CN109859278A - The scaling method and calibration system joined outside in-vehicle camera system camera - Google Patents
The scaling method and calibration system joined outside in-vehicle camera system camera Download PDFInfo
- Publication number
- CN109859278A CN109859278A CN201910070089.1A CN201910070089A CN109859278A CN 109859278 A CN109859278 A CN 109859278A CN 201910070089 A CN201910070089 A CN 201910070089A CN 109859278 A CN109859278 A CN 109859278A
- Authority
- CN
- China
- Prior art keywords
- angle
- camera
- point
- lane line
- image information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application provides a kind of scaling method that in-vehicle camera system camera is joined outside, is applied to electronic equipment, comprising: obtains a frame image information, passes through the lane line information in method for detecting lane lines world identification image information；At least two characteristic points are randomly selected on every lane line, calculate coordinate of the characteristic point on world coordinate system, and combining camera height seeks angle modification amount using antitrigonometric function；Angle correction is iterated compensation to Camera extrinsic angle using iterative method, obtains accurate Camera extrinsic angle.The present invention obtains road ahead image by forward sight camera, extract lane line and target vehicle location information in road image, go out the outer ginseng angle of camera using lane line information combination static demarcating result and antitrigonometric function dynamic solution, more accurate Camera extrinsic angle is solved, and distance of the target relative to vehicle body is solved according to the position of target vehicle in image with this.
Description
Technical field
This application involves in-vehicle camera system data process field, in particular to join outside a kind of in-vehicle camera system camera
Scaling method and calibration system.
Background technique
Camera calibration restores most important during the three-dimensional information of object in two dimensional image, several in the imaging of camera
In what model on spatial point and the plane of delineation between picture point there are corresponding relationship, this corresponding relationship is determined by camera parameters
's.Usual video camera includes that outer ginseng is participated in camera, and internal reference is the parameter of video camera itself, and outer ginseng is on camera installation locations
Such as pitch angle, rotation angle and yaw angle.Divide from broadly, camera calibration can be divided into two classes, i.e., traditional camera shooting at present
Machine standardization and camera self-calibration method.
1, traditional camera calibration method is under camera static situation, camera calibration usually pass through traditional calibrating method into
Rower is fixed, this process needs to calculate the inside and outside parameter of camera in the imaging position of the plane of delineation using scaling board.This side
The shortcomings that method is to be only used for the opposing stationary environment of camera, is difficult to realize in many application scenarios.For example, in in-vehicle camera
In system, realize that target position is estimated using vision, since vehicle can generate vibration in driving process is due to road, from
And will lead to Camera extrinsic and change, and then influence camera coordinate system and world coordinate system transition matrix, at this time if
Camera is not carried out real-time calibration, can further influence the accuracy of target range position, it is difficult to safely and effectively navigate
Decision.
2, camera self-calibration method, this method are demarcated without using scaling board.The method of dynamic calibration is advantageous at present
The method demarcated at a distance from parallel lines with end point with vehicle, the condition needed are more.It is only applicable to specified link, is led to
It is lower with property.
It is, therefore, desirable to provide a kind of scaling method that can accurately calculate Camera extrinsic angle, carries video camera reality to obtain
When, accurately outer join angle.
Apply for content
This patent provides a kind of scaling method and calibration system that in-vehicle camera system camera is joined outside, and lane line is utilized and combines instead
Trigonometric function, so that the Camera extrinsic angle solved is more accurate.
This patent provides a kind of scaling method that in-vehicle camera system camera is joined outside, is applied to electronic equipment, comprising:
A frame image information is obtained, the lane line information in image information is identified by method for detecting lane lines；
At least two characteristic points are randomly selected on every lane line, calculate coordinate of the characteristic point on world coordinate system,
And combining camera height seeks angle modification amount using antitrigonometric function；
Angle correction is iterated compensation to Camera extrinsic angle using iterative method, obtains accurate Camera extrinsic angle.
Optionally, the Camera extrinsic angle includes at least one of pitch angle, yaw angle and roll angle.
Optionally, angle correction is iterated compensation to Camera extrinsic angle using iterative method, obtains accurate camera
Outer ginseng angle, including
Using last modified outer ginseng angle as inputting, and it is added with the angle modification amount that this is sought or this is corrected
Outer ginseng angle and export；
Judge whether this modified angle modification amount is less than correction threshold, if then completing this step, otherwise continues iteration and mend
It repays.
Optionally, iterative compensation is iterated calculating using Newton method.
Optionally, the amendment step of the pitch angle includes:
Any two points L1, L2 in left-lane line and any point in right-lane line are chosen in current frame image information
R1, and calculate the world coordinates of each point；
It is modified using following formula
；
Wherein,Pitch angle angle when correcting for the i-th in current frame image information, h is camera heights, and L1.x is
The lateral coordinates value of point L1, L1.y are the longitudinal coordinate value of point L1, and L2.x is the lateral coordinates value of point L2, and L2.y is the vertical of point L2
To coordinate value, R1.x is the lateral coordinates value of point R1, and R1.y is the longitudinal coordinate value of point R1.
Optionally, it is also further corrected using Optic flow information after pitch angle iterated revision, comprising:
Target identification is carried out in this frame image information, and chooses the coordinate of at least one trace point of target, is believed by light stream
Breath acquires coordinate of the trace point in next frame image information, forms one group of trace point group；
The pixel distance ratio between multiple groups trace point group is calculated, and takes in-between value S；
By trace point pixel distance than in median S and current frame image information at a distance from target, using aperture at
As principle calculates the distance of next frame image information, while target range is calculated according to Camera extrinsic goniometer；
Pitch angle is modified by following formula using iterative method
；
WhenWithDifference be less than correction threshold when, amendment terminates.
Optionally, the amendment step of the yaw angle includes:
Any two points L1, L2 in left-lane line and any two points in right-lane line are chosen in current frame image information
R1, R2, and calculate the world coordinates of each point；
It is modified using following formula
；
Wherein,Yaw angle angle when correcting for the i-th in current frame image information, L1.x are that the lateral of point L1 is sat
Scale value, L1.y are the longitudinal coordinate value of point L1, and L2.x is the lateral coordinates value of point L2, and L2.y is the longitudinal coordinate value of point L2,
R1.x is the lateral coordinates value of point R1, and R1.y is the longitudinal coordinate value of point R1, and R2.x is the lateral coordinates value of point R2, and R2.y is a little
The longitudinal coordinate value of R2.
Optionally, the amendment step of the roll angle includes:
Be chosen in current frame image information any point L1 in left-lane line, any point R1 in right-lane line and
Any point N1 of neighbouring lane line, and calculate the world coordinates of each point；
It is modified using following formula
When neighbouring lane line is left neighbouring lane, roll angle correction formula is as follows:
When neighbouring lane line is right neighbouring lane, roll angle correction formula is as follows:
；
Wherein,Roll angle angle when correcting for the i-th in current frame image information, h is camera heights, and L1.x is
The lateral coordinates value of point L1, R1.x are the lateral coordinates value of point R1, and N1.x is the lateral coordinates value of point N1.
