data connection and for receiving image acquisition device, and to the image information of image acquisition device
It is identified, and tells the function of markings, the central processing unit module is with image processor data connection and according to pre-
The program first set sends decision instruction after carrying out comprehensive analysis processing to the signal that image processor transmits out, and decision-making is referred to
Order is transferred to control execution system, whether controlling automobile lane change.
2. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:Described image collector is set
It is set to high-speed area array camera.
3. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:The central processing unit mould
Group is arranged to vehicle-mounted ECD.
4. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:Further include navigation system,
The navigation system and central processing unit module data connection, the navigation system are automobile planning row according to the destination of input
Vehicle scheme, and according to the information real-time update database collected.
5. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:The navigation system includes
Cloud database, car-mounted terminal and the module of ground GPS base station three, wherein, car-mounted terminal respectively with cloud database, ground
GPS Base Station carries out information exchange by the way of wireless telecommunications.
6. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:Further include environment sensing system
System, the context aware systems and central processing unit module data connection, the context aware systems include camera and millimeter
Ripple radar for gathering the relative distance of surrounding vehicles, relative velocity and barrier situation, and the information collected is transferred to
Central processing unit module.
7. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:The control execution system
Including brake monitor, steering controller, lamp controller and throttle control are turned to, which performs system according to central processing
The decision instruction of device module transmission, respectively by brake monitor, steering controller, turn to lamp controller and throttle control with
Change the speed and steering angle of this vehicle, complete lane change action.
8. pilotless automobile according to claim 1 becomes duct device automatically, it is characterised in that:Further include central processing unit
The decision instruction of central processing unit module is fed back to occupant by module loud speaker by voice signal.
A kind of 9. automatic lane change method of pilotless automobile, it is characterised in that:Comprise the following steps,
Step 1 gathers road information by high-speed area array camera, the information collected is transmitted to image processor;
Step 2 will handle the image information received by image processor and carry out identifying processing, after identification is post-processed
Information is transmitted to vehicle-mounted ECU;
Step 3 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change;
Step 4 carries out comprehensive analysis processing to the image information that receives by vehicle-mounted ECU and sends decision instruction, and by decision-making
Instruction is transferred to control execution system, whether controlling automobile lane change.
10. a kind of automatic lane change method of pilotless automobile according to claim 9, it is characterised in that:The step 2
In image-recognizing method include, image is pre-processed, gray processing is carried out to the image of acquisition, and is carried out at morphology
Reason, based on image detection traffic marking, is used for quickly detecting using shape and marginal information, is then based on style characteristic and is carried
It takes, and necessary correction once is carried out to the image of deformation, finally, by estimating using distance as similarity, complete to image
Identification, wherein, concretely comprise the following steps:
Step 1, colored original image is converted into gray level image, the method for expressing of gray level image is by each picture of image
The brightness value of vegetarian refreshments carries out quantification treatment, and the brightness range of each pixel is usually divided between 0-255 totally 256 gray scales
Rank, 0 to represent the point completely black, and 255 represent that the point is entirely white, and principle is using the palette of 256 colors, the value of each single item RGB
It is identical, tonal range 0-255, gray value is formulated as:
Energy effective expression and the picture content of description region shape in figure are extracted with the method for mathematical morphology, such as border, bone
Frame and convex hull, after pretreatment, it is also necessary to which carrying out some includes expansion, burn into opening operation and closed operation processing;
Step 2, the binaryzation of image, by the way that the pixel with same alike result is classified as a region, different attribute is classified as
Another region, when according to a certain attribute carry out image region segmentation when seek to set corresponding threshold value, if G=0,
1 ..., L-1 } be image intensity value set, L representative image grey levels, setting gray value B={ b0, b1 } is threshold value T ∈ G
Two gray values and b0, b1 ∈ G, using T be threshold value to image f (x, y) carry out binaryzation, obtain one only 0 and 255 two
The image f of grey levelT(x, y), expression are as follows:
The selection of threshold value herein utilizes minimum error method, and edge detection can be completed by the convolution of differential operator, calculated with derivative
The value that the region that son acts on image grey scale change can be made larger is drawn is higher, therefore, corresponding fringe region is set thresholding,
So as to extract the pixel at edge, edge extracting is carried out used here as Canny operators, the feature extraction of roadmarking utilizes throwing
Shadow, geometrical property, Fourier descriptors, chain code feature statement roadmarking contour shape, comprehensive utilization Hu not bending moment and
Bending moment does not identify target to Zernike as characteristic value;
Step 3, the identification of roadmarking, it is similar to images to be recognized feature using Euclidean distance metrics exemplary feature
Property, the feature vector of roadmarking to be identified and the mark sheet of sample storehouse Plays are compared one by one, when in sample storehouse
When a certain traffic marking characteristic value and reticle image to be identified match, then it is the standard traffic mark to judge identified image
Line, and corresponding function signal is exported, conversely, identified image is not roadmarking.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711272791.3A CN108068817A (en) | 2017-12-06 | 2017-12-06 | A kind of automatic lane change device and method of pilotless automobile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711272791.3A CN108068817A (en) | 2017-12-06 | 2017-12-06 | A kind of automatic lane change device and method of pilotless automobile |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108068817A true CN108068817A (en) | 2018-05-25 |
Family
ID=62157925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711272791.3A Pending CN108068817A (en) | 2017-12-06 | 2017-12-06 | A kind of automatic lane change device and method of pilotless automobile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108068817A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035863A (en) * | 2018-08-09 | 2018-12-18 | 北京智行者科技有限公司 | Vehicle compulsory lane-change running method |
CN109696173A (en) * | 2019-02-20 | 2019-04-30 | 苏州风图智能科技有限公司 | A kind of car body air navigation aid and device |
CN109739244A (en) * | 2019-02-01 | 2019-05-10 | 温州大学 | One kind being used for unpiloted information sharing system |
CN109878523A (en) * | 2019-03-08 | 2019-06-14 | 北京领骏科技有限公司 | A kind of automatic driving vehicle lane changing control method and device |
CN109946688A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | Lane-change contextual data extracting method, device and server |
WO2020024101A1 (en) * | 2018-07-31 | 2020-02-06 | 深圳市大疆创新科技有限公司 | Map data source processing method, map updating method, device, and storage medium |
CN111273668A (en) * | 2020-02-18 | 2020-06-12 | 福州大学 | Unmanned vehicle motion track planning system and method for structured road |
CN111338353A (en) * | 2020-03-26 | 2020-06-26 | 吉林大学 | Intelligent vehicle lane change track planning method under dynamic driving environment |
CN111599182A (en) * | 2020-07-22 | 2020-08-28 | 中汽院汽车技术有限公司 | Automatic lane changing behavior extraction method based on natural driving data |
CN112092827A (en) * | 2020-09-23 | 2020-12-18 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
CN112519780A (en) * | 2020-09-29 | 2021-03-19 | 广州巨时信息科技股份有限公司 | Unmanned vehicle and lane changing system thereof |
CN112634655A (en) * | 2020-12-15 | 2021-04-09 | 北京百度网讯科技有限公司 | Lane changing processing method and device based on lane line, electronic equipment and storage medium |
CN113335310A (en) * | 2021-07-21 | 2021-09-03 | 新石器慧通(北京)科技有限公司 | Decision-based exercise planning method and device, electronic equipment and storage medium |
CN113702066A (en) * | 2021-08-31 | 2021-11-26 | 中汽院(重庆)汽车检测有限公司 | Evaluation system and evaluation method for lane departure warning system of commercial vehicle |
CN113942458A (en) * | 2021-10-29 | 2022-01-18 | 禾多科技(北京)有限公司 | Control method, device, equipment and medium for vehicle-mounted camera adjusting system |
CN115171428A (en) * | 2022-06-24 | 2022-10-11 | 重庆长安汽车股份有限公司 | Vehicle cut-in early warning method based on visual perception |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010271929A (en) * | 2009-05-21 | 2010-12-02 | Denso Corp | Device and method for estimating lane boundary line kind |
CN102208019A (en) * | 2011-06-03 | 2011-10-05 | 东南大学 | Method for detecting lane change of vehicle based on vehicle-mounted camera |
CN103996031A (en) * | 2014-05-23 | 2014-08-20 | 奇瑞汽车股份有限公司 | Self adaptive threshold segmentation lane line detection system and method |
CN104331710A (en) * | 2014-11-19 | 2015-02-04 | 集美大学 | On-off state recognition system |
CN105015545A (en) * | 2015-07-03 | 2015-11-04 | 内蒙古麦酷智能车技术有限公司 | Autonomous lane-changing decision making system for pilotless automobile |
CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
CN106529404A (en) * | 2016-09-30 | 2017-03-22 | 张家港长安大学汽车工程研究院 | Imaging principle-based recognition method for pilotless automobile to recognize road marker line |
-
2017
- 2017-12-06 CN CN201711272791.3A patent/CN108068817A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010271929A (en) * | 2009-05-21 | 2010-12-02 | Denso Corp | Device and method for estimating lane boundary line kind |
CN102208019A (en) * | 2011-06-03 | 2011-10-05 | 东南大学 | Method for detecting lane change of vehicle based on vehicle-mounted camera |
CN103996031A (en) * | 2014-05-23 | 2014-08-20 | 奇瑞汽车股份有限公司 | Self adaptive threshold segmentation lane line detection system and method |
CN104331710A (en) * | 2014-11-19 | 2015-02-04 | 集美大学 | On-off state recognition system |
CN105015545A (en) * | 2015-07-03 | 2015-11-04 | 内蒙古麦酷智能车技术有限公司 | Autonomous lane-changing decision making system for pilotless automobile |
CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
CN106529404A (en) * | 2016-09-30 | 2017-03-22 | 张家港长安大学汽车工程研究院 | Imaging principle-based recognition method for pilotless automobile to recognize road marker line |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020024101A1 (en) * | 2018-07-31 | 2020-02-06 | 深圳市大疆创新科技有限公司 | Map data source processing method, map updating method, device, and storage medium |
CN109035863A (en) * | 2018-08-09 | 2018-12-18 | 北京智行者科技有限公司 | Vehicle compulsory lane-change running method |
CN109739244A (en) * | 2019-02-01 | 2019-05-10 | 温州大学 | One kind being used for unpiloted information sharing system |
CN109696173A (en) * | 2019-02-20 | 2019-04-30 | 苏州风图智能科技有限公司 | A kind of car body air navigation aid and device |
CN109878523A (en) * | 2019-03-08 | 2019-06-14 | 北京领骏科技有限公司 | A kind of automatic driving vehicle lane changing control method and device |
CN109946688A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | Lane-change contextual data extracting method, device and server |
CN109946688B (en) * | 2019-03-18 | 2019-12-24 | 中国汽车工程研究院股份有限公司 | Lane changing scene data extraction method and device and server |
CN111273668A (en) * | 2020-02-18 | 2020-06-12 | 福州大学 | Unmanned vehicle motion track planning system and method for structured road |
CN111273668B (en) * | 2020-02-18 | 2021-09-03 | 福州大学 | Unmanned vehicle motion track planning system and method for structured road |
CN111338353A (en) * | 2020-03-26 | 2020-06-26 | 吉林大学 | Intelligent vehicle lane change track planning method under dynamic driving environment |
CN111599182B (en) * | 2020-07-22 | 2020-10-20 | 中汽院汽车技术有限公司 | Automatic lane changing behavior extraction method based on natural driving data |
CN111599182A (en) * | 2020-07-22 | 2020-08-28 | 中汽院汽车技术有限公司 | Automatic lane changing behavior extraction method based on natural driving data |
CN112092827A (en) * | 2020-09-23 | 2020-12-18 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
CN112092827B (en) * | 2020-09-23 | 2022-04-22 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
CN112519780A (en) * | 2020-09-29 | 2021-03-19 | 广州巨时信息科技股份有限公司 | Unmanned vehicle and lane changing system thereof |
CN112634655A (en) * | 2020-12-15 | 2021-04-09 | 北京百度网讯科技有限公司 | Lane changing processing method and device based on lane line, electronic equipment and storage medium |
CN112634655B (en) * | 2020-12-15 | 2022-11-22 | 阿波罗智联(北京)科技有限公司 | Lane changing processing method and device based on lane line, electronic equipment and storage medium |
CN113335310A (en) * | 2021-07-21 | 2021-09-03 | 新石器慧通(北京)科技有限公司 | Decision-based exercise planning method and device, electronic equipment and storage medium |
CN113335310B (en) * | 2021-07-21 | 2021-11-30 | 新石器慧通(北京)科技有限公司 | Decision-based exercise planning method and device, electronic equipment and storage medium |
CN113702066A (en) * | 2021-08-31 | 2021-11-26 | 中汽院(重庆)汽车检测有限公司 | Evaluation system and evaluation method for lane departure warning system of commercial vehicle |
CN113942458A (en) * | 2021-10-29 | 2022-01-18 | 禾多科技(北京)有限公司 | Control method, device, equipment and medium for vehicle-mounted camera adjusting system |
CN115171428A (en) * | 2022-06-24 | 2022-10-11 | 重庆长安汽车股份有限公司 | Vehicle cut-in early warning method based on visual perception |
CN115171428B (en) * | 2022-06-24 | 2023-06-30 | 重庆长安汽车股份有限公司 | Vehicle cut-in early warning method based on visual perception |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108068817A (en) | A kind of automatic lane change device and method of pilotless automobile | |
CN111874006B (en) | Route planning processing method and device | |
US11521009B2 (en) | Automatically generating training data for a lidar using simulated vehicles in virtual space | |
CN110345961B (en) | Controlling a host vehicle based on detected parked vehicle characteristics | |
US10896539B2 (en) | Systems and methods for updating highly automated driving maps | |
US11373532B2 (en) | Pothole detection system | |
CN105260699B (en) | A kind of processing method and processing device of lane line data | |
Broggi | Automatic vehicle guidance: the experience of the ARGO autonomous vehicle | |
CN102682292B (en) | Method based on monocular vision for detecting and roughly positioning edge of road | |
Li et al. | Springrobot: A prototype autonomous vehicle and its algorithms for lane detection | |
JP6082802B2 (en) | Object detection device | |
JP3619628B2 (en) | Driving environment recognition device | |
Turk et al. | Video road-following for the autonomous land vehicle | |
CN109635737B (en) | Auxiliary vehicle navigation positioning method based on road marking line visual identification | |
CN107506760A (en) | Traffic signals detection method and system based on GPS location and visual pattern processing | |
CN102073846A (en) | Method for acquiring traffic information based on aerial images | |
CN111931683B (en) | Image recognition method, device and computer readable storage medium | |
WO2021199584A1 (en) | Detecting debris in a vehicle path | |
CN110008891A (en) | A kind of pedestrian detection localization method, device, cart-mounted computing device and storage medium | |
CN113255553B (en) | Sustainable learning method based on vibration information supervision | |
CN117671617A (en) | Real-time lane recognition method in container port environment | |
CN110727269B (en) | Vehicle control method and related product | |
CN113071515A (en) | Movable carrier control method, device, movable carrier and storage medium | |
CN112580489A (en) | Traffic light detection method and device, electronic equipment and storage medium | |
CN114677658B (en) | Billion-pixel dynamic large scene image acquisition and multi-target detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180525 |