CN104157160B - Vehicle travel control method, device and vehicle - Google Patents
Vehicle travel control method, device and vehicle Download PDFInfo
- Publication number
- CN104157160B CN104157160B CN201410390012.XA CN201410390012A CN104157160B CN 104157160 B CN104157160 B CN 104157160B CN 201410390012 A CN201410390012 A CN 201410390012A CN 104157160 B CN104157160 B CN 104157160B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane line
- information
- lane
- particle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 239000002245 particle Substances 0.000 claims description 111
- 230000004888 barrier function Effects 0.000 claims description 21
- 239000011551 heat transfer agent Substances 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000011084 recovery Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012952 Resampling Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Abstract
The present invention provides a kind of vehicle travel control method, device and vehicle, and wherein method includes: receive vehicle-mounted camera collection the lane line image sent;Using lane detection algorithm that described lane line image is carried out lane detection, obtain lane detection result, described lane detection result represents whether front lane line disappears;If described lane detection result represents that front lane line disappears, then control vehicle to stop travelling, and send described vehicle present position information to network side information centre, determine that the traveling of described vehicle controls information for described network side information centre according to described vehicle present position information;Receive the traveling control information that network side information centre sends, and control described vehicle traveling according to described traveling control information.The vehicle travel control method that the present invention provides, it is possible to when or lane line poor in lane line situation disappears, continues to control vehicle and travels, and ensure that the safety of traveling.
Description
Technical field
The present invention relates to intelligent transport technology, particularly relate to a kind of vehicle travel control method, device and car
?.
Background technology
Intelligent transport technology is by advanced satellite positioning navigation technology, computer technology, graph image
Treatment technology, data communication technology, sensor technology, information technology, electron controls technology etc. are high-new
Technology applies in the transport of traffic, control and vehicle manufacture effectively, so that vehicle leans on self
Intelligence is at safe on-road, freely travel.
At present, intelligent vehicle is applied on the less highway of automobile more, utilizes lane detection to calculate
Method determines the positional information of lane line, provides reference for navigation, if automotive run-off-road line, then by car
Master controller according to vehicle relative to the position of both sides lane line drive steering spindle turn over certain angle
Degree, thus control vehicle in predetermined lanes, it is possible to realize unmanned to a certain extent.
Being in place of the deficiencies in the prior art, the direction controlling of automatic driving vehicle places one's entire reliance upon detection
The lane line position arrived, when or lane line poor in a certain section lane line situation disappears, according to
Algorithm inspection may not measure lane line, and vehicle can be caused cannot to continue to travel.
Summary of the invention
The present invention provides a kind of vehicle travel control method, device and vehicle, in order to solve in prior art
The problem that when or lane line poor in lane line situation disappears, vehicle cannot continue to travel.
The first aspect of the invention is to provide a kind of vehicle travel control method, including:
Receive vehicle-mounted camera collection the lane line image sent;
Use lane detection algorithm that described lane line image is carried out lane detection, obtain lane line inspection
Surveying result, described lane detection result represents whether front lane line disappears;
If described lane detection result represents that front lane line disappears, then control vehicle and stop travelling, and
Described vehicle present position information is sent, in described network side information to network side information centre
According to described vehicle present position information, the heart determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
Further, in above-mentioned vehicle travel control method, described vehicle present position information, bag
Include at least one in following information:
The road image information in the described vehicle present position front of described vehicle-mounted camera shooting;
The vehicle mounted guidance image information in described vehicle present position front;
The latitude and longitude information of described vehicle present position.
Further, in above-mentioned vehicle travel control method, described employing lane detection algorithm is to described
Lane line image carries out lane detection, obtains lane detection result, including:
The boundary pixel point of lane line is extracted from described lane line image;
Particle state value in previous frame lane line image is added with dimensional Gaussian random noise, obtains
Particle state value in described lane line image, described state value is particle horizontal stroke in lane line image
Vertical coordinate, described particle produces in the first two field picture in the following way: according to the border picture of lane line
Vegetarian refreshments obtains lane line straight line at place in the first frame lane line image, chooses first on described straight line
The point of interest of quantity, the particle of the second quantity uniformly produced with normal distribution centered by each point of interest;
Boundary pixel point according to the lane line extracted and described particle are in described lane line image
State value, obtains described particle weight in described lane line image;
Weight is set as effective particle more than the particle of the first predetermined threshold value, and judges whether that each is emerging
The weight sum of effective particle of interest point is both less than the second predetermined threshold value, if, it is determined that current vehicle diatom
Disappear, if not, it is determined that current vehicle diatom does not disappears.