Optionally, the correction threshold be 0.01 ° ~ 0.1 ° between any value, further preferably 0.05 °.
In addition, the present invention also provides join calibration system outside a kind of in-vehicle camera, which is characterized in that including
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors；
One or more of application programs are configurable for executing in-vehicle camera system camera described in above-mentioned any one
The step of scaling method of outer ginseng.
From the foregoing, it will be observed that the present invention by forward sight camera obtain road ahead image, extract road image in lane line with
Target vehicle location information goes out the outer of camera using lane line information combination static demarcating result and antitrigonometric function dynamic solution
Join angle, the Optic flow information in image in target vehicle detection frame is extracted with Opencv, using Optic flow information to calculated
Camera extrinsic angle is adjusted, and solves more accurate Camera extrinsic angle, and with this according to target vehicle in image
Position solves distance of the target relative to vehicle body.
Detailed description of the invention
Fig. 1 is the implementation flow chart for the scaling method joined outside in-vehicle camera system camera provided by the embodiments of the present application.
Fig. 2 is the lane line schematic diagram after outer ginseng deviation provided by the embodiments of the present application.
The schematic diagram that characteristic point is chosen when Fig. 3 is provided by the embodiments of the present application is modified.
Fig. 4 is the flow chart provided by the embodiments of the present application that pitch angle is corrected using Optic flow information.
Fig. 5 is the modified schematic diagram of yaw angle provided by the embodiments of the present application.
Fig. 6 is the modified schematic diagram of roll angle provided by the embodiments of the present application.
Fig. 7 is calibration system schematic diagram provided by the embodiments of the present application.
Specific embodiment
The preferred embodiment of the application is described in detail with reference to the accompanying drawing so that the advantages of the application and feature more
It is easily readily appreciated by one skilled in the art, to make apparent define to the protection scope of the application.
Referring to Fig. 1, showing the scaling method joined outside in-vehicle camera system camera provided by the embodiments of the present application in figure
Implementation process.
The scaling method joined outside the in-vehicle camera system camera is applied to electronic equipment, which can be to be installed on
Vehicle electronic device on automobile.The vehicle electronic device may include lane detection module, world coordinates conversion module and
Iterate to calculate correction module.
The lane detection module lane line feature in current frame image for identification, and to lane line carry out identification and
Label is calculated for subsequent correction.
The world coordinates conversion module is used to current frame image information being converted into world three dimensional from planar two dimensional coordinate to sit
Mark.
The iterative calculation correction module is used to calculate the image information being converted into after three-dimensional coordinate amendment Current camera
Outer ginseng angle, make its complete calibration.
Referring to Fig. 1, showing the scaling method joined outside in-vehicle camera system camera provided by the embodiments of the present application in figure
Implementation process.
As shown in Figure 1, the scaling method joined outside a kind of in-vehicle camera system camera, is applied in electronic equipment, the electronics
Equipment can be electronic equipment described in embodiment as above, this method comprises:
101, a frame image information is obtained, the lane line information in image information is identified by method for detecting lane lines.
It should include lane line information, since image information is by being arranged in the monocular phase of front side in the frame image information
Machine obtains, can also be as needed to neighbouring vehicle during identification usually other than identification left-lane and right lane information
The lane line in road is identified.
There is error simultaneously in order to avoid demarcating for the first time, it is 0 that Camera extrinsic angle is assigned initial value automatically by system.Calculating phase
Before the amendment joined outside machine, system can once be calculated Camera extrinsic by way of static demarcating, so that it is determined that its phase
The information such as machine height, modified this patent institute emphasis includes pitch angle, yaw angle and roll angle.
Wherein, pitch angle is worth being the angle between camera shooting direction and horizontal plane, and yaw angle is camera shooting direction
With the angle of perpendicular, roll angle is then camera using its shooting direction as the rotation angle in axle center.
These three Camera extrinsics by image information from during two-dimensional coordinate system is converted to three-dimensional world coordinate system
Important role is arrived.Under the three-dimensional world coordinate system directly obtained by simple static calibration without amendment, lane
Line will appear following several situations, as shown in Figure 2.
When deviation occur in three kinds of Camera extrinsics that Fig. 2 illustrates this patent, lane line occurs after image information conversion
Deviation situation.Wherein if pitch angle is bigger than normal or less than normal, lane line shows as shown in the figure " interior in world coordinate system
Eight " or " outer eight " shape, such as Fig. 2 (a).Equally when yaw angle is incorrect, lane line middle line can be tilted to a side, be sat in the world
The state such as parallelogram is formed in mark system, such as Fig. 2 (b).When roll angle is incorrect, then its two vehicle in world coordinate system
Road width can be unequal, such as Fig. 2 (c).
Only when Camera extrinsic angle is all correct, lane line just can be simultaneously when image coordinate is projected to world coordinates
There is the case where " parallel ", " vertical ", " equidistant ".Therefore it can use above-mentioned phenomenon to be modified Camera extrinsic angle, directly
Meet three cases above to lane line projection result, i.e. " parallel ", " vertical ", " equidistant ".
102, at least two characteristic points are randomly selected on every lane line, calculate the characteristic point on world coordinate system
Coordinate, and combining camera height seeks angle modification amount using antitrigonometric function.
Wherein, during the selection of characteristic point, can preferably choose the marginal portion of lane line, due to surrounding
It is capable of forming.By image characteristic point from two-dimensional assemblage be world coordinate system method there are many kinds of, the emphasis of this patent exists
It carries out outer ginseng angle to camera in the world coordinate system by completing conversion to seek, therefore this patent is not to the conversion of coordinate system
It is repeated.In some embodiments, conversion method can with but be not limited only to take FPR model (Fast Perspective
Removal quickly goes to have an X-rayed) it is converted.
Wherein, the acquisition of camera heights is also possible to diversified forms, and the preset condition of this patent is that camera heights are
Know, since camera heights are relative constant in the process of running, can by but be not limited only to carry out using in a manner of static demarcating
It is quickly obtained, to reduce the overall calculation amount of system.
In this patent embodiment, modified Camera extrinsic is angle parameter, therefore correction amount is also angle parameter.It is repaired
Positive basic principle is by the coordinate position between random character point each in left-lane, right lane and/or adjacent lane line
Suitable trigonometric function relationship is found in relationship, calculates itself and the deviation under ideal operating condition, and further to triangle letter
Number relationship carries out antitrigonometric function processing, calculates corresponding angle modification amount.Angle modification amount is carried out by antitrigonometric function
Calculating involved in calculation amount it is smaller relative to other calculations, and data conversion step is few, can simply directly
Ground obtains.
103, angle correction is iterated compensation to Camera extrinsic angle using iterative method, obtains accurate Camera extrinsic
Angle.
Wherein, in this patent embodiment, iterative method is preferably using Newton iteration method.It exports preceding primary calculating
Parameter carries out a corrected Calculation as current modified input parameter, this time is being calculated to the parameter of output as next
The secondary input parameter calculated of resting and reorganizing.To make outer ginseng angle gradually approach exact value.
In order to reduce calculation amount, by the preceding primary Camera extrinsic angle for calculating acquisition and can all work as after each corrected Calculation
The preceding resulting Camera extrinsic angle of calculating carries out that difference is asked to obtain corrected parameter, when the two difference is less than preset correction threshold,
Then determine that amendment is completed.It should be understood that the difference is every time modified correction amount, every frame image only needs under normal conditions
Condition can be met by carrying out the interative computation no more than 10 times.
In some embodiments, the amendment step of pitch angle includes following sub-step.
Fig. 3 is referred to, the schematic diagram that characteristic point is chosen when being modified by this patent embodiment is illustrated.
As shown in figure 3, in current frame image information, by being chosen in left-lane line in the world coordinate system after conversion
Any point R1 on any two points L1, L2 and right-lane line.Wherein,It is repaired for the i-th in current frame image information
The pitch angle angle of timing, h are camera heights, and L1.x is the lateral coordinates value of point L1, and L1.y is the longitudinal coordinate value of point L1,
L2.x is the lateral coordinates value of point L2, and L2.y is the longitudinal coordinate value of point L2, and R1.x is the lateral coordinates value of point R1, and R1.y is a little
The longitudinal coordinate value of R1.
Theoretically, when deviation occurs in pitch angle, it will appear the not parallel situation of lane line after converting world coordinate system,
It, at this time can be opposite with the angle of deviation according to the trigonometric function relationship between selected characteristic point such as splayed or herringbone
It answers, and in pitch angle makeover process, correction amount is then the angle of deviation, therefore after only needing to obtain the world coordinates of characteristic point,
Certain calculate both it is known that the deviation of current pitch angle is carried out to world coordinates.
The optional embodiment of the present invention is modified pitch angle using following formula
Wherein,Striked is pitch angle deviation value, works as pitch angle
When closer to perfect condition, all lane lines then more level off in parallel, at this time two characteristic points on selected left-lane
Abscissa is then about close, and its difference from the abscissa of characteristic point on right lane then with it is more close, pitch angle about close to ideal value,
I.e. 0 degree.
For example, when two lane lines are parallel,, it is then about 0 that antitrigonometric function, which then seeks out the result come,
It does not need to correct；And when two lane lines about close to it is vertical when,, correction amount is then bigger.
In some embodiments, it in order to reduce calculation amount, can usually be regarded as when correction amount is less than certain threshold value
Amendment is completed, correction threshold selected by the present embodiment is any value between 0.01 ° ~ 0.1 °, may further be preferably
0.05°.I.e. when correction amount is less than 0.05 °, that is, it is judged to completing to correct, current outer ginseng angle is exported.
In addition,It then indicates amendment step-length, is adapted with camera heights h.
In some embodiments, in order to further correct pitch angle, can also after the completion of above-mentioned pitch angle amendment step after
It is continuous further to be corrected using Optic flow information.
Referring to Fig. 4, shown in figure this patent embodiment offer further correct pitch angle using Optic flow information
Flow chart.
As shown in figure 4, also further correcting using Optic flow information after the pitch angle iterated revision and including:
401, target identification is carried out in this frame image information, and chooses the coordinate of at least one trace point of target, passes through light
Stream information acquires coordinate of the trace point in next frame image information, forms one group of trace point group.
Wherein the method for target identification can be the modes such as logical characteristic image identification, artificial intelligence identification and precisely be known
Not, the characteristic point of combining target carries out profile calculating, the final range for determining target.For example, when objects ahead is vehicle,
It selects suitable characteristic point as trace point by identifying to vehicle's contour, while in its profile, and calculates its seat
Mark information.
After determining the trace point, next frame image information is obtained, while finding trace point in this frame image information
Coordinate position.One group of trace point group is collectively formed by the trace point found in upper and lower two frame.The phase of two trace points in trace point group
Position is then reflected in reality
For example, by the characteristic of light stream it is found that the trace point between upper and lower two frame is same point on realistic objective vehicle, in other words
Two tracking in two frames up and down can be obtained there is no variation in position of two trace points on target vehicle in upper and lower two frame
Point horizontal width in real life is equal, it is assumed that and the real width between two trace points is W, camera focus f,,It is wide for two trace points pixel that horizontal direction occupies in image between upper and lower two frame,,For upper and lower two frames target
The distance of vehicle.Assuming that pixel of the S between upper and lower two frame is wide,The ratio between, it is available as inferior by pinhole imaging system principle
Formula:
。
402, the pixel distance ratio between multiple groups trace point group is calculated, and takes in-between value S.
The case where there may be certain trace point matching errors when in view of light stream matching, in order to remove the feelings of matching error
Condition, this method, which uses, takes N group trace point group to take its median for the wide ratio of the pixel of upper and lower two frame, to improve the accuracy of algorithm.
In this patent embodiment, in order to reduce noise, the information of every group of two trace points of N group can be taken to be compared at random, found out
Distance ratio between N group trace point pixel between lower two frames, and take its intermediate value S.Preferential relation is
403, by trace point pixel distance than in median S and current frame image information at a distance from target, utilization is small
Borescopic imaging principle calculates the distance of next frame image information, while target range is calculated according to Camera extrinsic goniometer。
404, pitch angle is modified by following formula using iterative method
。
405, it is not calculated using above-mentioned formula and once correction threshold is compared, until working asWithDifference
When less than correction threshold,Substantially approachAdjustment terminates, whereinFor camera pitch angle.
The modified schematic diagram of yaw angle is carried out by this patent embodiment referring to Fig. 5, illustrating in figure.
In some embodiments, as shown in figure 5, in current frame image information, by being selected in the world coordinate system after conversion
Take any two points L1, L2 in left-lane line and any two points R1, R2 in right-lane line.Wherein,For present frame
Yaw angle angle when i-th in image information is corrected, L1.x are the lateral coordinates value of point L1, and L1.y is that the longitudinal of point L1 sits
Scale value, L2.x are the lateral coordinates value of point L2, and L2.y is the longitudinal coordinate value of point L2, and R1.x is the lateral coordinates value of point R1,
R1.y is the longitudinal coordinate value of point R1, and R2.x is the lateral coordinates value of point R2, and R2.y is the longitudinal coordinate value of point R2.
Theoretically, when deviation occurs in yaw angle, it will appear the case where lane line tilts after converting world coordinate system, i.e.,
Can integrally be tilted to the left or it is whole be tilted to the right, at this time according to the trigonometric function relationship between selected characteristic point can with it is inclined
Declinate is corresponding, and in yaw angle makeover process, correction amount is then the angle of deviation, therefore is only needed the world coordinates of characteristic point
After acquisition, certain calculate both it is known that the deviation of current pitch angle is carried out to world coordinates.
The optional embodiment of the present invention is modified yaw angle using following formula
。
Wherein, striked is with the tilt angle of the midpoint line of the midpoint of R1 and L1, R2 and L2, when yaw angle more connects
When nearly perfect condition, all lane lines then more level off to vertically, and the middle line of selected characteristic point also will be close to vertically.
For example, when yaw angle is accurate,, antitrigonometric function then seek out come result
Then it is about 0, that is, does not need to correct；And when two lane lines about close to it is vertical when,, correction amount is then
It is bigger.
When correcting yaw angle, it should be noted that when the parallel lane line of vehicle drives amendment pitch angle, yaw angle with
Otherwise roll angle is only adjusted pitch angle and roll angle.
In some embodiments, it may appear that the case where pitch angle and yaw angle are corrected simultaneously, therefore thing needs exist in the two
During amendment, while meeting pitching angle correction and yawing angle correction and being respectively less than correction threshold, just determines that amendment step is completed.
The modified schematic diagram of roll angle is carried out by this patent embodiment referring to Fig. 6, illustrating in figure.
In some embodiments, as shown in fig. 6, in the corrected Calculation of roll angle, need to identify three in image information
Lane line is the lane line of the left-lane line of current lane, right-lane line and neighbouring lane respectively.If a left side for current lane
There are at least one lanes for side, then can the left-lane line by left side adjacent to lane regard neighbouring lane line；Similarly, if worked as
There are at least one lanes on the right side in preceding lane, then can the right-lane line by right side adjacent to lane regard neighbouring lane line；Such as
When at least one lane is all deposited in fruit two sides, then one is randomly selected.
L ', R ', N ' in figure are respectively a bit of the lane line on practical road surface, and L1, R1, N1 are then respectively to join outside
On the lane line obtained under angle calculation a bit, angle roll between solid line and dotted line is roll angle.On this basis, into
The following antitrigonometric function processing of row.
Any point L1 in left-lane line, any point R1 in right-lane line are chosen in current frame image information
And any point N1 of neighbouring lane line, and calculate the world coordinates of each point.In calculating process, it is only necessary to know three points
Abscissa.Wherein,Roll angle angle when correcting for the i-th in current frame image information, h are that camera is high
Degree, L1.x are the lateral coordinates value of point L1, and R1.x is the lateral coordinates value of point R1, and N1.x is the lateral coordinates value of point N1.
When being modified using formula, need to consider the neighbouring lane orientation of current lane.
When neighbouring lane line is left neighbouring lane, roll angle correction formula is as follows:
。
When neighbouring lane line is right neighbouring lane, roll angle correction formula is as follows:
。
Wherein, above-mentioned formula has done certain approximate setting, due to roll angle under normal circumstances would generally within 5 °,
Under the angle, the practical lane width in lane differs smaller with calibrated and calculated lane width where camera, therefore can do as above
Approximation is assert:
1, think that the current lane width come out by outer ginseng angle calculation is practical lane width.
2, camera height can also be approximately considered always perpendicular to road surface.
Based on above-mentioned two approximate setting, it is known that be in roll angle makeover process be actually only to neighbouring lane
Width is modified, and by taking Fig. 6 as an example, the neighbouring lane that Fig. 6 is illustrated is right neighbouring lane, at this time because applying right neighbouring lane
Roll angle correction formula.
It is actually to be directed to two different angles to go to calculate neighbouring lane there are two antitrigonometric functions in formula
With the angle of camera this line and vertical direction.
This patent embodiment is specifically calculated using the antitrigonometric function for being tangent, it is believed that projection of the camera on road surface
For coordinate origin.
Wherein, when roll angle is correct, the neighbouring lane line N1 abscissa calculated can be horizontal with practical lane line N '
Coordinate is equal.And the N1 abscissa calculated is directly acquired as obtained by calibrated and calculated, i.e.,.It should be equal to
R1 abscissa adds a lane line width, i.e.,。
Therefore, in the accurate situation of roll angle,.If there is roll angle inaccuracy,
It will appear, the difference for the antitrigonometric function result that the two is found out at this time is correction amount.
During doing iterative compensation, this correction amount can iterate to calculate number and increase and reduce, final to meet amendment
The amendment of roll angle is completed in the restriction of threshold value.
Referring to Fig. 7, illustrating the architecture principle figure by this patent embodiment calibration system in figure.
As shown in fig. 7, ginseng calibration system includes outside the in-vehicle camera
One or more processors, memory and one or more application program, wherein one or more of application program quilts
It stores in memory and is configured as being executed by one or more of processors.
One or more application program is configurable for ginseng outside in-vehicle camera system camera disclosed in above-described embodiment
The step of scaling method.
In some embodiments, which further includes forward sight monocular cam, and the monocular cam is for obtaining
Take the image information of vehicle front.
Road ahead is obtained by forward sight camera from the foregoing, it will be observed that joining scaling method and system outside in-vehicle camera of the invention
Image extracts lane line and target vehicle location information in road image, using lane line information combination static demarcating result with
Antitrigonometric function dynamic solution goes out the outer ginseng angle of camera, extracts the light stream in image in target vehicle detection frame with Opencv
Information is adjusted calculated Camera extrinsic angle using Optic flow information, solves more accurate Camera extrinsic angle,
And distance of the target relative to vehicle body is solved according to the position of target vehicle in image with this.
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 may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
In the embodiment of the present application, join one of calibration system and foregoing embodiments in-vehicle camera system phase outside in-vehicle camera
The scaling method joined outside machine belongs to same design, and the in-vehicle camera system can be run on calibration system by joining outside in-vehicle camera
Either offer method step, specific implementation process are detailed in in-vehicle camera system phase in the scaling method embodiment of Camera extrinsic
The scaling method embodiment joined outside machine, and the alternative embodiment of the application can be formed using any combination, details are not described herein again.
Presently filed embodiment is explained in detail above in conjunction with attached drawing, but the application is not limited to above-mentioned implementation
Mode within the knowledge of a person skilled in the art can also be under the premise of not departing from the application objective
Various changes can be made.
Claims (10)
1. the scaling method joined outside a kind of in-vehicle camera system camera is applied to electronic equipment characterized by comprising
A frame image information is obtained, the lane line information in image information is identified by method for detecting lane lines；
At least two characteristic points are randomly selected on every lane line, calculate coordinate of the characteristic point on world coordinate system,
And combining camera height seeks angle modification amount using antitrigonometric function；
Angle correction is iterated compensation to Camera extrinsic angle using iterative method, obtains accurate Camera extrinsic angle.
2. the scaling method joined outside in-vehicle camera system camera as described in claim 1, which is characterized in that outside the camera
Joining angle includes at least one of pitch angle, yaw angle and roll angle.
3. the scaling method joined outside in-vehicle camera system camera as described in claim 1, which is characterized in that will using iterative method
Angle correction is iterated compensation to Camera extrinsic angle, obtains accurate Camera extrinsic angle, including
Using last modified outer ginseng angle as inputting, and it is added with the angle modification amount that this is sought or this is corrected
Outer ginseng angle and export；
Judge whether this modified angle modification amount is less than correction threshold, if then completing this step, otherwise continues iteration and mend
It repays.
4. the scaling method joined outside in-vehicle camera system camera as claimed in claim 4, which is characterized in that iterative compensation uses
Newton method is iterated calculating.
5. the scaling method joined outside in-vehicle camera system camera as claimed in claim 2, which is characterized in that the pitch angle
Amendment step includes:
Any two points L1, L2 in left-lane line and any point in right-lane line are chosen in current frame image information
R1, and calculate the world coordinates of each point；
It is modified using following formula
；
Wherein,Pitch angle angle when correcting for the i-th in current frame image information, h is camera heights, and L1.x is
The lateral coordinates value of point L1, L1.y are the longitudinal coordinate value of point L1, and L2.x is the lateral coordinates value of point L2, and L2.y is the vertical of point L2
To coordinate value, R1.x is the lateral coordinates value of point R1, and R1.y is the longitudinal coordinate value of point R1.
6. the scaling method joined outside in-vehicle camera system camera as claimed in claim 5, which is characterized in that pitch angle iteration is repaired
Just also further corrected using Optic flow information afterwards, comprising:
Target identification is carried out in this frame image information, and chooses the coordinate of at least one trace point of target, is believed by light stream
Breath acquires coordinate of the trace point in next frame image information, forms one group of trace point group；
The pixel distance ratio between multiple groups trace point group is calculated, and takes in-between value S；
By trace point pixel distance than in median S and current frame image information at a distance from target, using aperture at
As principle calculates the distance of next frame image information, while target range is calculated according to Camera extrinsic goniometer；
Pitch angle is modified by following formula using iterative method
；
WhenWithDifference be less than correction threshold when, amendment terminates.
7. the scaling method joined outside in-vehicle camera system camera as claimed in claim 2, which is characterized in that the yaw angle
Amendment step includes:
Any two points L1, L2 in left-lane line and any two points in right-lane line are chosen in current frame image information
R1, R2, and calculate the world coordinates of each point；
It is modified using following formula
；
Wherein,Yaw angle angle when correcting for the i-th in current frame image information, L1.x are that the lateral of point L1 is sat
Scale value, L1.y are the longitudinal coordinate value of point L1, and L2.x is the lateral coordinates value of point L2, and L2.y is the longitudinal coordinate value of point L2,
R1.x is the lateral coordinates value of point R1, and R1.y is the longitudinal coordinate value of point R1, and R2.x is the lateral coordinates value of point R2, and R2.y is a little
The longitudinal coordinate value of R2.
8. the scaling method joined outside in-vehicle camera system camera as claimed in claim 2, which is characterized in that the roll angle
Amendment step includes:
Be chosen in current frame image information any point L1 in left-lane line, any point R1 in right-lane line and
Any point N1 of neighbouring lane line, and calculate the world coordinates of each point；
It is modified using following formula
When neighbouring lane line is left neighbouring lane, roll angle correction formula is as follows:
When neighbouring lane line is right neighbouring lane, roll angle correction formula is as follows:
；
Wherein,Roll angle angle when correcting for the i-th in current frame image information, h is camera heights, and L1.x is a little
The lateral coordinates value of L1, R1.x are the lateral coordinates value of point R1, and N1.x is the lateral coordinates value of point N1.
9. the scaling method joined outside the in-vehicle camera system camera as described in claim 1-8 any one, which is characterized in that
The correction threshold is any value between 0.01 ° ~ 0.1 °.
10. joining calibration system outside a kind of in-vehicle camera, which is characterized in that including
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors；
One or more of application programs are configurable for perform claim and require in-vehicle camera described in any one of 1-9
The step of scaling method joined outside system camera.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910070089.1A CN109859278B (en) | 2019-01-24 | 2019-01-24 | Calibration method and calibration system for camera external parameters of vehicle-mounted camera system |
| PCT/CN2019/098633 WO2020151212A1 (en) | 2019-01-24 | 2019-07-31 | Calibration method for extrinsic camera parameter of on-board camera system, and calibration system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910070089.1A CN109859278B (en) | 2019-01-24 | 2019-01-24 | Calibration method and calibration system for camera external parameters of vehicle-mounted camera system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109859278A true CN109859278A (en) | 2019-06-07 |
| CN109859278B CN109859278B (en) | 2023-09-01 |
Family
ID=66896041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910070089.1A Active CN109859278B (en) | 2019-01-24 | 2019-01-24 | Calibration method and calibration system for camera external parameters of vehicle-mounted camera system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109859278B (en) |
| WO (1) | WO2020151212A1 (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264525A (en) * | 2019-06-13 | 2019-09-20 | 惠州市德赛西威智能交通技术研究院有限公司 | A kind of camera calibration method based on lane line and target vehicle |
| CN110363819A (en) * | 2019-06-25 | 2019-10-22 | 华为技术有限公司 | The method and relevant device that image capture device is demarcated in intelligent automobile |
| CN110378966A (en) * | 2019-06-11 | 2019-10-25 | 北京百度网讯科技有限公司 | Camera extrinsic scaling method, device, computer equipment and storage medium |
| CN110412603A (en) * | 2019-07-22 | 2019-11-05 | 昆山伟宇慧创智能科技有限公司 | A kind of calibrating parameters adaptive updates method calculated for deviation |
| CN110490936A (en) * | 2019-07-15 | 2019-11-22 | 杭州飞步科技有限公司 | Scaling method, device, equipment and the readable storage medium storing program for executing of vehicle camera |
| CN110991232A (en) * | 2019-10-28 | 2020-04-10 | 纵目科技（上海）股份有限公司 | Vehicle position correction method and system, storage medium and terminal |
| CN111223150A (en) * | 2020-01-15 | 2020-06-02 | 电子科技大学 | Vehicle-mounted camera external parameter calibration method based on double vanishing points |
| WO2020151212A1 (en) * | 2019-01-24 | 2020-07-30 | 惠州市德赛西威汽车电子股份有限公司 | Calibration method for extrinsic camera parameter of on-board camera system, and calibration system |
| CN111753605A (en) * | 2019-06-11 | 2020-10-09 | 北京京东尚科信息技术有限公司 | Lane line positioning method and device, electronic equipment and readable medium |
| CN111862234A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862236A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Fixed-focus binocular camera self-calibration method and system |
| CN111862235A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111931630A (en) * | 2020-08-05 | 2020-11-13 | 重庆邮电大学 | Dynamic expression recognition method based on facial feature point data enhancement |
| CN112115968A (en) * | 2020-08-10 | 2020-12-22 | 北京智行者科技有限公司 | Intelligent sweeper garbage identification method and system |
| CN112184821A (en) * | 2019-07-01 | 2021-01-05 | 上海安亭地平线智能交通技术有限公司 | Method and device for adjusting roll angle of camera, storage medium and electronic equipment |
| CN112288821A (en) * | 2019-07-25 | 2021-01-29 | 上海高德威智能交通系统有限公司 | Method and device for calibrating external parameters of camera |
| CN112509054A (en) * | 2020-07-20 | 2021-03-16 | 北京智行者科技有限公司 | Dynamic calibration method for external parameters of camera |
| CN112529966A (en) * | 2020-12-17 | 2021-03-19 | 豪威科技(武汉)有限公司 | On-line calibration method of vehicle-mounted looking-around system and vehicle-mounted looking-around system thereof |
| CN112614192A (en) * | 2020-12-24 | 2021-04-06 | 湖北亿咖通科技有限公司 | On-line calibration method of vehicle-mounted camera and vehicle-mounted information entertainment system |
| CN112800986A (en) * | 2021-02-02 | 2021-05-14 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter calibration method and device, vehicle-mounted terminal and storage medium |
| CN112907678A (en) * | 2021-01-25 | 2021-06-04 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter attitude dynamic estimation method and device and computer equipment |
| CN113033253A (en) * | 2019-12-24 | 2021-06-25 | 北京车和家信息技术有限公司 | Camera calibration method and device |
| CN113313770A (en) * | 2021-06-29 | 2021-08-27 | 智道网联科技(北京)有限公司 | Calibration method and device of automobile data recorder |
| CN113375687A (en) * | 2021-05-12 | 2021-09-10 | 武汉极目智能技术有限公司 | Method, system and device for compensating vanishing points of lane lines based on parallel constraint |
| CN113432620A (en) * | 2021-06-04 | 2021-09-24 | 苏州智加科技有限公司 | Error estimation method, error estimation device, vehicle-mounted terminal and storage medium |
| CN113568533A (en) * | 2021-06-30 | 2021-10-29 | 惠州市德赛西威智能交通技术研究院有限公司 | Automatic generation system for arbitrary-style trajectory line of vehicle-mounted camera |
| CN113674357A (en) * | 2021-08-04 | 2021-11-19 | 禾多科技（北京）有限公司 | Camera external parameter calibration method and device, electronic equipment and computer readable medium |
| CN113706624A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Camera external parameter correction method and device and vehicle-mounted all-round-looking system |
| WO2022247619A1 (en) * | 2021-05-28 | 2022-12-01 | 北京字跳网络技术有限公司 | Image processing method and device, and electronic device |
| WO2023273376A1 (en) * | 2021-06-28 | 2023-01-05 | 所托(杭州)汽车智能设备有限公司 | Self-calibration method for vehicle-mounted bsd camera, device, and storage medium |
| CN116681776A (en) * | 2023-05-30 | 2023-09-01 | 元橡科技（北京）有限公司 | External parameter calibration method and system for binocular camera |
| CN117061719A (en) * | 2023-08-11 | 2023-11-14 | 元橡科技（北京）有限公司 | Parallax correction method for vehicle-mounted binocular camera |
| CN112509054B (en) * | 2020-07-20 | 2024-05-17 | 重庆兰德适普信息科技有限公司 | Camera external parameter dynamic calibration method |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112444798B (en) * | 2020-11-27 | 2024-04-09 | 杭州易现先进科技有限公司 | Method and device for calibrating space-time external parameters of multi-sensor equipment and computer equipment |
| CN112509064A (en) * | 2020-12-22 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for displaying camera calibration progress |
| CN112785653A (en) * | 2020-12-30 | 2021-05-11 | 中山联合汽车技术有限公司 | Vehicle-mounted camera attitude angle calibration method |
| CN113610932A (en) * | 2021-08-20 | 2021-11-05 | 苏州智加科技有限公司 | Binocular camera external parameter calibration method and device |
| CN114046889B (en) * | 2021-11-18 | 2024-04-30 | 佗道医疗科技有限公司 | Automatic calibration method for infrared camera |
| CN114445505A (en) * | 2021-12-28 | 2022-05-06 | 中公高科养护科技股份有限公司 | Camera calibration system and calibration method for road surface detection |
| CN114708333A (en) * | 2022-03-08 | 2022-07-05 | 智道网联科技(北京)有限公司 | Method and device for generating external reference model of automatic calibration camera |
| CN114782549B (en) * | 2022-04-22 | 2023-11-24 | 南京新远见智能科技有限公司 | Camera calibration method and system based on fixed point identification |
| CN114998849B (en) * | 2022-05-27 | 2024-04-16 | 电子科技大学 | Traffic flow element sensing and positioning method based on road-side monocular camera and application thereof |
| CN115079637A (en) * | 2022-06-29 | 2022-09-20 | 歌尔股份有限公司 | Method, device and equipment for establishing workpiece coordinate system and storage medium |
| CN115578470A (en) * | 2022-09-22 | 2023-01-06 | 虹软科技股份有限公司 | Monocular vision positioning method and device, storage medium and electronic equipment |
| CN117036505B (en) * | 2023-08-23 | 2024-03-29 | 长和有盈电子科技(深圳)有限公司 | On-line calibration method and system for vehicle-mounted camera |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110115912A1 (en) * | 2007-08-31 | 2011-05-19 | Valeo Schalter Und Sensoren Gmbh | Method and system for online calibration of a video system |
| JP2013222302A (en) * | 2012-04-16 | 2013-10-28 | Alpine Electronics Inc | Mounting angle correction device for in-vehicle camera and mounting angle correction method |
| CN106558080A (en) * | 2016-11-14 | 2017-04-05 | 天津津航技术物理研究所 | Join on-line proving system and method outside a kind of monocular camera |
| CN106875448A (en) * | 2017-02-16 | 2017-06-20 | 武汉极目智能技术有限公司 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
| CN107133985A (en) * | 2017-04-20 | 2017-09-05 | 常州智行科技有限公司 | A kind of vehicle-mounted vidicon automatic calibration method for the point that disappeared based on lane line |
| US20180286078A1 (en) * | 2016-02-03 | 2018-10-04 | Panasonic Intellectual Property Management Co., Ltd. | Vehicle-mounted camera calibration system |
| CN108898638A (en) * | 2018-06-27 | 2018-11-27 | 江苏大学 | A kind of on-line automatic scaling method of vehicle-mounted camera |
| CN109191531A (en) * | 2018-07-30 | 2019-01-11 | 深圳市艾为智能有限公司 | A kind of automatic outer ginseng scaling method of the rear in-vehicle camera based on lane detection |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101271639B1 (en) * | 2011-12-13 | 2013-06-17 | (주)팜비젼 | A extrinsic parameter calibration method and system for camera on mobile device |
| CN106127787B (en) * | 2016-07-01 | 2019-04-02 | 北京美讯美通信息科技有限公司 | A kind of camera calibration method based on Inverse projection |
| CN106709956B (en) * | 2016-12-30 | 2020-05-15 | 广州汽车集团股份有限公司 | Remote calibration method and system of panoramic image system |
| CN109859278B (en) * | 2019-01-24 | 2023-09-01 | 惠州市德赛西威汽车电子股份有限公司 | Calibration method and calibration system for camera external parameters of vehicle-mounted camera system |
-
2019
- 2019-01-24 CN CN201910070089.1A patent/CN109859278B/en active Active
- 2019-07-31 WO PCT/CN2019/098633 patent/WO2020151212A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110115912A1 (en) * | 2007-08-31 | 2011-05-19 | Valeo Schalter Und Sensoren Gmbh | Method and system for online calibration of a video system |
| JP2013222302A (en) * | 2012-04-16 | 2013-10-28 | Alpine Electronics Inc | Mounting angle correction device for in-vehicle camera and mounting angle correction method |
| US20180286078A1 (en) * | 2016-02-03 | 2018-10-04 | Panasonic Intellectual Property Management Co., Ltd. | Vehicle-mounted camera calibration system |
| CN106558080A (en) * | 2016-11-14 | 2017-04-05 | 天津津航技术物理研究所 | Join on-line proving system and method outside a kind of monocular camera |
| CN106875448A (en) * | 2017-02-16 | 2017-06-20 | 武汉极目智能技术有限公司 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
| CN107133985A (en) * | 2017-04-20 | 2017-09-05 | 常州智行科技有限公司 | A kind of vehicle-mounted vidicon automatic calibration method for the point that disappeared based on lane line |
| CN108898638A (en) * | 2018-06-27 | 2018-11-27 | 江苏大学 | A kind of on-line automatic scaling method of vehicle-mounted camera |
| CN109191531A (en) * | 2018-07-30 | 2019-01-11 | 深圳市艾为智能有限公司 | A kind of automatic outer ginseng scaling method of the rear in-vehicle camera based on lane detection |
Non-Patent Citations (1)
| Title |
|---|
| 陈军等: "基于道路特征的车载相机标定动态补偿算法", 机械工程学报, vol. 46, no. 20, pages 112 - 117 * |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020151212A1 (en) * | 2019-01-24 | 2020-07-30 | 惠州市德赛西威汽车电子股份有限公司 | Calibration method for extrinsic camera parameter of on-board camera system, and calibration system |
| CN110378966A (en) * | 2019-06-11 | 2019-10-25 | 北京百度网讯科技有限公司 | Camera extrinsic scaling method, device, computer equipment and storage medium |
| CN111753605A (en) * | 2019-06-11 | 2020-10-09 | 北京京东尚科信息技术有限公司 | Lane line positioning method and device, electronic equipment and readable medium |
| CN110264525A (en) * | 2019-06-13 | 2019-09-20 | 惠州市德赛西威智能交通技术研究院有限公司 | A kind of camera calibration method based on lane line and target vehicle |
| CN110264525B (en) * | 2019-06-13 | 2021-08-06 | 惠州市德赛西威智能交通技术研究院有限公司 | Camera calibration method based on lane line and target vehicle |
| CN110363819A (en) * | 2019-06-25 | 2019-10-22 | 华为技术有限公司 | The method and relevant device that image capture device is demarcated in intelligent automobile |
| CN110363819B (en) * | 2019-06-25 | 2023-03-03 | 华为技术有限公司 | Method for calibrating image acquisition equipment in intelligent automobile and related equipment |
| CN112184821A (en) * | 2019-07-01 | 2021-01-05 | 上海安亭地平线智能交通技术有限公司 | Method and device for adjusting roll angle of camera, storage medium and electronic equipment |
| CN112184821B (en) * | 2019-07-01 | 2023-03-10 | 上海安亭地平线智能交通技术有限公司 | Method and device for adjusting roll angle of camera, storage medium and electronic equipment |
| CN110490936B (en) * | 2019-07-15 | 2021-09-07 | 杭州飞步科技有限公司 | Calibration method, device and equipment of vehicle camera and readable storage medium |
| CN110490936A (en) * | 2019-07-15 | 2019-11-22 | 杭州飞步科技有限公司 | Scaling method, device, equipment and the readable storage medium storing program for executing of vehicle camera |
| CN110412603A (en) * | 2019-07-22 | 2019-11-05 | 昆山伟宇慧创智能科技有限公司 | A kind of calibrating parameters adaptive updates method calculated for deviation |
| CN112288821B (en) * | 2019-07-25 | 2024-04-23 | 上海高德威智能交通系统有限公司 | Method and device for calibrating external parameters of camera |
| CN112288821A (en) * | 2019-07-25 | 2021-01-29 | 上海高德威智能交通系统有限公司 | Method and device for calibrating external parameters of camera |
| CN110991232B (en) * | 2019-10-28 | 2024-02-13 | 纵目科技（上海）股份有限公司 | Vehicle position correction method and system, storage medium and terminal |
| CN110991232A (en) * | 2019-10-28 | 2020-04-10 | 纵目科技（上海）股份有限公司 | Vehicle position correction method and system, storage medium and terminal |
| CN113033253A (en) * | 2019-12-24 | 2021-06-25 | 北京车和家信息技术有限公司 | Camera calibration method and device |
| CN111223150A (en) * | 2020-01-15 | 2020-06-02 | 电子科技大学 | Vehicle-mounted camera external parameter calibration method based on double vanishing points |
| CN113706624A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Camera external parameter correction method and device and vehicle-mounted all-round-looking system |
| CN112509054B (en) * | 2020-07-20 | 2024-05-17 | 重庆兰德适普信息科技有限公司 | Camera external parameter dynamic calibration method |
| CN112509054A (en) * | 2020-07-20 | 2021-03-16 | 北京智行者科技有限公司 | Dynamic calibration method for external parameters of camera |
| CN111862235A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862235B (en) * | 2020-07-22 | 2023-12-29 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862234B (en) * | 2020-07-22 | 2023-10-20 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862236A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Fixed-focus binocular camera self-calibration method and system |
| CN111862236B (en) * | 2020-07-22 | 2023-10-20 | 中国科学院上海微系统与信息技术研究所 | Self-calibration method and system for fixed-focus binocular camera |
| CN111862234A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111931630A (en) * | 2020-08-05 | 2020-11-13 | 重庆邮电大学 | Dynamic expression recognition method based on facial feature point data enhancement |
| CN111931630B (en) * | 2020-08-05 | 2022-09-09 | 重庆邮电大学 | Dynamic expression recognition method based on facial feature point data enhancement |
| CN112115968A (en) * | 2020-08-10 | 2020-12-22 | 北京智行者科技有限公司 | Intelligent sweeper garbage identification method and system |
| CN112115968B (en) * | 2020-08-10 | 2024-04-19 | 北京智行者科技股份有限公司 | Intelligent sweeper garbage identification method and system |
| CN112529966A (en) * | 2020-12-17 | 2021-03-19 | 豪威科技(武汉)有限公司 | On-line calibration method of vehicle-mounted looking-around system and vehicle-mounted looking-around system thereof |
| CN112529966B (en) * | 2020-12-17 | 2023-09-15 | 豪威科技(武汉)有限公司 | On-line calibration method of vehicle-mounted looking-around system and vehicle-mounted looking-around system thereof |
| CN112614192B (en) * | 2020-12-24 | 2022-05-17 | 亿咖通(湖北)技术有限公司 | On-line calibration method of vehicle-mounted camera and vehicle-mounted information entertainment system |
| CN112614192A (en) * | 2020-12-24 | 2021-04-06 | 湖北亿咖通科技有限公司 | On-line calibration method of vehicle-mounted camera and vehicle-mounted information entertainment system |
| CN112907678A (en) * | 2021-01-25 | 2021-06-04 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter attitude dynamic estimation method and device and computer equipment |
| CN112907678B (en) * | 2021-01-25 | 2022-05-13 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter attitude dynamic estimation method and device and computer equipment |
| CN112800986A (en) * | 2021-02-02 | 2021-05-14 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter calibration method and device, vehicle-mounted terminal and storage medium |
| CN113375687A (en) * | 2021-05-12 | 2021-09-10 | 武汉极目智能技术有限公司 | Method, system and device for compensating vanishing points of lane lines based on parallel constraint |
| CN113375687B (en) * | 2021-05-12 | 2023-06-02 | 武汉极目智能技术有限公司 | Method, system and device for lane line vanishing point compensation based on parallel constraint |
| WO2022247619A1 (en) * | 2021-05-28 | 2022-12-01 | 北京字跳网络技术有限公司 | Image processing method and device, and electronic device |
| CN113432620A (en) * | 2021-06-04 | 2021-09-24 | 苏州智加科技有限公司 | Error estimation method, error estimation device, vehicle-mounted terminal and storage medium |
| CN113432620B (en) * | 2021-06-04 | 2024-04-09 | 苏州智加科技有限公司 | Error estimation method and device, vehicle-mounted terminal and storage medium |
| WO2023273376A1 (en) * | 2021-06-28 | 2023-01-05 | 所托(杭州)汽车智能设备有限公司 | Self-calibration method for vehicle-mounted bsd camera, device, and storage medium |
| CN113313770A (en) * | 2021-06-29 | 2021-08-27 | 智道网联科技(北京)有限公司 | Calibration method and device of automobile data recorder |
| CN113568533A (en) * | 2021-06-30 | 2021-10-29 | 惠州市德赛西威智能交通技术研究院有限公司 | Automatic generation system for arbitrary-style trajectory line of vehicle-mounted camera |
| CN113674357A (en) * | 2021-08-04 | 2021-11-19 | 禾多科技（北京）有限公司 | Camera external parameter calibration method and device, electronic equipment and computer readable medium |
| CN116681776A (en) * | 2023-05-30 | 2023-09-01 | 元橡科技（北京）有限公司 | External parameter calibration method and system for binocular camera |
| CN116681776B (en) * | 2023-05-30 | 2024-02-23 | 元橡科技（北京）有限公司 | External parameter calibration method and system for binocular camera |
| CN117061719A (en) * | 2023-08-11 | 2023-11-14 | 元橡科技（北京）有限公司 | Parallax correction method for vehicle-mounted binocular camera |
| CN117061719B (en) * | 2023-08-11 | 2024-03-08 | 元橡科技（北京）有限公司 | Parallax correction method for vehicle-mounted binocular camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109859278B (en) | 2023-09-01 |
| WO2020151212A1 (en) | 2020-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109859278A (en) | The scaling method and calibration system joined outside in-vehicle camera system camera | |
| CN108805934B (en) | External parameter calibration method and device for vehicle-mounted camera | |
| CN107230218B (en) | Method and apparatus for generating confidence measures for estimates derived from images captured by vehicle-mounted cameras | |
| CN102830793B (en) | Sight tracing and equipment | |
| CN106340044B (en) | Join automatic calibration method and caliberating device outside video camera | |
| US10452938B2 (en) | System and method for pattern detection and camera calibration | |
| CN109816704A (en) | The 3 D information obtaining method and device of object | |
| US9087374B2 (en) | Automatic airview correction method | |
| US20200279387A1 (en) | Light field image rendering method and system for creating see-through effects | |
| CN107679537A (en) | A kind of texture-free spatial target posture algorithm for estimating based on profile point ORB characteristic matchings | |
| CN110264525A (en) | A kind of camera calibration method based on lane line and target vehicle | |
| CN106705849A (en) | Calibration method of linear-structure optical sensor | |
| CN102831601A (en) | Three-dimensional matching method based on union similarity measure and self-adaptive support weighting | |
| CN113327296B (en) | Laser radar and camera online combined calibration method based on depth weighting | |
| US20210287022A1 (en) | Method for estimating a relative position of an object in the surroundings of a vehicle and electronic control unit for a vehicle and vehicle | |
| CN105551020A (en) | Method and device for detecting dimensions of target object | |
| CN108154536A (en) | The camera calibration method of two dimensional surface iteration | |
| CN111105452A (en) | High-low resolution fusion stereo matching method based on binocular vision | |
| CN113744315A (en) | Semi-direct vision odometer based on binocular vision | |
| CN114119749A (en) | Monocular 3D vehicle detection method based on dense association | |
| US8422765B2 (en) | Three-dimensional image analysis system, process device, and method thereof | |
| CN110211190B (en) | Method and device for training camera self-motion parameter estimation model and storage medium | |
| CN116402904A (en) | Combined calibration method based on laser radar inter-camera and monocular camera | |
| CN111738035A (en) | Method, device and equipment for calculating yaw angle of vehicle | |
| CN115761684A (en) | AGV target recognition and attitude angle resolving method and system based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |