CN109460739A - Method for detecting lane lines and device - Google Patents
Method for detecting lane lines and device Download PDFInfo
- Publication number
- CN109460739A CN109460739A CN201811355962.3A CN201811355962A CN109460739A CN 109460739 A CN109460739 A CN 109460739A CN 201811355962 A CN201811355962 A CN 201811355962A CN 109460739 A CN109460739 A CN 109460739A
- Authority
- CN
- China
- Prior art keywords
- lane line
- line information
- vehicle
- current
- confidence level
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The present invention relates to vehicle arrangement technical fields, a kind of method for detecting lane lines and device are disclosed, include: the current lane line information of road where obtaining vehicle by image capture device, and the first confidence level of current lane line information is calculated according to current lane line information；The prediction lane line information of road where analyzing vehicle according to the current motion state of vehicle；The second confidence level of prediction lane line information is determined according to the first confidence level；Using current lane line information, the first confidence level, prediction lane line information and the second confidence level as foundation, standard vehicle diatom information is calculated.Implement the embodiment of the present invention, current lane line information can be obtained by image capture device, and prediction lane line information is obtained according to the current motion state of vehicle, and calculate the confidence level for generating each lane line information, the lane line information of standard is calculated according to the confidence level of each lane line information, to improve the accuracy of lane detection.
Description
Technical field
The present invention relates to technical field of vehicle, and in particular to a kind of method for detecting lane lines and device.
Background technique
It is to realize the driving of Vehicular intelligent auxiliary and unpiloted basis to the perception of ambient enviroment in vehicle travel process,
Lane detection technology is to realize the important link of Vehicular intelligent path planning and Decision Control, and realize that lane keeps auxiliary
The auxiliary such as (Lane Keeping Assist, LKA) and lane departure warning (Lane Departure Warning, LDW) drive
Basis.
Existing lane detection technology is usually: the present road scene photo of road where obtaining vehicle, and from working as
Lane line is detected in preceding road scene photo.However, finding in practice process, the lane line in real road is likely to occur
The case where missing, furthermore, it is also possible to occur roadside guardrail similar in color in present road scene photo etc. interfering analyte detection
It is higher so as to cause the error rate of lane detection for lane line, the accuracy of Vehicular intelligent Driving Decision-making is influenced, is caused serious
Security risk.
Summary of the invention
The embodiment of the present invention discloses a kind of method for detecting lane lines and device, is able to ascend the accuracy of lane detection.
First aspect of the embodiment of the present invention discloses a kind of method for detecting lane lines, which comprises
The current lane line information of road where obtaining vehicle by image capture device；
The first confidence level of the current lane line information is calculated according to the current lane line information；
The prediction lane line information of road where analyzing the vehicle according to the current motion state of the vehicle；
The second confidence level of the prediction lane line information is determined according to first confidence level；
It can with the current lane line information, first confidence level, the prediction lane line information and described second
Reliability is foundation, and standard vehicle diatom information is calculated.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described to pass through image capture device
The current lane line information of road where obtaining vehicle, comprising:
The present road image of road where obtaining vehicle by image capture device；
The current lane line information for including in the present road image is identified by image recognition technology；
First confidence level that the current lane line information is calculated according to the current lane line information, packet
It includes:
Using the current lane line information as foundation, the current lane line information is calculated by deep learning algorithm
The first confidence level.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the working as according to the vehicle
The prediction lane line information of road where preceding motion state analyzes the vehicle, comprising:
The current motion state of the vehicle is obtained by Inertial Measurement Unit；
The current posture information of the vehicle is calculated according to the current motion state；
By analyzing the current posture information, the motion profile of the vehicle is predicted；
Using the motion profile as foundation, the prediction lane line information of road where analysis obtains the vehicle.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described credible according to described first
Degree determines the second confidence level of the prediction lane line information, comprising:
Obtain preset standard confidence level；
Calculate the absolute value of the difference of the preset standard confidence level and first confidence level；
The absolute value of the difference is determined as to the second confidence level of the prediction lane line information.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described with the current lane line
Information, first confidence level, the prediction lane line information and second confidence level are foundation, and standard vehicle is calculated
Diatom information, comprising:
It is current lane line equation to be generated according to fitting, and believe with the prediction lane line with the current lane line information
Breath is according to fitting generation prediction lane line equation；
First confidence level is determined as to the first weighted value of the current lane line equation, and credible by described second
Degree is determined as the second weighted value of the prediction lane line equation；
Using first weighted value and second weighted value as foundation, by the current lane line equation and the prediction
Lane line equation is merged, and standard vehicle diatom equation is obtained；
Standard vehicle diatom information is obtained according to the standard vehicle diatom equation.
Second aspect of the embodiment of the present invention discloses a kind of lane detection device, comprising:
Acquiring unit, the current lane line information for road where obtaining vehicle by image capture device；
First computing unit, for being calculated the of the current lane line information according to the current lane line information
One confidence level；
Analytical unit, the prediction lane for road where analyzing the vehicle according to the current motion state of the vehicle
Line information；
Determination unit, for determining the second confidence level of the prediction lane line information according to first confidence level；
Second computing unit, for the current lane line information, first confidence level, prediction lane line letter
Breath and second confidence level are foundation, and standard vehicle diatom information is calculated.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the acquiring unit includes:
First obtains subelement, the present road image for road where obtaining vehicle by image capture device；
Subelement is identified, for identifying the current lane line for including in the present road image by image recognition technology
Information；
First computing unit is calculated the of the current lane line information according to the current lane line information
The mode of one confidence level specifically:
Using the current lane line information as foundation, the current lane line information is calculated by deep learning algorithm
The first confidence level.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the analytical unit includes:
Second obtains subelement, for obtaining the current motion state of the vehicle by Inertial Measurement Unit；
First computation subunit, the current pose for the vehicle to be calculated according to the current motion state are believed
Breath；
Subelement is predicted, for predicting the motion profile of the vehicle by analyzing the current posture information；
Subelement is analyzed, for using the motion profile as foundation, analysis to obtain the pre- measuring car of vehicle place road
Diatom information.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the determination unit includes:
Third obtains subelement, for obtaining preset standard confidence level；
Second computation subunit, for calculating the absolute of the preset standard confidence level and the difference of first confidence level
Value；
First determines subelement, can for the absolute value of the difference to be determined as the second of the prediction lane line information
Reliability.
As an alternative embodiment, in second aspect of the embodiment of the present invention, second computing unit includes:
It is fitted subelement, generates current lane line equation for being fitted with the current lane line information for foundation, and with
The prediction lane line information is that prediction lane line equation is generated according to fitting；
Second determines subelement, for first confidence level to be determined as to the first weight of the current lane line equation
Value, and second confidence level is determined as second weighted value for predicting lane line equation；
Subelement is merged, is used for using first weighted value and second weighted value as foundation, by the current lane
Line equation and the prediction lane line equation are merged, and standard vehicle diatom equation is obtained；
Subelement is obtained, for obtaining standard vehicle diatom information according to the standard vehicle diatom equation.
The third aspect of the embodiment of the present invention discloses a kind of vehicle electronic device, comprising:
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, executes any of first aspect
A kind of some or all of method step.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, the computer readable storage medium
Store program code, wherein said program code includes the part or complete for executing any one method of first aspect
The instruction of portion's step.
The 5th aspect of the embodiment of the present invention discloses a kind of computer program product, when the computer program product is calculating
When being run on machine, so that the computer executes some or all of any one method of first aspect step.
The aspect of the embodiment of the present invention the 6th disclose a kind of using distribution platform, and the application distribution platform is for publication calculating
Machine program product, wherein when the computer program product is run on computers, so that the computer executes first party
Some or all of any one method in face step.
Compared with prior art, the embodiment of the present invention has the advantages that
In the embodiment of the present invention, the current lane line information of road where obtaining vehicle by image capture device, and root
The first confidence level of current lane line information is calculated according to current lane line information；It is analyzed according to the current motion state of vehicle
The prediction lane line information of road where vehicle；The second confidence level of prediction lane line information is determined according to the first confidence level；With
Current lane line information, the first confidence level, prediction lane line information and the second confidence level are foundation, and standard lane is calculated
Line information.As it can be seen that implementing the embodiment of the present invention, current lane line information can be obtained by image capture device, and according to vehicle
Current motion state obtain prediction lane line information, and the confidence level for generating each lane line information is calculated, according to each
The lane line information of standard is calculated in the confidence level of a lane line information, to improve the accuracy of lane detection.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of method for detecting lane lines disclosed by the embodiments of the present invention；
Fig. 2 is the flow diagram of another method for detecting lane lines disclosed by the embodiments of the present invention；
Fig. 3 is the flow diagram of another method for detecting lane lines disclosed by the embodiments of the present invention；
Fig. 4 is a kind of flow diagram of lane detection device disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of another lane detection device disclosed by the embodiments of the present invention；
Fig. 6 is the structural schematic diagram of another lane detection device disclosed by the embodiments of the present invention；
Fig. 7 is a kind of structural schematic diagram of vehicle electronic device disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that term " includes " and " having " and their any changes in the embodiment of the present invention and attached drawing
Shape, it is intended that cover and non-exclusive include.Such as contain the process, method of a series of steps or units, system, product or
Equipment is not limited to listed step or unit, but optionally further comprising the step of not listing or unit or optional
Ground further includes the other step or units intrinsic for these process, methods, product or equipment.
The embodiment of the present invention discloses a kind of method for detecting lane lines and device, is able to ascend the accuracy of lane detection.
It is described in detail separately below.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of method for detecting lane lines disclosed by the embodiments of the present invention.Such as Fig. 1
Shown, which may comprise steps of:
101, the current lane line information of road where lane detection device obtains vehicle by image capture device.
In the embodiment of the present invention, image capture device can be the picture pick-up devices such as vehicle-mounted vidicon, lane detection device
The road image for obtaining vehicle and being presently in road can be shot by image capture device, which can be picture shape
Formula, it is also possible to visual form, in this regard, the embodiment of the present invention is without limitation.Lane detection device can pass through image
Identification technology identifies lane line image from the road image taken, and the lane line image is converted to lane line letter
Breath, as lane line information may include the shape of the position of the lane line identified, the distance away from current vehicle and lane line
The information such as shape.
As an alternative embodiment, lane detection device obtains vehicle place road by image capture device
The mode of current lane line information may comprise steps of:
The present road image of road where lane detection device obtains vehicle by image capture device；
Lane detection device identifies the semantic feature in the current road image by deep learning algorithm；
Lane detection device confirms and the matched target semantic feature of lane line from semantic feature；
Lane detection device is obtained corresponding with target semantic feature in present road image by image Segmentation Technology
Current lane line image；
Lane line image obtains current lane line information before lane detection device is deserved by analysis.
Wherein, implement this embodiment, lane detection device can be by being arranged in taking the photograph for any position on vehicle
As first-class image capture device acquisition vehicle is currently located the present road image of road, wherein can be in present road image
Including but not limited to the corresponding image of the objects such as vehicle, lane line, greenbelt, pedestrian, building, road sign, and it can determine and work as
The semantic feature of the corresponding images of objects such as vehicle, lane line, greenbelt, pedestrian, building, road sign in preceding road image,
Wherein, semantic feature can be understood as mark of the lane detection device to the object generic for including in present road image
Note, lane detection device can determine mark corresponding with lane line by identification mark；Lane detection device can lead to
The convolutional neural networks (Convoltional Neural Networks, CNN) in depth learning algorithm are crossed to present road figure
As being handled, to obtain the corresponding semantic feature of various subject images for including in present road image；Convolutional Neural net
Network may include convolutional layer (Convolution Layer), pond layer (Pooling Layer) and full articulamentum (Fully
Connected Layer), wherein convolutional layer can cooperate with pond layer, and multiple convolution are formed based on present road image
Group, and feature is successively extracted to multiple convolution groups, classified later by several full articulamentums to the feature of extraction, finally
Obtain the semantic feature for including in present road image.There are when lane line on the road locating for the vehicle, image capture device is clapped
It may include the image of lane line in the present road image taken the photograph, therefore lane detection device passes through in deep learning algorithm
It may include the semantic feature of lane line in the semantic feature that convolutional neural networks identify, if lane detection device can be from
The corresponding target semantic feature of lane line is determined in dry semantic feature, and target semantic feature can be determined in current road
Corresponding region in the image of road, the region may be considered the corresponding region of lane line image, and lane detection device can lead to
It crosses image Segmentation Technology and obtains the corresponding current lane line image of target semantic feature in present road image, later according to acquisition
Current lane line image determine current lane line information, and the first confidence level of current lane line information is calculated, thus
The current lane line information and the first confidence level for obtaining lane detection device are more accurate.
102, lane detection device according to current lane line information current lane line information is calculated it is first credible
Degree.
In the embodiment of the present invention, there may be similar to lane line in the road image that is taken due to image capture device
Object or image, it is also possible to there is situations such as lane line missing, therefore the lane line information that lane detection device identifies
There may be errors, and therefore, lane detection device can analyze road image, to identify vehicle from road image
Diatom information, and can use the image capture device of lane detection device or calculate the devices such as mould group to lane line information
It is analyzed, so that the first confidence level of the lane line information is obtained, so that lane detection device is according to first confidence level
The final lane line information for determining standard.
103, the prediction lane line of road where lane detection device analyzes vehicle according to the current motion state of vehicle
Information.
In the embodiment of the present invention, lane detection device can pass through vehicle mileage meter, wheel speed meter and accelerometer etc.
The several motion information for the vehicle that equipment is got simultaneously, then above-mentioned several motion information is combined, to generate vehicle
Current motion state, which may include the current driving speed of vehicle, driving direction and vehicle
The information such as acceleration, in this regard, the embodiment of the present invention is without limitation.Lane detection device can be according to the current driving shape of vehicle
State predicts the lane line of road where vehicle, predicts lane line information to generate, lane detection device predicts road
Lane line can by obtain vehicle driving direction, according to the driving direction of vehicle judge vehicle place road lane line
Direction, can also predict vehicle according to the acceleration of the travel speed of vehicle and vehicle locating in road with the presence or absence of certain special
Lane line, thus obtain more accurately prediction lane line information.
As an alternative embodiment, lane detection device analyzes vehicle institute according to the current motion state of vehicle
It may comprise steps of in the mode of the prediction lane line information of road:
Lane detection device detects the steering state of the turn signal of vehicle, and obtains the current location information of vehicle；
Lane detection device identification target position corresponding with the current location information in pre-stored electronic map；
Lane detection device is detected in the electronic map using the target position as the center of circle, and radius is the area of preset length
The road information in domain；
Current motion state, above-mentioned steering state and the above-mentioned road for the vehicle that lane detection device comprehensive analysis obtains
Road information, the prediction lane line information of road where obtaining vehicle.
Wherein, implement this embodiment, can from vehicle be exclusive rights steering state, vehicle periphery road information with
And the lane line information of road locating for the movement state comprehensive analysis vehicle of vehicle itself, so that lane detection device be made to predict
Obtained prediction lane line information is more accurate.
104, lane detection device determines the second confidence level of prediction lane line information according to the first confidence level.
In the embodiment of the present invention, since lane detection device is needed according to current lane line information and prediction lane line letter
Standard vehicle diatom information is calculated in breath jointly, therefore, can be arranged not to current lane line information and prediction lane line information
With confidence level, and the confidence level of current lane line information and prediction lane line information is there may be being associated with, so that lane line inspection
It is more accurate to survey the standard vehicle diatom information that device generates.Such as, the first confidence level and the second confidence level and can be fixed
Value etc., in this regard, the embodiment of the present invention is without limitation.
For example, the sum of the first confidence level and the second confidence level can be set to 1, and the first confidence level can be set
Value interval be the value interval of [0,1] and the second confidence level may be [0,1]；Assuming that lane detection device root
The first confidence level being calculated according to current lane line information is 0.7, then can pass through the first confidence level for being arranged and the
The sum of two confidence levels subtract the first confidence level, so that it may obtain the second confidence level of prediction lane line information, i.e. the second confidence level
Can be 0.3 (1-0.7=0.3), through the above way can the first confidence level quickly according to current lane line information it is true
Make the second confidence level of prediction lane line information.
105, lane detection device is with current lane line information, the first confidence level, prediction lane line information and second
Confidence level is foundation, and standard vehicle diatom information is calculated.
In the embodiment of the present invention, lane detection device can be according to current lane line information, the first confidence level, pre- measuring car
Diatom information and the second confidence level obtain standard lane line computation formula, so that lane detection device is according to the standard lane
The standard vehicle diatom information that line computation formula is calculated is more accurate, and confidence level is higher.
Optionally, using the plane right-angle coordinate pre-established as foundation, lane detection device can work as according to vehicle
Course variable quantity (dx, dy, d θ) of the preceding driving status estimation vehicle in a certain preset time period, wherein when this is a certain default
Between the initial time of section can be current time；And it can be according to course variable quantity (dx, dy, d θ) and the vehicle of initial time
Road line coordinates (x0, y0) be calculated a certain preset time period end time prediction lane line coordinates (x1, y1), wherein
Predict that the formula of lane line coordinates can be with are as follows:
Lane detection device can will predict lane line coordinates (x1, y1) be fitted, it obtains in prediction lane line information
The prediction lane line formula for including:
Wherein, C0、C1、C2And C3It can be the constant for the prediction lane line formula that fitting generates；
In addition, lane detection device can also be intended according to the current lane line image that image capture device obtains
It closes, generates the current lane line formula for including in current lane line information:
Wherein, C4、C5、C6And C7The constant for the current lane line formula that can be generated for fitting；
Lane detection device can also determine that the first confidence level of current lane line formula is E, it may be considered that prediction
Second confidence level of lane line formula is W=1-E, it is determined that the standard lane line computation formula of standard vehicle diatom information can be with
Are as follows:
In the method depicted in fig. 1, the lane of standard can be calculated according to the confidence level of each lane line information
Line information, to improve the accuracy of lane detection.In addition, implementing method described in Fig. 1, lane detection can be made
The current lane line information and the first confidence level that device obtains are more accurate.In addition, implementing method described in Fig. 1, can make
The prediction lane line information that lane detection device is predicted is more accurate.
Embodiment two
Referring to Fig. 2, Fig. 2 is the flow diagram of another method for detecting lane lines disclosed by the embodiments of the present invention.With
Embodiment one is compared, and the embodiment of the present invention is more detailed to illustrate the process of image capture device acquisition current lane line image
And analyzed to obtain the concrete mode of prediction lane line information according to the current motion state of vehicle, improve current lane line letter
The accuracy rate obtained is ceased, it is also possible that the prediction lane line information arrived is more accurate.As shown in Fig. 2, the lane detection side
Method may comprise steps of:
201, the present road image of road where lane detection device obtains vehicle by image capture device.
In the embodiment of the present invention, image capture device can be positioned only at the front of vehicle, can also be in the surrounding of vehicle
It is both provided with image capture device, in this regard, the embodiment of the present invention is without limitation.If the surrounding of vehicle is arranged in image capture device
When, the panoramic picture of vehicle periphery can be shot by image capture device, so that the lane that lane detection device detects
Line information is more comprehensive.
202, lane detection device identifies the current lane line for including in present road image by image recognition technology
Information.
In the embodiment of the present invention, lane detection device can be believed by color, shape, width of preset lane line etc.
Comprehensive analysis present road image is ceased, so that lane detection device identifies that current lane line is believed from present road image
Breath.Lane detection device can also detect road where vehicle by equipment such as ultrasonic sensor or infrared temperature sensors
Object around road, by analysis detection to object position and present road image in the current lane line image that identifies
Position, by the false lane line information misidentified reject, thus improve lane line information identification accuracy.
203, lane detection device is calculated currently using current lane line information as foundation by deep learning algorithm
First confidence level of lane line information.
In the embodiment of the present invention, due in present road image there may be image similar with lane line, lane
Line detector may recognize false lane line information, sensor can be set in lane detection device, so that the sensing
Device analyzes the current lane line information recognized, obtains the accuracy rate of current lane line information, and true according to accuracy rate
Recognition result can be that false current lane line information is picked by the recognition result of settled preceding lane line information, lane detection device
It removes, so that the higher current lane line information of accuracy rate is obtained, to calculate according to the higher current lane line information of accuracy rate
Obtain the first confidence level.
In the embodiment of the present invention, implement above-mentioned step 201~step 203, vehicle can be obtained by image capture device
The current lane line information of road where, so that the current lane line information and actual conditions that obtain more are coincide, raising is worked as
The accuracy rate of preceding lane line information acquisition.
204, lane detection device obtains the current motion state of vehicle by Inertial Measurement Unit.
In the embodiment of the present invention, Inertial Measurement Unit (Inertial Measurement Unit, IMU) may include list
Axis accelerometer and uniaxial gyro, single-axis accelerometer can detecte acceleration signal of the vehicle in preset coordinate system, single
Axis gyro can detecte angular velocity signal of the vehicle relative to the preset coordinate system, and IMU can measure vehicle in three dimensions
Angular speed and acceleration, and the current motion state of vehicle can be calculated with this.
205, the current posture information of vehicle is calculated according to current motion state for lane detection device.
In the embodiment of the present invention, current posture information may include the driving direction of vehicle, the deflection angle of vehicle and vehicle
The information such as acceleration so that lane detection device can obtain the fortune of vehicle according to the current pose information analysis of vehicle
Dynamic rail mark.
206, lane detection device predicts the motion profile of vehicle by analyzing current posture information.
207, lane detection device is using motion profile as foundation, the prediction lane line letter of road where analysis obtains vehicle
Breath.
In the embodiment of the present invention, due to being limited by traffic law, vehicle needs during traveling with vehicle
Diatom is that cannot arbitrarily press lane line, lane detection device can be according to traveling with the driving trace of the vehicle of prediction
According to the lane line information of road locating for analysis vehicle, to obtain and prediction lane line information.
In the embodiment of the present invention, implement above-mentioned step 204~step 207, it can be accurate by Inertial Measurement Unit
The motion state of vehicle is obtained, and predicts the motion profile of vehicle according to the motion state, thus according to the motion profile of vehicle
The prediction lane line information of road where analysis obtains vehicle, so that obtained prediction lane line information is more accurate.
208, lane detection device determines the second confidence level of prediction lane line information according to the first confidence level.
209, lane detection device is with current lane line information, the first confidence level, prediction lane line information and second
Confidence level is foundation, and standard vehicle diatom information is calculated.
In the method depicted in fig. 2, the lane of standard can be calculated according to the confidence level of each lane line information
Line information, to improve the accuracy of lane detection.In addition, implementing method described in Fig. 2, can make to obtain current
Lane line information and actual conditions are more coincide, and the accuracy rate of current lane line information acquisition is improved.It is retouched in addition, implementing Fig. 2
The method stated, the prediction lane line information of road where vehicle can be obtained according to the motion trail analysis of vehicle, so as to obtain
Prediction lane line information it is more accurate.
Embodiment three
Referring to Fig. 3, Fig. 3 is the flow diagram of another method for detecting lane lines disclosed by the embodiments of the present invention.With
Embodiment one is compared with embodiment two, and the embodiment of the present invention further explains the calculation and standard of the second confidence level
The calculation of lane line information, so that current lane line information and prediction lane line information can also make to mark there are correlation
The calculation of quasi- lane line information is more reasonable.As shown in figure 3, the method for detecting lane lines may comprise steps of:
301, the current lane line information of road where lane detection device obtains vehicle by image capture device
302, lane detection device according to current lane line information current lane line information is calculated it is first credible
Degree.
303, the prediction lane line of road where lane detection device analyzes vehicle according to the current motion state of vehicle
Information.
304, lane detection device obtains preset standard confidence level.
305, lane detection device calculates the absolute value of the difference of preset standard confidence level and the first confidence level.
306, the absolute value of difference is determined as predicting the second confidence level of lane line information by lane detection device.
For example, the preset standard confidence level of lane detection device is 1, the sensor of lane detection device according to
The first confidence level that current lane line information is calculated is 0.7, then standard confidence level and the difference of the first confidence level is exhausted
Can be calculated to value is 0.3, therefore, predicts that the second confidence level of lane line information can be the absolute value 0.3 of the difference.
In the embodiment of the present invention, implement above-mentioned step 304~step 306, can be calculated according to the first confidence level
Second confidence level, so that current lane line information is related to prediction lane line information, so that the standard lane being subsequently generated
Line information is more accurate.
307, lane detection device is foundation fitting generation current lane line equation with current lane line information, and with pre-
Measuring car diatom information is that prediction lane line equation is generated according to fitting.
As an alternative embodiment, lane detection device is to generate to work as according to fitting with current lane line information
Preceding lane line equation, and may include following in a manner of predicting lane line information to generate prediction lane line equation according to fitting
Step:
Lane detection device establishes plane right-angle coordinate；
Lane detection device maps current lane line information in the plane right-angle coordinate, generates and deserves
Corresponding first image of preceding lane line information；
Lane detection device maps prediction lane line information in the plane right-angle coordinate, generates pre- with this
Corresponding second image of measuring car diatom information；
First image is fitted by lane detection device, generates current lane line equation；
Second image is fitted by lane detection device, generates prediction lane line equation.
Wherein, implement this embodiment, it can be in plane right-angle coordinate by current lane line information and pre- measuring car
Diatom information is indicated, so that current lane line information is fitted to current lane line equation and will by lane detection device
The mode that prediction lane line information is fitted to prediction lane line equation is more accurate.
308, the first confidence level is determined as the first weighted value of current lane line equation by lane detection device, and by
Two confidence levels are determined as predicting the second weighted value of lane line equation.
In the embodiment of the present invention, the first weighted value and the second weighted value can be current lane line equation and prediction lane line
Equation ratio shared during generating standard vehicle diatom equation, ratio shared by each lane line equation is with each lane
The confidence level of the corresponding lane line information of line equation is directly proportional, that is to say the higher corresponding lane line of lane line information of confidence level
The ratio that equation accounts in the generating process of standard vehicle diatom equation is bigger, therefore the first weighted value can be credible according to first
Degree determines that the second weighted value can be determined according to the second confidence level.
309, lane detection device is using the first weighted value and the second weighted value as foundation, by current lane line equation and in advance
Measuring car diatom equation is merged, and standard vehicle diatom equation is obtained.
310, lane detection device obtains standard vehicle diatom information according to standard vehicle diatom equation.
In the embodiment of the present invention, which can be mapped in the locating road of vehicle by lane detection device
Lu Zhong can obtain standard vehicle diatom equation in the road by being mapped to standard vehicle diatom equation in the road locating for vehicle
Corresponding standard vehicle diatom information, to keep the standard vehicle diatom information obtained more accurate.
In the embodiment of the present invention, implement above-mentioned step 307~step 310, it can be by current lane line information and prediction
Lane line information is all converted to lane line equation, and generates standard vehicle diatom according to the first confidence level and the second confidence level are comprehensive
Equation obtains standard vehicle diatom information further according to standard vehicle diatom equation, so that the calculation of lane line information is more
Rationally.
In the method depicted in fig. 3, the lane of standard can be calculated according to the confidence level of each lane line information
Line information, to improve the accuracy of lane detection.In addition, method described in implementing Fig. 3, can make current lane line
Information is related to prediction lane line information, so that the standard vehicle diatom information being subsequently generated is more accurate.In addition, implementing figure
Method described in 3 can make lane detection device that current lane line information are fitted to current lane line equation and incited somebody to action
The mode that prediction lane line information is fitted to prediction lane line equation is more accurate.In addition, method described in implementing Fig. 3, it can
So that the calculation of lane line information is more reasonable.
Example IV
Referring to Fig. 4, Fig. 4 is a kind of structural schematic diagram of lane detection device disclosed by the embodiments of the present invention.Such as Fig. 4
Shown, which may include:
Acquiring unit 401, the current lane line information for road where obtaining vehicle by image capture device.
As an alternative embodiment, acquiring unit 401 obtains vehicle place road by image capture device
The mode of current lane line information is specifically as follows:
The present road image of road where obtaining vehicle by image capture device；
The semantic feature in the current road image is identified by deep learning algorithm；
Confirmation and the matched target semantic feature of lane line from semantic feature；
Current lane line image corresponding with target semantic feature in present road image is obtained by image Segmentation Technology；
Lane line image obtains current lane line information before being deserved by analysis.
Wherein, implement this embodiment, can be identified from present road image by image recognition technology current
Lane line image, and the first credible of current lane line information and current lane line information is determined according to current lane line image
Degree, so that the current lane line information and the first confidence level that obtain lane detection device are more accurate.
First computing unit 402, the current lane line information for being obtained according to acquiring unit 401, which is calculated, works as front truck
First confidence level of diatom information.
Analytical unit 403, the prediction lane line for road where analyzing vehicle according to the current motion state of vehicle are believed
Breath.
As an alternative embodiment, analytical unit 403 analyzes vehicle place according to the current motion state of vehicle
The mode of the prediction lane line information of road is specifically as follows:
The steering state of the turn signal of vehicle is detected, and obtains the current location information of vehicle；
The identification target position corresponding with the current location information in pre-stored electronic map；
Using the target position as the center of circle, radius is the road information in the region of preset length for detection in the electronic map；
Current motion state, above-mentioned steering state and the above-mentioned road information for the vehicle that comprehensive analysis obtains, obtain vehicle
The prediction lane line information of road where.
Wherein, implement this embodiment, can from vehicle be exclusive rights steering state, vehicle periphery road information with
And the lane line information of road locating for the movement state comprehensive analysis vehicle of vehicle itself, so that lane detection device be made to predict
Obtained prediction lane line information is more accurate.
Determination unit 404, the first confidence level for being obtained according to the first computing unit 402 determine that analytical unit 403 obtains
Second confidence level of the prediction lane line information arrived.
Second computing unit 405, current lane line information, the first computing unit 402 for being obtained with acquiring unit 401
The prediction lane line information and determination unit 404 that obtained the first confidence level, analytical unit 403 obtain determine second credible
Degree is foundation, and standard vehicle diatom information is calculated.
As it can be seen that implementing lane detection device described in Fig. 4, can be calculated according to the confidence level of each lane line information
The lane line information of standard is obtained, to improve the accuracy of lane detection.In addition, implementing lane line described in Fig. 4
Detection device, the current lane line information and the first confidence level that lane detection device can be made to obtain are more accurate.In addition, real
Lane detection device described in Fig. 4 is applied, the prediction lane line information that lane detection device can be made to predict is more
Accurately.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structural schematic diagram of another lane detection device disclosed by the embodiments of the present invention.Its
In, lane detection device shown in fig. 5 is that lane detection device as shown in Figure 4 optimizes.With shown in Fig. 4
Lane detection device compare, lane detection device shown in fig. 5 is more detailed to illustrate that image capture device acquires
The process of current lane line image and the specific side for analyzing to obtain prediction lane line information according to the current motion state of vehicle
Formula, improves the accuracy rate of current lane line information acquisition, it is also possible that the prediction lane line information arrived is more accurate, Fig. 5
Shown in the acquiring unit 401 of lane detection device may include:
First obtains subelement 4011, the present road figure for road where obtaining vehicle by image capture device
Picture.
Subelement 4012 is identified, for obtaining the current road that subelement 4011 obtains by image recognition technology identification first
The current lane line information for including in the image of road.
First computing unit 402 is calculated the first of the current lane line information according to the current lane line information
The mode of confidence level is specifically as follows:
Using current lane line information as foundation, working as the identification acquisition of subelement 4012, is calculated by deep learning algorithm
First confidence level of preceding lane line information.
In the embodiment of the present invention, the current lane line information of road where vehicle being obtained by image capture device,
So that the current lane line information and actual conditions that obtain more are coincide, the accuracy rate of current lane line information acquisition is improved.
As an alternative embodiment, the analytical unit 403 of lane detection device shown in fig. 5 may include:
Second obtains subelement 4031, for obtaining the current motion state of vehicle by Inertial Measurement Unit；
First computation subunit 4032, the current motion state for being obtained according to the second acquisition subelement 4031 calculate
To the current posture information of vehicle；
It predicts subelement 4033, divides for the current posture information by being obtained to the first computation subunit 4032
Analysis, predicts the motion profile of vehicle；
Subelement 4034 is analyzed, for the motion profile to predict the prediction of subelement 4033 as foundation, analysis obtains vehicle
The prediction lane line information of place road.
Wherein, implement this embodiment, the motion state of vehicle can be accurately obtained by Inertial Measurement Unit, and
The motion profile of vehicle is predicted according to the motion state, thus road where obtaining vehicle according to the motion trail analysis of vehicle
Lane line information is predicted, so that obtained prediction lane line information is more accurate.
As it can be seen that implementing lane detection device described in Fig. 5, can be calculated according to the confidence level of each lane line information
The lane line information of standard is obtained, to improve the accuracy of lane detection.In addition, implementing lane line described in Fig. 5
Detection device can make the current lane line information obtained and actual conditions more coincide, and improve current lane line information acquisition
Accuracy rate.In addition, implementing lane detection device described in Fig. 5, vehicle can be obtained according to the motion trail analysis of vehicle
The prediction lane line information of road where, so that obtained prediction lane line information is more accurate.
Embodiment six
Referring to Fig. 6, Fig. 6 is the structural schematic diagram of another lane detection device disclosed by the embodiments of the present invention.Its
In, lane detection device shown in fig. 6 is that lane detection device as shown in Figure 5 optimizes.With shown in Fig. 5
Lane detection device compare, lane detection device shown in fig. 6 further explains the calculating side of the second confidence level
The calculation of formula and standard vehicle diatom information, so that current lane line information and prediction lane line information is there are correlation,
The calculation of standard vehicle diatom information can also be made more reasonable.The determination unit 404 of lane detection device shown in fig. 6
May include:
Third obtains subelement 4041, for obtaining preset standard confidence level.
Second computation subunit 4042 obtains the preset standard confidence level and that subelement 4041 obtains for calculating third
The absolute value of the difference for the first confidence level that one computing unit 402 obtains.
First determines that subelement 4043, the absolute value of the difference for obtaining the second computation subunit 4042 are determined as point
Second confidence level of the prediction lane line information that analysis subelement 4034 obtains.
In the embodiment of the present invention, the second confidence level can be calculated according to the first confidence level, so that current lane line is believed
Breath is related to prediction lane line information, so that the standard vehicle diatom information being subsequently generated is more accurate.
As an alternative embodiment, the second computing unit 405 of lane detection device shown in fig. 5 can wrap
It includes:
It is fitted subelement 4051, for generating to identify the current lane line information that subelement 4012 obtains according to fitting
Current lane line equation, and prediction lane line is generated according to fitting to analyze the prediction lane line information that subelement 4034 obtains
Equation；
Second determines subelement 4052, and the first confidence level for obtaining the first computing unit 402 is determined as fitting
First weighted value of the current lane line equation that unit 4051 obtains, and it is credible by the second of the first determination determination of subelement 4043
Degree is determined as being fitted the second weighted value of the prediction lane line equation that subelement 4051 obtains；
Subelement 4053 is merged, the first weighted value and the second weighted value for determining with the second determining subelement 4052 are
Foundation will identify the current lane line equation that subelement 4012 obtains and the prediction lane line equation that analysis subelement 4034 obtains
It is merged, obtains standard vehicle diatom equation；
Subelement 4054 is obtained, the standard vehicle diatom equation for obtaining according to fusion subelement 4053 obtains standard lane
Line information.
Wherein, implement this embodiment, current lane line information and prediction lane line information can be all converted to vehicle
Diatom equation, and standard vehicle diatom equation is generated according to the first confidence level and the second confidence level are comprehensive, further according to standard lane
Line equation obtains standard vehicle diatom information, so that the calculation of lane line information is more reasonable.
As an alternative embodiment, fitting subelement 4051 is to generate to work as according to fitting with current lane line information
Preceding lane line equation, and be specifically as follows in a manner of predicting lane line information to generate prediction lane line equation according to fitting:
Establish plane right-angle coordinate；
Current lane line information is mapped in the plane right-angle coordinate, lane line information pair before generating and deserving
The first image answered；
Prediction lane line information is mapped in the plane right-angle coordinate, is generated and the prediction lane line information pair
The second image answered；
First image is fitted, current lane line equation is generated；
Second image is fitted, prediction lane line equation is generated.
Wherein, implement this embodiment, it can be in plane right-angle coordinate by current lane line information and pre- measuring car
Diatom information is indicated, so that current lane line information is fitted to current lane line equation and will by lane detection device
The mode that prediction lane line information is fitted to prediction lane line equation is more accurate.
As it can be seen that implementing lane detection device described in Fig. 6, can be calculated according to the confidence level of each lane line information
The lane line information of standard is obtained, to improve the accuracy of lane detection.In addition, implementing lane line described in Fig. 6
Detection device can make current lane line information related to prediction lane line information, so that the standard lane being subsequently generated
Line information is more accurate.In addition, implementing lane detection device described in Fig. 6, the calculating side of lane line information can be made
Formula is more reasonable.In addition, implementing lane detection device described in Fig. 6, lane detection device can be made current lane
Line information is fitted to current lane line equation and will predict that lane line information is fitted to the mode of prediction lane line equation more
Accurately.
Embodiment seven
Referring to Fig. 7, Fig. 7 is a kind of structural schematic diagram of vehicle electronic device disclosed by the embodiments of the present invention.Such as Fig. 7 institute
Show, which may include:
It is stored with the memory 701 of executable program code；
The processor 702 coupled with memory 701；
Wherein, processor 702 calls the executable program code stored in memory 701, executes the above each method and implements
Some or all of method in example step.
A kind of computer readable storage medium is also disclosed in the embodiment of the present invention, wherein computer-readable recording medium storage
Program code, wherein program code includes for executing some or all of the method in above each method embodiment step
Instruction.
A kind of computer program product is also disclosed in the embodiment of the present invention, wherein when computer program product on computers
When operation, so that computer executes some or all of the method in such as above each method embodiment step.
The embodiment of the present invention is also disclosed a kind of using distribution platform, wherein using distribution platform for issuing computer journey
Sequence product, wherein when computer program product is run on computers, so that computer executes such as the above each method embodiment
In some or all of method step.
It should be understood that " embodiment of the present invention " that specification is mentioned in the whole text mean special characteristic related with embodiment,
Structure or characteristic is included at least one embodiment of the present invention.Therefore, the whole instruction occur everywhere " in the present invention
In embodiment " not necessarily refer to identical embodiment.In addition, these a particular feature, structure, or characteristics can be with any suitable
Mode combines in one or more embodiments.Those skilled in the art should also know that embodiment described in this description
Alternative embodiment is belonged to, related actions and modules are not necessarily necessary for the present invention.
In various embodiments of the present invention, it should be appreciated that magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Successively, the execution sequence of each process should be determined by its function and internal logic the certainty of sequence, without coping with the embodiment of the present invention
Implementation process constitutes any restriction.
In addition, the terms " system " and " network " are often used interchangeably herein.It should be understood that the terms
"and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist three kinds of relationships, such as A and/or B, can
To indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, character "/" herein, typicallys represent
Forward-backward correlation object is a kind of relationship of "or".
In embodiment provided by the present invention, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, can be in one place, or may be distributed over multiple nets
On network unit.Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can integrate in one processing unit, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit
Both it can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in a retrievable memory of computer.Based on this understanding, technical solution of the present invention substantially or
Person says all or part of of the part that contributes to existing technology or the technical solution, can be in the form of software products
It embodies, which is stored in a memory, including several requests are with so that a computer is set
Standby (can be personal computer, server or network equipment etc., specifically can be the processor in computer equipment) executes
Some or all of each embodiment above method of the invention step.
A kind of method for detecting lane lines disclosed by the embodiments of the present invention and device are described in detail above, herein
Apply that a specific example illustrates the principle and implementation of the invention, the explanation of above example is only intended to help
Understand method and its core concept of the invention；At the same time, for those skilled in the art, according to the thought of the present invention,
There will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as to this
The limitation of invention.
Claims (10)
1. a kind of method for detecting lane lines, which is characterized in that the described method includes:
The current lane line information of road where obtaining vehicle by image capture device；
The first confidence level of the current lane line information is calculated according to the current lane line information；
The prediction lane line information of road where analyzing the vehicle according to the current motion state of the vehicle；
The second confidence level of the prediction lane line information is determined according to first confidence level；
With the current lane line information, first confidence level, the prediction lane line information and second confidence level
For foundation, standard vehicle diatom information is calculated.
2. the method according to claim 1, wherein described obtain vehicle place road by image capture device
Current lane line information, comprising:
The present road image of road where obtaining vehicle by image capture device；
The current lane line information for including in the present road image is identified by image recognition technology；
First confidence level that the current lane line information is calculated according to the current lane line information, comprising:
Using the current lane line information as foundation, the of the current lane line information is calculated by deep learning algorithm
One confidence level.
3. method according to claim 1 or 2, which is characterized in that the current motion state according to the vehicle point
The prediction lane line information of road where analysing the vehicle, comprising:
The current motion state of the vehicle is obtained by Inertial Measurement Unit；
The current posture information of the vehicle is calculated according to the current motion state；
By analyzing the current posture information, the motion profile of the vehicle is predicted；
Using the motion profile as foundation, the prediction lane line information of road where analysis obtains the vehicle.
4. described in any item methods according to claim 1~3, which is characterized in that described to be determined according to first confidence level
Second confidence level of the prediction lane line information, comprising:
Obtain preset standard confidence level；
Calculate the absolute value of the difference of the preset standard confidence level and first confidence level；
The absolute value of the difference is determined as to the second confidence level of the prediction lane line information.
5. method according to any one of claims 1 to 4, which is characterized in that described with the current lane line information, institute
Stating the first confidence level, the prediction lane line information and second confidence level is foundation, and standard vehicle diatom letter is calculated
Breath, comprising:
It is to generate current lane line equation according to fitting, and be with the current lane line information with the prediction lane line information
Prediction lane line equation is generated according to fitting；
First confidence level is determined as to the first weighted value of the current lane line equation, and second confidence level is true
It is set to the second weighted value of the prediction lane line equation；
Using first weighted value and second weighted value as foundation, by the current lane line equation and the prediction lane
Line equation is merged, and standard vehicle diatom equation is obtained；
Standard vehicle diatom information is obtained according to the standard vehicle diatom equation.
6. a kind of lane detection device characterized by comprising
Acquiring unit, the current lane line information for road where obtaining vehicle by image capture device；
First computing unit, can for being calculated the first of the current lane line information according to the current lane line information
Reliability；
Analytical unit, the prediction lane line for road where analyzing the vehicle according to the current motion state of the vehicle are believed
Breath；
Determination unit, for determining the second confidence level of the prediction lane line information according to first confidence level；
Second computing unit, for the current lane line information, first confidence level, the prediction lane line information with
And second confidence level is foundation, and standard vehicle diatom information is calculated.
7. lane detection device according to claim 6, which is characterized in that the acquiring unit includes:
First obtains subelement, the present road image for road where obtaining vehicle by image capture device；
Subelement is identified, for identifying the current lane line for including in present road image letter by image recognition technology
Breath；
First computing unit is calculated the first of the current lane line information according to the current lane line information can
The mode of reliability specifically:
Using the current lane line information as foundation, the of the current lane line information is calculated by deep learning algorithm
One confidence level.
8. lane detection device according to claim 6 or 7, which is characterized in that the analytical unit includes:
Second obtains subelement, for obtaining the current motion state of the vehicle by Inertial Measurement Unit；
First computation subunit, for the current posture information of the vehicle to be calculated according to the current motion state；
Subelement is predicted, for predicting the motion profile of the vehicle by analyzing the current posture information；
Subelement is analyzed, for using the motion profile as foundation, analysis to obtain the prediction lane line of vehicle place road
Information.
9. according to the described in any item lane detection devices of claim 6~8, which is characterized in that the determination unit includes:
Third obtains subelement, for obtaining preset standard confidence level；
Second computation subunit, the absolute value of the difference for calculating the preset standard confidence level and first confidence level；
First determines subelement, for the absolute value of the difference to be determined as the second credible of the prediction lane line information
Degree.
10. according to the described in any item lane detection devices of claim 6~9, which is characterized in that second computing unit
Include:
It is fitted subelement, for generating current lane line equation with the current lane line information for foundation fitting, and with described
Predict that lane line information is that prediction lane line equation is generated according to fitting；
Second determines subelement, for first confidence level to be determined as to the first weighted value of the current lane line equation,
And second confidence level is determined as to the second weighted value of the prediction lane line equation；
Subelement is merged, is used for using first weighted value and second weighted value as foundation, by the current lane line side
Journey and the prediction lane line equation are merged, and standard vehicle diatom equation is obtained；
Subelement is obtained, for obtaining standard vehicle diatom information according to the standard vehicle diatom equation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811355962.3A CN109460739A (en) | 2018-11-13 | 2018-11-13 | Method for detecting lane lines and device |
| PCT/CN2019/093439 WO2020098286A1 (en) | 2018-11-13 | 2019-06-28 | Lane line detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811355962.3A CN109460739A (en) | 2018-11-13 | 2018-11-13 | Method for detecting lane lines and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109460739A true CN109460739A (en) | 2019-03-12 |
Family
ID=65610562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811355962.3A Pending CN109460739A (en) | 2018-11-13 | 2018-11-13 | Method for detecting lane lines and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109460739A (en) |
| WO (1) | WO2020098286A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109976348A (en) * | 2019-04-11 | 2019-07-05 | 深圳市大富科技股份有限公司 | A kind of vehicle and its motion control method, equipment, storage medium |
| CN110426051A (en) * | 2019-08-05 | 2019-11-08 | 武汉中海庭数据技术有限公司 | A kind of lane line method for drafting, device and storage medium |
| CN111114544A (en) * | 2019-11-25 | 2020-05-08 | 福瑞泰克智能系统有限公司 | Method and device for determining compensation lane line, movable equipment and storage medium |
| WO2020098286A1 (en) * | 2018-11-13 | 2020-05-22 | 广州小鹏汽车科技有限公司 | Lane line detection method and device |
| CN111291681A (en) * | 2020-02-07 | 2020-06-16 | 北京百度网讯科技有限公司 | Method, device and equipment for detecting lane line change information |
| CN111738207A (en) * | 2020-07-13 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Lane line detection method and device, electronic device and readable storage medium |
| CN111750878A (en) * | 2019-03-28 | 2020-10-09 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN111780744A (en) * | 2020-06-24 | 2020-10-16 | 浙江大华技术股份有限公司 | Mobile robot hybrid navigation method, equipment and storage device |
| CN112115857A (en) * | 2020-09-17 | 2020-12-22 | 福建牧月科技有限公司 | Lane line identification method and device for intelligent automobile, electronic equipment and medium |
| CN112132109A (en) * | 2020-10-10 | 2020-12-25 | 北京百度网讯科技有限公司 | Lane line processing and lane positioning method, device, equipment and storage medium |
| CN112487861A (en) * | 2020-10-27 | 2021-03-12 | 爱驰汽车（上海）有限公司 | Lane line recognition method and device, computing equipment and computer storage medium |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392794B (en) * | 2021-06-28 | 2023-06-02 | 北京百度网讯科技有限公司 | Vehicle line crossing identification method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160046290A1 (en) * | 2014-08-18 | 2016-02-18 | Mobileye Vision Technologies Ltd. | Recognition and prediction of lane constraints and construction areas in navigation |
| CN107021104A (en) * | 2017-04-21 | 2017-08-08 | 天津英创汇智汽车技术有限公司 | A kind of lane identification compensation method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103940434B (en) * | 2014-04-01 | 2017-12-15 | 西安交通大学 | Real-time lane detection system based on monocular vision and inertial navigation unit |
| CN105825173B (en) * | 2016-03-11 | 2019-07-19 | 福州华鹰重工机械有限公司 | General road and lane detection system and method |
| US10207706B2 (en) * | 2016-12-28 | 2019-02-19 | Automotive Research & Testing Center | System for detecting lane line of road and method thereof |
| CN107830869B (en) * | 2017-11-16 | 2020-12-11 | 百度在线网络技术（北京）有限公司 | Information output method and apparatus for vehicle |
| CN107832732B (en) * | 2017-11-24 | 2021-02-26 | 河南理工大学 | Lane line detection method based on treble traversal |
| CN108801286B (en) * | 2018-08-01 | 2021-11-30 | 奇瑞汽车股份有限公司 | Method and device for determining a driving trajectory |
| CN109460739A (en) * | 2018-11-13 | 2019-03-12 | 广州小鹏汽车科技有限公司 | Method for detecting lane lines and device |
-
2018
- 2018-11-13 CN CN201811355962.3A patent/CN109460739A/en active Pending
-
2019
- 2019-06-28 WO PCT/CN2019/093439 patent/WO2020098286A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160046290A1 (en) * | 2014-08-18 | 2016-02-18 | Mobileye Vision Technologies Ltd. | Recognition and prediction of lane constraints and construction areas in navigation |
| CN107021104A (en) * | 2017-04-21 | 2017-08-08 | 天津英创汇智汽车技术有限公司 | A kind of lane identification compensation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 路顺杰: "综合考虑视觉和雷达的车道线检测研究", 《中国优秀硕士学位论文全文数据库（电子期刊），工程科技Ⅱ辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020098286A1 (en) * | 2018-11-13 | 2020-05-22 | 广州小鹏汽车科技有限公司 | Lane line detection method and device |
| CN111750878B (en) * | 2019-03-28 | 2022-06-24 | 北京魔门塔科技有限公司 | Vehicle pose correction method and device |
| CN111750878A (en) * | 2019-03-28 | 2020-10-09 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN109976348A (en) * | 2019-04-11 | 2019-07-05 | 深圳市大富科技股份有限公司 | A kind of vehicle and its motion control method, equipment, storage medium |
| CN110426051B (en) * | 2019-08-05 | 2021-05-18 | 武汉中海庭数据技术有限公司 | Lane line drawing method and device and storage medium |
| CN110426051A (en) * | 2019-08-05 | 2019-11-08 | 武汉中海庭数据技术有限公司 | A kind of lane line method for drafting, device and storage medium |
| CN111114544A (en) * | 2019-11-25 | 2020-05-08 | 福瑞泰克智能系统有限公司 | Method and device for determining compensation lane line, movable equipment and storage medium |
| CN111291681A (en) * | 2020-02-07 | 2020-06-16 | 北京百度网讯科技有限公司 | Method, device and equipment for detecting lane line change information |
| CN111291681B (en) * | 2020-02-07 | 2023-10-20 | 北京百度网讯科技有限公司 | Method, device and equipment for detecting lane change information |
| CN111780744A (en) * | 2020-06-24 | 2020-10-16 | 浙江大华技术股份有限公司 | Mobile robot hybrid navigation method, equipment and storage device |
| CN111780744B (en) * | 2020-06-24 | 2023-12-29 | 浙江华睿科技股份有限公司 | Mobile robot hybrid navigation method, equipment and storage device |
| CN111738207A (en) * | 2020-07-13 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Lane line detection method and device, electronic device and readable storage medium |
| CN112115857A (en) * | 2020-09-17 | 2020-12-22 | 福建牧月科技有限公司 | Lane line identification method and device for intelligent automobile, electronic equipment and medium |
| CN112115857B (en) * | 2020-09-17 | 2024-03-01 | 福建牧月科技有限公司 | Lane line identification method and device of intelligent automobile, electronic equipment and medium |
| CN112132109A (en) * | 2020-10-10 | 2020-12-25 | 北京百度网讯科技有限公司 | Lane line processing and lane positioning method, device, equipment and storage medium |
| CN112487861A (en) * | 2020-10-27 | 2021-03-12 | 爱驰汽车（上海）有限公司 | Lane line recognition method and device, computing equipment and computer storage medium |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020098286A1 (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460739A (en) | Method for detecting lane lines and device | |
| CN111856963B (en) | Parking simulation method and device based on vehicle-mounted looking-around system | |
| JP6658088B2 (en) | Information processing apparatus, program, and map data updating system | |
| KR102483649B1 (en) | Vehicle localization method and vehicle localization apparatus | |
| JP5057183B2 (en) | Reference data generation system and position positioning system for landscape matching | |
| US8428362B2 (en) | Scene matching reference data generation system and position measurement system | |
| CN106767852B (en) | A kind of method, apparatus and equipment generating detection target information | |
| CN106485233A (en) | Drivable region detection method, device and electronic equipment | |
| JP5062497B2 (en) | Vehicle position detection system using landscape image recognition | |
| CN109686031B (en) | Identification following method based on security | |
| US20110320163A1 (en) | Method and system for determining road data | |
| CN106503653A (en) | Area marking method, device and electronic equipment | |
| JP2018092483A (en) | Object recognition device | |
| CN109271857A (en) | A kind of puppet lane line elimination method and device | |
| JP5333860B2 (en) | Vehicle position detection system using landscape image recognition | |
| CN109583416A (en) | Pseudo- Lane detection method and system | |
| Sun et al. | Combining machine learning and dynamic time wrapping for vehicle driving event detection using smartphones | |
| JP7328281B2 (en) | Method and system for predicting the trajectory of a target vehicle in a vehicle's environment | |
| CN107957258A (en) | Pavement marker identification device | |
| JP2006160116A (en) | Vehicle motion estimation device and moving body detection device | |
| CN108960083A (en) | Based on automatic Pilot objective classification method combined of multi-sensor information and system | |
| CN113532499B (en) | Sensor security detection method and device for unmanned system and storage medium | |
| JP6263453B2 (en) | Momentum estimation device and program | |
| JP6115429B2 (en) | Own vehicle position recognition device | |
| CN113011285A (en) | Lane line detection method and device, automatic driving vehicle and readable storage medium |
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: 20190312 |