Further, above-mentioned vehicle travel control method, the row that described reception network side information centre sends
Sail control information, and control after described vehicle travels, also to include according to described traveling control information:
Receiving the driving recovery message that network side information centre sends, wherein, described driving recovers message and is
Described network side information centre sends when determining that lane line recovers;
Vehicle described in lane detection algorithm controls is used to travel.
Further, above-mentioned vehicle travel control method, also include:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
Another aspect of the present invention is to provide a kind of controlling device for vehicle running, including,
Lane line receiver module, for receiving vehicle-mounted camera collection the lane line image sent;
Lane detection module, is used for using lane detection algorithm that described lane line image is carried out track
Line detects, and obtains lane detection result, and described lane detection result represents whether front lane line disappears
Lose;
Information sending module, for when described lane detection result represents that front lane line disappears, controlling
Vehicle processed stops travelling, and sends described vehicle present position information to network side information centre, with
Determine the traveling of described vehicle according to described vehicle present position information for described network side information centre
Control information;
Information receiving module, for receiving the traveling control information that network side information centre sends, and according to
Described traveling control information controls described vehicle and travels.
Further, in above-mentioned controlling device for vehicle running, described vehicle present position information, bag
Include at least one in following information:
The road image information in the described vehicle present position front of described vehicle-mounted camera shooting;
The vehicle mounted guidance image information in described vehicle present position front;
The latitude and longitude information of described vehicle present position.
Further, in above-mentioned controlling device for vehicle running, described lane detection module, including:
Boundary Extraction unit, for extracting the boundary pixel point of lane line from described lane line image;
State value determines unit, for particle state value in previous frame lane line image is high with two dimension
This random noise is added, and obtains particle state value in described lane line image, and described state value is grain
Son transverse and longitudinal coordinate in lane line image, described particle produces in the first two field picture in the following way:
Boundary pixel point according to lane line obtains lane line straight line at place in the first frame lane line image,
Choose the point of interest of the first quantity on described straight line, uniformly produce with normal distribution centered by each point of interest
The particle of the second raw quantity;
Weight determining unit, for the boundary pixel point of lane line extracted and described particle described
State value in lane line image, obtains described particle weight in described lane line image;
Judging unit, for weight is set as effective particle more than the particle of the first predetermined threshold value, and sentences
The weight sum of effective particle of disconnected whether each point of interest is both less than the second predetermined threshold value, the most then
Determine current lane heading line off, if not, it is determined that current vehicle diatom does not disappears.
Further, in above-mentioned controlling device for vehicle running, described information receiving module, it is additionally operable to:
The traveling sent in described reception network side information centre controls information, and controls according to described traveling
After information controls described vehicle traveling, receive the driving recovery message that network side information centre sends, its
In, described driving recovers the message transmission when determining that lane line recovers that is described network side information centre;
Vehicle described in lane detection algorithm controls is used to travel.
Further, in above-mentioned controlling device for vehicle running, described information sending module, it is additionally operable to:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
An additional aspect of the present invention is to provide a kind of vehicle, including vehicle-mounted camera and intelligent control platform,
Wherein, described intelligent control platform includes any of the above-described controlling device for vehicle running.
Vehicle travel control method, device and the vehicle that the present invention provides, when detecting that lane line disappears
Control vehicle to stop travelling, communicate with network side information centre simultaneously, send vehicle and be currently located position
Confidence ceases to information centre, and the traveling determined according to information centre controls information and controls vehicle traveling, energy
Enough the most poor in lane line situation or time lane line disappears, continue to control vehicle and travel, and ensure that traveling
Safety.
Accompanying drawing explanation
Fig. 1 is the flow chart of vehicle travel control method embodiment of the present invention;
Fig. 2 is the flow chart of lane detection algorithm in vehicle travel control method embodiment of the present invention;
Fig. 3 is the structural representation of controlling device for vehicle running embodiment of the present invention;
Fig. 4 is the structural representation of lane detection module in controlling device for vehicle running embodiment of the present invention
Figure;
Fig. 5 is the structural representation of vehicle embodiments of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
Fig. 1 is the flow chart of vehicle travel control method embodiment of the present invention, as it is shown in figure 1, this enforcement
The method of example may include that
Step 101, reception vehicle-mounted camera collection the lane line image sent;
Wherein, vehicle-mounted camera carries out video acquisition to lane line, and video is made up of picture frame, vehicle-mounted takes the photograph
As each frame lane line image is sent to for carrying out the device that vehicle traveling controls, photographic head by head in real time
When mounted it is ensured that can accurate acquisition to the information of right ahead lane line.
Step 102, employing lane detection algorithm carry out lane detection to described lane line image,
To lane detection result, described lane detection result represents whether front lane line disappears;
Specifically, after receiving the lane line image that vehicle-mounted camera sends, lane detection algorithm is used
Detecting whether the lane line in this image disappears, lane detection algorithm has a variety of, for example, it is possible to be
Kalman filtering algorithm, dynamic bayesian network etc., this is not limited by the present embodiment.
If step 103 described lane detection result represents that front lane line disappears, then control vehicle and stop
Only travel, and send described vehicle present position information to network side information centre, for described net
According to described vehicle present position information, Luo Ce information centre determines that the traveling of described vehicle controls letter
Breath;
Specifically, if testing result represents that lane line does not disappears, then control vehicle along the car detected
Diatom travels, if testing result represents that front lane line disappears, then controls vehicle and stops travelling, and will
Vehicle present position information is sent to information centre.
Wherein, at least one during vehicle present position information can be following information:
The road image information in this vehicle present position front of vehicle-mounted camera shooting;
The vehicle mounted guidance image information in vehicle present position front;
The latitude and longitude information of vehicle present position.
Above-mentioned vehicle present position information is connected transmission by vehicle-mounted high-capacity SIM card by GPRS data
To information centre.
While sending vehicle present position information to information centre, it is also possible to send out to information centre
Send sound prompting, need information centre to carry out travelling control to it with this vehicle of prompting message center.Work as letter
After breath center receives sound prompting, information centre staff open the display module of information centre,
The position letter that display module collects for showing the vehicle-mounted camera received and/or onboard navigation system
Breath, information centre can be according to the vehicle front traffic information comprised in positional information or vehicle place
Position coordinates determines that the traveling of vehicle controls information.Such as, the staff of information centre can be according to car
Carry the image information that photographic head photographs, as driver, vehicle is controlled in real time, wherein, OK
Sailing control information can be vehicle steering angle or acceleration, deceleration, so that vehicle is according to this traveling
Control information normally travels in the case of lane line disappears.
The traveling that step 104, reception network side information centre send controls information, and according to described traveling
Control information controls described vehicle and travels.
The vehicle travel control method that the present embodiment provides, when detecting that lane line disappears, control vehicle stops
Only travel, communicate with network side information centre simultaneously, send vehicle present position information to letter
Breath center, and the traveling control information control vehicle traveling determined according to information centre, it is possible at lane line
When situation is poor or lane line disappears, continues to control vehicle and travel, and ensure that the safety of traveling.
Fig. 2 is the flow chart of lane detection algorithm in vehicle travel control method embodiment of the present invention, as
Shown in Fig. 2, on the basis of the technical scheme that above-described embodiment provides, the specific embodiment party of step 102
Formula may include that
Step 1021, from described lane line image, extract the boundary pixel point of lane line;
In real road, road surface is divided into one or more track by lane line, and lane line has substantially
Following characteristics:
(1), on color, lane line is in the majority with white and yellow;
(2) gray scale of lane line is apparently higher than the gray scale of surrounding;
(3) lane line is in the majority with straight line and regular curve, and curved degree is little.
In lane detection algorithm, these features can be made full use of.For the lane line of different situations,
The method that extraction boundary pixel point is used is the most different.Such as, it is the situation of white to lane line,
The RGB image received from vehicle-mounted camera can be converted to gray image, then gray image is carried out
Luminance transformation, extracts the boundary pixel point of lane line;It is the situation of yellow to lane line, can use
The method of the Color edge detection of gradient carries out Boundary Extraction, and Color edge detection method is relative to directly conversion
For the method for gray image, it is possible to retain the brightness of coloured image, by the border picture of yellow lane line
Vegetarian refreshments extracts so that it is the similar gray value of the white lane line obtained in gray scale and preceding method.
In order to ensure the real-time of lane detection, the efficiency of lane detection algorithm can not be the lowest, so
After extracting the boundary pixel point of lane line, it is also possible to lane line image is carried out intercepting process, such as,
1/2 that global image can intercept on width and/or on height centre is converted into topography, then
Carrying out conversion process according to the relation between local and global image, wherein, the width intercepting image is necessary
It is spaced more than lane line.Image is carried out intercepting process and not only greatly reduces amount of calculation, additionally it is possible to avoid
Noise jamming.
Step 1022, by particle state value in previous frame lane line image and dimensional Gaussian random noise
Being added, obtain particle state value in described lane line image, described state value is that particle is at lane line
Transverse and longitudinal coordinate in image, described particle produces in the first two field picture in the following way: according to track
The boundary pixel point of line obtains lane line straight line at place in the first frame lane line image, at described straight line
On choose the point of interest of the first quantity, second uniformly produced centered by each point of interest with normal distribution
The particle of quantity;
After extracting the boundary pixel point of lane line, can use particle filter algorithm that lane line is carried out
Detection further.Particle filter algorithm is a kind of method utilizing Monte Carlo simulation to realize Bayesian filter,
It can reasonable solution nonlinear problem.Core concept be utilize a series of sample randomly drawed and
The weight of sample carrys out the Posterior probability distribution of alternative state, when the number of sample becomes sufficiently large, passes through
Such arbitrary sampling method can be obtained by real Posterior distrbutionp and well approximates.
Specifically, for the first frame lane line image, use the Hough transformation lane line border picture to extracting
Vegetarian refreshments processes, it may be determined that the straight line at lane line place.The straight line at lane line place is chosen
The point of interest of one quantity, the grain of the second quantity uniformly produced with normal distribution centered by each point of interest
Son.Choosing 20 points of interest in the present embodiment, the point of interest chosen at least will be with image boundary distance 10-20
More than individual pixel, in case point of interest goes out image boundary during follow-up lane detection.To each point of interest,
Producing a number of particle near it, in order to ensure precision, number of particles to be chosen abundant,
The number of particles that the present embodiment selects is 100.
From the beginning of the second frame lane line image, each particle state value in current lane line image is
Particle state value in previous frame lane line image and dimensional Gaussian random noise sum, i.e. this
In embodiment, the state equation of particle filter is:
Hij(t)=Hij(t-1)+M (1)
Wherein, HijT () represents the state value of the jth particle of i-th point of interest in t two field picture, M
For dimensional Gaussian random noise, M obeys the normal distribution of N (0,5).In the present embodiment,
I=1,2 ... 20, j=1,2 ... 100, the abscissa of state value particle and vertical coordinate (x (t), y (t)) represent,
Particle state value in t frame lane line image, equal to this particle in t-1 frame lane line image
State value and dimensional Gaussian random noise sum.
The boundary pixel point of the lane line that step 1023, basis extract and described particle are in described track
State value in line image, obtains described particle weight in described lane line image;
First, by particle state value H in current lane line imageijT () adds observation noise E, obtain
Particle observation Z in current lane line imageij(t), i.e. the observation side of particle filter in this enforcement
Cheng Wei:
Zij(t)=Hij(t)+E (2)
Wherein, observation ZijT () is also made up of transverse and longitudinal coordinate, observation noise E is just obeying N (0,3)
State is distributed.
Then, the boundary pixel point of lane line is linked to be a smooth line segment, seeks observation Z of particleij(t)
Nearest distance l to this line segmentij;If lane line is relatively thicker, the boundary pixel point of lane line can connect
Become two sections of line segments, then observation Z of particle on the basis of the center line of these two sections of line segments, can be soughtijT () arrives
Nearest distance l of this center lineij。
Finally, according to lijObtain likelihood probability p of particleij, the likelihood probability computing formula of particle is:
pij=exp (-a × lij) (3)
Wherein a is the constant more than 0.
The likelihood probability of all particles of each point of interest is normalized, to ensure all particles
Probability sum be added equal to 1, the likelihood probability after normalization is the weight of each particle.
Step 1024, weight is set as effective particle more than the particle of the first predetermined threshold value, it may be judged whether
The weight sum of effective particle of each point of interest is both less than the second predetermined threshold value, if, it is determined that when
Front lane line disappears, if not, it is determined that current vehicle diatom does not disappears.
Such as, for first point of interest, including 100 particles, after weight calculation, this is found
100 particles have the weight of 10 less than the first predetermined threshold value, then it is assumed that these 10 particles are invalid
Particle, remaining 90 particles is effective particle, sues for peace the weight of 90 effective particles, and judges power
Whether weight sum is less than the second predetermined threshold value.Aforesaid operations is also performed for remaining point of interest, if institute
Effective particle weights sum of interesting point is respectively less than the second predetermined threshold value, then it is assumed that current vehicle diatom is
Disappear.
When lane line does not disappears, for each point of interest, by the state value H of its all particlesijAnd power
Weight pijWeighted sum, it is believed that the value obtained is exactly true in current lane line image of this point of interest
Position, can obtain the estimation position of lane line in present image according to the actual position of whole points of interest,
And control vehicle traveling with this.
When lane line disappears, control vehicle and stop travelling, and communicate with network side information centre,
To enable the vehicle to travel under the control of the heart in the information.
Additionally, after obtaining point of interest actual position in current lane line image, it is also possible to reject nothing
Effect particle, and carry out re-sampling operations according to remaining effective particle, it is therefore an objective to reduce the grain that weight is less
The number of son, concentrates on the particle with greater weight.The method of resampling has a variety of,
Conventional, effective particle bigger for weight is split as two or more, to fill up the invalid grain of rejecting
The position of son, making the number of particles after resampling remain in that is 100.
Such as, for a certain point of interest, it is assumed that after weight calculation, t two field picture has 10 grains
These 10 invalid particles less than the first predetermined threshold value, are then rejected by the weight of son, and now particle number reduces,
Remaining 90 particles are re-started normalized, obtains the new weight of each particle, make residue
The weight sum of 90 particles is equal to 1.Assume that normalized recoil is designated as the power of the particle of (48,52)
Be heavily 0.08, coordinate be the weight of the particle of (42,50) be 0.04, residue 88 particles weight equal
It is 0.01, in order to keep particle number constant, the particle that weight is 0.08 is splitted into 8, by weight
Be 0.04 particle split into 4, remaining particle keep constant, again gather into 100 particles, namely
Saying, in 100 new particles, the coordinate having 8 is (48,52), and the coordinate having 4 is (42,50),
When t+1 frame lane line image processes, based on these 100 new particles, calculate state value.
In the vehicle travel control method that the present embodiment provides, particle filter algorithm is used to carry out lane line inspection
Survey, the most directly use the transverse and longitudinal coordinate state value as particle of particle, it is possible to reduce the complexity of algorithm
Degree, improves efficiency of algorithm.
Further, above-described embodiment provide technical scheme on the basis of, it is preferred that described in connect
Receive the traveling control information that network side information centre sends, and control according to described traveling control information described
After vehicle travels, also include:
Receiving the driving recovery message that network side information centre sends, wherein, described driving recovers message and is
Described network side information centre sends when determining that lane line recovers;
After receiving driving recovery message, vehicle described in lane detection algorithm controls is used to travel.
Further, on the basis of the technical scheme that above-described embodiment provides, it is preferred that also include:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
Specifically, vehicle is also equipped with the sensor for detecting barrier, and such as, Vehicle radar senses
Device etc., when detecting that there is barrier in front, if automobile also continues to travel according to the lane line detected,
It may happen that dangerous, therefore, even if now lane line does not disappear, carry out vehicle and travel the dress controlled
Put and can also communicate with information centre, vehicle present position information is sent to information centre, information
Center can adjust vehicle heading according to the traffic information of vehicle present position, avoid front
Barrier.
If additionally, vehicle has arrived at destination, i.e. the distance travelled number of vehicle reaches to preset mileage number,
Then can control vehicle to stop travelling, and send prompting message to information centre, information centre be vehicle
Distributing next traveling task, next starting point travelling task is vehicle present position, and terminal is by information
Center resets.
Fig. 3 is the structural representation of controlling device for vehicle running embodiment of the present invention, as it is shown on figure 3, this
The device of embodiment may include that
Lane line receiver module 31, for receiving vehicle-mounted camera collection the lane line image sent;
Lane detection module 32, is used for using lane detection algorithm that described lane line image is carried out car
Diatom detects, and obtains lane detection result, and whether described lane detection result represents front lane line
Disappear;
Information sending module 33, is used for when described lane detection result represents that front lane line disappears,
Control vehicle to stop travelling, and send described vehicle present position information to network side information centre,
Determine the row of described vehicle according to described vehicle present position information for described network side information centre
Sail control information;
Information receiving module 34, the traveling sent for receiving network side information centre controls information, and root
Control described vehicle according to described traveling control information to travel.
The device of the present embodiment, may be used for performing the technical scheme of embodiment of the method shown in Fig. 1, in fact
Existing principle is similar with technique effect, and here is omitted.
On the basis of the apparatus structure that above-described embodiment provides, further, described vehicle is currently located
Positional information, including at least one in following information:
The road image information in the described vehicle present position front of described vehicle-mounted camera shooting;
The vehicle mounted guidance image information in described vehicle present position front;
The latitude and longitude information of described vehicle present position.
Fig. 4 is the structural representation of lane detection module in controlling device for vehicle running embodiment of the present invention
Figure, as shown in Figure 4, the device of the present embodiment is on the basis of Fig. 3 shown device structure, further,
Lane detection module 32 may include that
Boundary Extraction unit 321, for extracting the boundary pixel of lane line from described lane line image
Point;
State value determines unit 322, for by particle state value and two in previous frame lane line image
Dimension gaussian random noise is added, and obtains particle state value in described lane line image, described state value
For particle transverse and longitudinal coordinate in lane line image, described particle in the first two field picture in the following way
Produce: obtain lane line place straight in the first frame lane line image according to the boundary pixel point of lane line
Line, chooses the point of interest of the first quantity on described straight line, with normal distribution centered by each point of interest
The particle of the second quantity uniformly produced;
Weight determining unit 323, for the boundary pixel point according to the lane line extracted and described grain
Son state value in described lane line image, obtains described particle weight in described lane line image;
Judging unit 324, for weight is set as effective particle more than the particle of the first predetermined threshold value,
And judge whether that the weight sum of effective particle of each point of interest is both less than the second predetermined threshold value, if so,
Then determine current lane heading line off, if not, it is determined that current vehicle diatom does not disappears.
The device of the present embodiment, may be used for performing lane detection algorithm in embodiment of the method shown in Fig. 2
Technical scheme, it is similar with technique effect that it realizes principle, and here is omitted.
On the basis of the apparatus structure that above-described embodiment provides, further, information receiving module 34,
It is additionally operable to:
The traveling sent in described reception network side information centre controls information, and controls according to described traveling
After information controls described vehicle traveling, receive the driving recovery message that network side information centre sends, its
In, described driving recovers the message transmission when determining that lane line recovers that is described network side information centre;
Vehicle described in lane detection algorithm controls is used to travel.
On the basis of the apparatus structure that above-described embodiment provides, further, information sending module 33,
It is additionally operable to:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
Fig. 5 is the structural representation of vehicle embodiments of the present invention, as it is shown in figure 5, the vehicle of the present embodiment
Can include vehicle-mounted camera 51 and intelligent control platform 52, wherein, intelligent control platform 55 includes
State the controlling device for vehicle running described in any embodiment.
The vehicle that the present invention provides, stops travelling when lane line disappears detecting, believes with network side simultaneously
Breath center communicates, and transmission present position information is to information centre, and determines according to information centre
Traveling control information and travel, it is possible to continue when or lane line poor in lane line situation disappears to travel,
And ensure that the safety of traveling.
One of ordinary skill in the art will appreciate that: realize all or part of step of above-mentioned each method embodiment
Suddenly can be completed by the hardware that programmed instruction is relevant.Aforesaid program can be stored in a computer can
Read in storage medium.This program upon execution, performs to include the step of above-mentioned each method embodiment;And
Aforesaid storage medium includes: ROM, RAM, magnetic disc or CD etc. are various can store program code
Medium.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, rather than right
It limits;Although the present invention being described in detail with reference to foregoing embodiments, this area common
Skilled artisans appreciate that the technical scheme described in foregoing embodiments still can be modified by it,
Or the most some or all of technical characteristic is carried out equivalent;And these amendments or replacement, and
The essence not making appropriate technical solution departs from the scope of various embodiments of the present invention technical scheme.
Claims (9)
1. a vehicle travel control method, it is characterised in that including:
Receive vehicle-mounted camera collection the lane line image sent;
Use lane detection algorithm that described lane line image is carried out lane detection, obtain lane line inspection
Surveying result, described lane detection result represents whether front lane line disappears;
If described lane detection result represents that front lane line disappears, then control vehicle and stop travelling, and
Described vehicle present position information is sent, in described network side information to network side information centre
According to described vehicle present position information, the heart determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel;
Described employing lane detection algorithm carries out lane detection to described lane line image, obtains track
Line testing result, including:
The boundary pixel point of lane line is extracted from described lane line image;
Particle state value in previous frame lane line image is added with dimensional Gaussian random noise, obtains
Particle state value in described lane line image, described state value is particle horizontal stroke in lane line image
Vertical coordinate, described particle produces in the first two field picture in the following way: according to the border picture of lane line
Vegetarian refreshments obtains lane line straight line at place in the first frame lane line image, chooses first on described straight line
The point of interest of quantity, the particle of the second quantity uniformly produced with normal distribution centered by each point of interest;
Boundary pixel point according to the lane line extracted and described particle are in described lane line image
State value, obtains described particle weight in described lane line image;
Weight is set as effective particle more than the particle of the first predetermined threshold value, and judges whether that each is emerging
The weight sum of effective particle of interest point is both less than the second predetermined threshold value, if, it is determined that current vehicle diatom
Disappear, if not, it is determined that current vehicle diatom does not disappears.
Method the most according to claim 1, it is characterised in that described vehicle present position is believed
Breath, including at least one in following information:
The road image information in the described vehicle present position front of described vehicle-mounted camera shooting;
The vehicle mounted guidance image information in described vehicle present position front;
The latitude and longitude information of described vehicle present position.
Method the most according to claim 1 and 2, it is characterised in that described reception network side information
Center send traveling control information, and according to described traveling control information control described vehicle travel after,
Also include:
Receiving the driving recovery message that network side information centre sends, wherein, described driving recovers message and is
Described network side information centre sends when determining that lane line recovers;
Vehicle described in lane detection algorithm controls is used to travel.
Method the most according to claim 1 and 2, it is characterised in that also include:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
5. a controlling device for vehicle running, it is characterised in that include,
Lane line receiver module, for receiving vehicle-mounted camera collection the lane line image sent;
Lane detection module, is used for using lane detection algorithm that described lane line image is carried out track
Line detects, and obtains lane detection result, and described lane detection result represents whether front lane line disappears
Lose;
Information sending module, for when described lane detection result represents that front lane line disappears, controlling
Vehicle processed stops travelling, and sends described vehicle present position information to network side information centre, with
Determine the traveling of described vehicle according to described vehicle present position information for described network side information centre
Control information;
Information receiving module, for receiving the traveling control information that network side information centre sends, and according to
Described traveling control information controls described vehicle and travels;
Described lane detection module, including:
Boundary Extraction unit, for extracting the boundary pixel point of lane line from described lane line image;
State value determines unit, for particle state value in previous frame lane line image is high with two dimension
This random noise is added, and obtains particle state value in described lane line image, and described state value is grain
Son transverse and longitudinal coordinate in lane line image, described particle produces in the first two field picture in the following way:
Boundary pixel point according to lane line obtains lane line straight line at place in the first frame lane line image,
Choose the point of interest of the first quantity on described straight line, uniformly produce with normal distribution centered by each point of interest
The particle of the second raw quantity;
Weight determining unit, exists for the boundary pixel point according to the lane line extracted and described particle
State value in described lane line image, obtains described particle weight in described lane line image;
Judging unit, for weight is set as effective particle more than the particle of the first predetermined threshold value, and sentences
The weight sum of effective particle of disconnected whether each point of interest is both less than the second predetermined threshold value, the most then
Determine current lane heading line off, if not, it is determined that current vehicle diatom does not disappears.
Device the most according to claim 5, it is characterised in that described vehicle present position is believed
Breath, including at least one in following information:
The road image information in the described vehicle present position front of described vehicle-mounted camera shooting;
The vehicle mounted guidance image information in described vehicle present position front;
The latitude and longitude information of described vehicle present position.
7. according to the device described in claim 5 or 6, it is characterised in that described information receiving module,
It is additionally operable to:
The traveling sent in described reception network side information centre controls information, and controls according to described traveling
After information controls described vehicle traveling, receive the driving recovery message that network side information centre sends, its
In, described driving recovers the message transmission when determining that lane line recovers that is described network side information centre;
Vehicle described in lane detection algorithm controls is used to travel.
8. according to the device described in claim 5 or 6, it is characterised in that described information sending module,
It is additionally operable to:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent instruction vehicle front has barrier, then control vehicle and stop travelling,
And send described vehicle present position information to network side information centre, for described network side information
According to described vehicle present position information, center determines that the traveling of described vehicle controls information;
Receive the traveling control information that network side information centre sends, and according to described traveling control information control
Make described vehicle to travel.
9. a vehicle, it is characterised in that include vehicle-mounted camera and intelligent control platform, wherein, institute
State intelligent control platform and include the controlling device for vehicle running described in any one of claim 5-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410390012.XA CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410390012.XA CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104157160A CN104157160A (en) | 2014-11-19 |
CN104157160B true CN104157160B (en) | 2016-08-17 |
Family
ID=51882646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410390012.XA Active CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104157160B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105261224B (en) * | 2015-09-02 | 2017-09-12 | 奇瑞汽车股份有限公司 | Intelligent vehicle control method and apparatus |
CN106203341B (en) * | 2016-07-11 | 2019-05-21 | 百度在线网络技术(北京)有限公司 | A kind of Lane detection method and device of unmanned vehicle |
CN106681318A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Vehicle safety control system and method for lane line detection temporary loss in automatic drive |
CN110177722B (en) * | 2017-01-19 | 2022-07-01 | 本田技研工业株式会社 | Vehicle control system, vehicle control method, and storage medium |
CN106886217B (en) * | 2017-02-24 | 2020-09-08 | 深圳中智卫安机器人技术有限公司 | Autonomous navigation control method and device |
CN108247630B (en) * | 2017-12-01 | 2021-01-05 | 西安电子科技大学 | Mobile robot obstacle avoidance method based on Bayesian network model |
CN110580046B (en) * | 2019-09-12 | 2022-08-16 | 吉利汽车研究院(宁波)有限公司 | Control method and system for unmanned sightseeing vehicle |
CN113954750B (en) * | 2020-07-20 | 2023-12-29 | 深圳市麦道微电子技术有限公司 | Electronic outside mirror system of commercial vehicle and imaging method |
CN113447970B (en) * | 2021-06-28 | 2023-05-23 | 潍柴动力股份有限公司 | Method and device for filling continuous missing data of navigation data and navigation system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001074490A (en) * | 1999-09-03 | 2001-03-23 | Aisin Aw Co Ltd | Navigation apparatus and memory medium |
CN102541061A (en) * | 2012-02-07 | 2012-07-04 | 清华大学 | Micro intelligent vehicle based on visual and auditory information |
CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
CN102862574A (en) * | 2012-09-21 | 2013-01-09 | 上海永畅信息科技有限公司 | Method for realizing active safety of vehicle on the basis of smart phone |
CN103592903A (en) * | 2013-08-18 | 2014-02-19 | 北京联合大学 | Method and system for remote monitoring on intelligent automobile driving test data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI332454B (en) * | 2008-09-10 | 2010-11-01 | Univ Nat Chiao Tung | Intelligent vehicle traffic safety supply system |
-
2014
- 2014-08-08 CN CN201410390012.XA patent/CN104157160B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001074490A (en) * | 1999-09-03 | 2001-03-23 | Aisin Aw Co Ltd | Navigation apparatus and memory medium |
CN102541061A (en) * | 2012-02-07 | 2012-07-04 | 清华大学 | Micro intelligent vehicle based on visual and auditory information |
CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
CN102862574A (en) * | 2012-09-21 | 2013-01-09 | 上海永畅信息科技有限公司 | Method for realizing active safety of vehicle on the basis of smart phone |
CN103592903A (en) * | 2013-08-18 | 2014-02-19 | 北京联合大学 | Method and system for remote monitoring on intelligent automobile driving test data |
Also Published As
Publication number | Publication date |
---|---|
CN104157160A (en) | 2014-11-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104157160B (en) | Vehicle travel control method, device and vehicle | |
US11084494B2 (en) | Method for detecting safety of driving behavior, apparatus, device and storage medium | |
CN110362077B (en) | Unmanned vehicle emergency hedge decision making system, method and medium | |
CN108189838B (en) | A kind of pattern of fusion adaptive cruise curve control method and device | |
CN110007675B (en) | Vehicle automatic driving decision-making system based on driving situation map and training set preparation method based on unmanned aerial vehicle | |
CN104573646B (en) | Chinese herbaceous peony pedestrian detection method and system based on laser radar and binocular camera | |
CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
CN106127107A (en) | The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges | |
CN103786729B (en) | lane recognition method and system | |
WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
CN104616502B (en) | Car license recognition and alignment system based on combination type bus or train route video network | |
CN102541061B (en) | Micro intelligent vehicle based on visual and auditory information | |
CN108537197A (en) | A kind of lane detection prior-warning device and method for early warning based on deep learning | |
CN109460709A (en) | The method of RTG dysopia analyte detection based on the fusion of RGB and D information | |
CN110232837A (en) | A kind of bus or train route collaboration anti-collision early warning system based on V2X | |
CN109733391A (en) | Control method, device, equipment, vehicle and the storage medium of vehicle | |
CN109814520A (en) | System and method for determining the security incident of autonomous vehicle | |
CN108303103A (en) | The determination method and apparatus in target track | |
CN106257242A (en) | For regulating unit and the method for road boundary | |
CN110531376A (en) | Detection of obstacles and tracking for harbour automatic driving vehicle | |
CN109472986A (en) | For determining the existing system and method for traffic control personnel and traffic control signals object | |
CN102222236A (en) | Image processing system and position measurement system | |
CN110531661A (en) | A kind of vehicle is automatically with control method of speeding, device and equipment | |
CN106326866B (en) | Early warning method and device for vehicle collision | |
CN110458050B (en) | Vehicle cut-in detection method and device based on vehicle-mounted video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |