CN110400255A - Generation method, system and the vehicle of vehicle panoramic image - Google Patents
Generation method, system and the vehicle of vehicle panoramic image Download PDFInfo
- Publication number
- CN110400255A CN110400255A CN201810380394.6A CN201810380394A CN110400255A CN 110400255 A CN110400255 A CN 110400255A CN 201810380394 A CN201810380394 A CN 201810380394A CN 110400255 A CN110400255 A CN 110400255A
- Authority
- CN
- China
- Prior art keywords
- image
- calibration
- region
- point
- vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000009466 transformation Effects 0.000 claims abstract description 76
- 238000013178 mathematical model Methods 0.000 claims abstract description 67
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 230000000694 effects Effects 0.000 abstract description 15
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 229910003460 diamond Inorganic materials 0.000 description 3
- 239000010432 diamond Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses generation method, system and the vehicles of a kind of vehicle panoramic image, wherein the generation method of vehicle panoramic image includes: the original image that vehicle's surroundings are acquired by multiple cameras；Determine multiple calibration regions in overlapping region in original image based on vehicle's surroundings；Obtain the image pixel point transformation mathematical model of multiple calibration points in calibration region；According to the image pixel point transformation mathematical model of multiple calibration points, the original image of the collected vehicle's surroundings of multiple cameras is transformed into target image respectively；And target image is spliced into panoramic picture.Generation method, system and the vehicle of the vehicle panoramic image of the embodiment of the present invention, so that the image co-registration Du Genggao being spliced into, avoids inconsistent phenomenon, alignment effect is more preferably.
Description
Technical field
The present invention relates to automobile technical field more particularly to a kind of generation method, system and the vehicles of vehicle panoramic image.
Background technique
With the arriving of information age, automobile is also more and more intelligent, is mainly reflected in and is mounted on vehicle drive platform
On car-mounted terminal.Car-mounted terminal can have internet wireless communication, GPS navigation, entertain the multiple functions such as audio-visual, mention for user
Better driving experience is supplied.Wherein, vehicle panoramic imaging function is one of function the most practical.The function can help
User is watched the image of vehicle's surroundings by vehicle displays curtain, eliminates the blind area of vehicle-surroundings during parking,
Make to stop more intuitive, conveniently.However, panoramic picture is all often In made of the image mosaic acquired by multiple cameras
When splicing, identical part needs to carry out at distortion correction and registration between the image of two neighboring camera shooting
Reason.At this time, it may be necessary to use demarcating module.In panoramic picture, demarcating module can be the region of multiple diamond shapes.Calibration when
It waits, usually chooses two vertex up and down of each diamond shape as standard point.Line between two vertex up and down of each diamond shape
All it is parallel, i.e., is all vertical direction.Image will first rotate a certain angle in splicing, be easy to cause level side at this time
Upward stretching causes matching inaccurate, and the image effect finally spliced is deteriorated.
Summary of the invention
The present invention provides generation method, system and the vehicle of a kind of vehicle panoramic image, to solve the above technical problems in
At least one.
The embodiment of the present invention provides a kind of generation method of vehicle panoramic image, comprising:
The original image of vehicle's surroundings is acquired by multiple cameras；
Determine multiple calibration regions in overlapping region in original image based on the vehicle's surroundings；
Obtain the image pixel point transformation mathematical model of multiple calibration points in the calibration region；
According to the image pixel point transformation mathematical model of the multiple calibration point, by the collected vehicle of the multiple camera
The original image of surrounding is transformed into target image respectively；And
The target image is spliced into panoramic picture.
Optionally, the original image of vehicle's surroundings is acquired by multiple cameras；
Determine multiple calibration regions in overlapping region in original image based on the vehicle's surroundings；
Obtain the image pixel point transformation mathematical model of multiple calibration points in the calibration region；
According to the image pixel point transformation mathematical model of the multiple calibration point, by the collected vehicle of the multiple camera
The original image of surrounding is transformed into target image respectively；And
The target image is spliced into panoramic picture.
Optionally, the image pixel point transformation mathematical model of multiple calibration points in the calibration region is obtained, comprising:
The central point in first calibration region and at least two vertex are determined as to the calibration in first calibration region
Point, and the coordinate of the calibration point in first calibration region is obtained, and the seat of the calibration point according to first calibration region
Mark generates the first image pixel point transformation mathematical model of multiple calibration points in first calibration region；
The central point in second calibration region and at least two vertex are determined as to the calibration in second calibration region
Point, and the coordinate of the calibration point in second calibration region is obtained, and the seat of the calibration point according to second calibration region
Mark generates the second image pixel point transformation mathematical model of multiple calibration points in second calibration region；
The central point in third calibration region and at least two vertex are determined as to the calibration in third calibration region
Point, and the coordinate of the calibration point in third calibration region is obtained, and the seat of the calibration point according to third calibration region
Mark generates the third image pixel point transformation mathematical model of multiple calibration points in third calibration region；
The central point in the 4th calibration region and at least two vertex are determined as to the calibration in the 4th calibration region
Point, and the coordinate of the calibration point in the 4th calibration region is obtained, and the seat of the calibration point according to the 4th calibration region
Mark generates the 4th image pixel point transformation mathematical model of multiple calibration points in the 4th calibration region.
Optionally, according to the image pixel point transformation mathematical model of the multiple calibration point, the multiple camera is adopted
The original image of the vehicle's surroundings collected is transformed into target image respectively, comprising:
Using the first image pixel point transformation mathematical model, the forward image and the left-side images are turned respectively
It is changed to the first image and the second image, and the first image and second image are spliced with predetermined angle to generate
First object image；
Using the second image pixel point transformation mathematical model, the forward image and the image right are turned respectively
It is changed to third image and the 4th image, and the third image and the 4th image are spliced with predetermined angle to generate
Second target image；
Using the third image pixel point transformation mathematical model, the rear images and the left-side images are turned respectively
It is changed to the 5th image and the 6th image, and the 5th image and the 6th image are spliced with predetermined angle to generate
Third target image；
Using the 4th image pixel point transformation mathematical model, the rear images and the image right are turned respectively
It is changed to the 7th image and the 8th image, and the 7th image and the 8th image are spliced with predetermined angle to generate
4th target image.
Optionally, the target image is spliced into panoramic picture, comprising:
By the first object image, second target image, the third target image and the 4th target figure
As being spliced, to generate the panoramic picture.
Optionally, the calibration region is polygonal region.
Optionally, method further include:
Obtain the angle information between current vehicle position and predeterminated position；
It is coordinately transformed according to coordinate information of the angle information to multiple calibration regions.
Another embodiment of the present invention provides a kind of generation systems of vehicle panoramic image, comprising:
Multiple cameras, for acquiring the original image of vehicle's surroundings；
Image received device, the original image of the vehicle's surroundings for receiving the multiple camera acquisition；
Image conversion device determines multiple calibration for the overlapping region in the original image based on the vehicle's surroundings
Region, and the image pixel point transformation mathematical model of multiple calibration points in the calibration region is obtained, and according to the multiple
The image pixel point transformation mathematical model of calibration point distinguishes the original image of the collected vehicle's surroundings of the multiple camera
It is transformed into target image；And
Image splicing device, for the target image to be spliced into panoramic picture.
Optionally, the original image of the vehicle's surroundings includes forward image, rear images, left-side images and right part of flg
Picture, described image converting means, is used for:
The first overlapping region between the forward image and the left-side images is obtained, and to first overlapping region
Binary conversion treatment is carried out, with the coordinate information in the first calibration region in determination first overlapping region；
The second overlapping region between the forward image and the image right is obtained, and to second overlapping region
Binary conversion treatment is carried out, with the coordinate information in the second calibration region in determination second overlapping region；
The third overlapping region between the rear images and the left-side images is obtained, and to the third overlapping region
Binary conversion treatment is carried out, with the coordinate information in the third calibration region in the determination third overlapping region；
The 4th overlapping region between the rear images and the image right is obtained, and to the 4th overlapping region
Binary conversion treatment is carried out, with the coordinate information in the 4th calibration region in determination the 4th overlapping region.
Optionally, described image converting means is used for:
The central point in first calibration region and at least two vertex are determined as to the calibration in first calibration region
Point, and the coordinate of the calibration point in first calibration region is obtained, and the seat of the calibration point according to first calibration region
Mark generates the first image pixel point transformation mathematical model of multiple calibration points in first calibration region；
The central point in second calibration region and at least two vertex are determined as to the calibration in second calibration region
Point, and the coordinate of the calibration point in second calibration region is obtained, and the seat of the calibration point according to second calibration region
Mark generates the second image pixel point transformation mathematical model of multiple calibration points in second calibration region；
The central point in third calibration region and at least two vertex are determined as to the calibration in third calibration region
Point, and the coordinate of the calibration point in third calibration region is obtained, and the seat of the calibration point according to third calibration region
Mark generates the third image pixel point transformation mathematical model of multiple calibration points in third calibration region；
The central point in the 4th calibration region and at least two vertex are determined as to the calibration in the 4th calibration region
Point, and the coordinate of the calibration point in the 4th calibration region is obtained, and the seat of the calibration point according to the 4th calibration region
Mark generates the 4th image pixel point transformation mathematical model of multiple calibration points in the 4th calibration region.
Optionally, described image converting means is used for:
Using the first image pixel point transformation mathematical model, the forward image and the left-side images are turned respectively
It is changed to the first image and the second image, and the first image and second image are spliced with predetermined angle to generate
First object image；
Using the second image pixel point transformation mathematical model, the forward image and the image right are turned respectively
It is changed to third image and the 4th image, and the third image and the 4th image are spliced with predetermined angle to generate
Second target image；
Using the third image pixel point transformation mathematical model, the rear images and the left-side images are turned respectively
It is changed to the 5th image and the 6th image, and the 5th image and the 6th image are spliced with predetermined angle to generate
Third target image；
Using the 4th image pixel point transformation mathematical model, the rear images and the image right are turned respectively
It is changed to the 7th image and the 8th image, and the 7th image and the 8th image are spliced with predetermined angle to generate
4th target image.
Optionally, described image splicing apparatus is used for
By the first object image, second target image, the third target image and the 4th target figure
As being spliced, to generate the panoramic picture.
Optionally, the calibration region is polygonal region.
Optionally, described image converting means is also used to:
The angle information between current vehicle position and predeterminated position is obtained, and according to the angle information to multiple calibration
The coordinate information in region is coordinately transformed.
A further embodiment of the present invention provides a kind of vehicle, the generation system including vehicle panoramic image described in a upper embodiment
System.
Technical solution provided in an embodiment of the present invention can include the following benefits:
The original image of vehicle's surroundings is acquired by multiple cameras, and in the original image based on the vehicle's surroundings
Multiple calibration regions are determined in overlapping region, and obtain the image pixel point transformation number of multiple calibration points in the calibration region
Model is learned, and according to the image pixel point transformation mathematical model of the multiple calibration point, the multiple camera is collected
The original image of vehicle's surroundings is transformed into target image respectively, and the target image is spliced into panoramic picture, so that spelling
The image co-registration Du Genggao picked out avoids inconsistent phenomenon, and alignment effect is more preferably.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart of the generation method of vehicle panoramic image according to an embodiment of the invention；
Fig. 2 is the effect diagram of the image calibration of vehicle in the related technology；
Fig. 3 is the effect diagram in determining calibration region according to an embodiment of the invention；
Fig. 4 is the effect diagram of determining transformation mathematical model according to an embodiment of the invention；
Fig. 5 is the effect diagram of the coordinate transform of vehicle according to an embodiment of the invention；
Fig. 6 is the structure chart of the generation system of vehicle panoramic image according to an embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings generation method, system and the vehicle of the vehicle panoramic image of the embodiment of the present invention are described.
Fig. 1 is the flow chart of the generation method of vehicle panoramic image according to an embodiment of the invention.
As shown in Figure 1, the generation method of the vehicle panoramic image includes:
S101 acquires the original image of vehicle's surroundings by multiple cameras.
Currently, more and more automobiles are provided with vehicle panoramic imaging function.The function can help user to stop
During, the image of vehicle's surroundings is watched by vehicle displays curtain, eliminates the blind area of vehicle-surroundings, keeps parking more straight
It sees, conveniently.Specifically, multiple cameras can be installed in the surrounding of vehicle, the image on different directions is acquired by camera,
Image is spliced again, to generate panoramic picture.As shown in Fig. 2, the white rectangle expression vehicle at figure center, the four of vehicle
It is mounted with six cameras, respectively forward and backward, left front, left back, right preceding and right rear camera week.This six camera acquisitions
Image, two adjacent images would generally have the region (splicing regions) of overlapping, and the region of each overlapping can select one
Calibration region (white piece in Fig. 2) calibrates it.When calibration, using the vertex up and down in calibration region as standard point.And
Line between upper and lower vertex is all parallel, i.e., is all the vertical direction in Fig. 2.Image will first rotate certain in splicing
Angle, the stretching being be easy to cause in horizontal direction at this time causes matching inaccurate, and the image effect finally spliced can be deteriorated.
To solve the above-mentioned problems, the present invention proposes a kind of generation method of vehicle panoramic image, can reduce cost
While, improve the effect for generating panoramic picture.
In one embodiment of the invention, multiple cameras can be installed in the surrounding of vehicle, is adopted by multiple cameras
Collect the original image of vehicle's surroundings.Such as: one camera is set in the front of vehicle, to acquire vehicle forward image；In vehicle
Rear be arranged a camera, to acquire rear view of vehicle image；One camera is set in the left side of vehicle, to acquire vehicle left side
Image；One camera is set on the right side of vehicle, to acquire vehicle image right.Certainly, the image on four direction not only limits
It acquires, can also be acquired using more cameras in four cameras.The present embodiment uses four cameras, not only may be used
To save cost, while the operand of processing image can also be reduced.
Multiple calibration regions are determined in S102, the overlapping region in the original image based on vehicle's surroundings.
Wherein, calibration region can be polygonal region.
Specifically, can obtain the first overlapping region between forward image and left-side images, and to the first overlapping region into
Row binary conversion treatment, to determine the coordinate information in the first calibration region in the first overlapping region, so that it is determined that the first calibration out
Region.As shown in figure 3, upper left diamond-shaped area i.e. first demarcates region.
Similarly, the second overlapping region between forward image and image right can be obtained, and the second overlapping region is carried out
Binary conversion treatment, to determine the coordinate information in the second calibration region in the second overlapping region, so that it is determined that the second calibration area out
Domain.As shown in figure 3, the diamond-shaped area in upper right side i.e. second demarcates region.
Similarly, the third overlapping region between rear images and left-side images can be obtained, and third overlapping region is carried out
Binary conversion treatment, to determine the coordinate information in the calibration of the third in third overlapping region region, so that it is determined that third demarcates area out
Domain.As shown in figure 3, the diamond-shaped area of lower left, that is, third demarcates region.
Similarly, the 4th overlapping region between rear images and image right can be obtained, and the 4th overlapping region is carried out
Binary conversion treatment, to determine the coordinate information in the 4th calibration region in the 4th overlapping region, so that it is determined that the 4th calibration area out
Domain.As shown in figure 3, the diamond-shaped area of lower right the i.e. the 4th demarcates region.
S103 obtains the image pixel point transformation mathematical model of multiple calibration points in calibration region.
Specifically, the central point in the first calibration region and at least two vertex can be determined as to the calibration in the first calibration region
Point, and the coordinate of the calibration point in the first calibration region is obtained, and the Coordinate generation the of the calibration point according to the first calibration region
First image pixel point transformation mathematical model of multiple calibration points in one calibration region.
Similarly, the central point in the second calibration region and at least two vertex can be determined as to the calibration in the second calibration region
Point, and the coordinate of the calibration point in the second calibration region is obtained, and the Coordinate generation the of the calibration point according to the second calibration region
Second image pixel point transformation mathematical model of multiple calibration points in two calibration regions.
Similarly, central point and at least two vertex that third can be demarcated to region are determined as the calibration in third calibration region
Point, and the coordinate of the calibration point in third calibration region is obtained, and the Coordinate generation the of the calibration point in region is demarcated according to third
The third image pixel point transformation mathematical model of multiple calibration points in three calibration regions.
Similarly, the central point in the 4th calibration region and at least two vertex can be determined as to the calibration in the 4th calibration region
Point, and the coordinate of the calibration point in the 4th calibration region is obtained, and the Coordinate generation the of the calibration point according to the 4th calibration region
4th image pixel point transformation mathematical model of multiple calibration points in four calibration regions.
It is described in detail by taking upper left first calibration region as an example below.
As shown in figure 4, the white rectangle at figure center is vehicle, it is known that the coordinate of the central point in the first calibration region, first
The length and width in calibration region are respectively W and H, and the rotation angle in the first calibration region is θ, the horizontal line where the vertex to central point A
Distance dA, then the abscissa x of A pointA=W/2-dA/tanθ, the ordinate y of A pointA=H/2+dA.Similarly, B point can be found out
Coordinate.Coordinate based on central point, A point and B point, can determine corresponding transformation mathematical model.Specifically can as formula one to
Formula three indicates.
Formula one:
Formula two:
Formula three:
Wherein, xiFor the abscissa before transformation, yiFor the ordinate before transformation, xi' it is transformed abscissa, yi' it is to become
Ordinate after changing, εxAnd εyFor error factor, Δ is error function, and a is parameter.
To the best panoramic picture of acquisition splicing effect, in the first overlapping region between forward image and left-side images
Image needs perfectly overlap.That is, central point, A point and the B point in calibration region, respectively in distortion correction
Error of coordinate in forward image and left-side images afterwards is minimum, then spliced effect is best.It so, can be to formula one and public affairs
The amendment adjustment that parameter a in formula two is iterated is finally reached error function Δ minimum, realizes that splicing effect is best.
Similarly, the second calibration region, third calibration region and the 4th calibration region are all made of aforesaid way and are handled, this
Place repeats no more.
S104, according to the image pixel point transformation mathematical model of multiple calibration points, by the collected vehicle of multiple cameras
The original image of surrounding is transformed into target image respectively.
Specifically, using the first image pixel point transformation mathematical model, forward image and left-side images are converted respectively
For the first image and the second image, and the first image and the second image are spliced with predetermined angle to generate first object figure
Picture.
Similarly, using the second image pixel point transformation mathematical model, forward image and image right are respectively converted into
Third image and the 4th image, and third image and the 4th image are spliced with predetermined angle to generate the second target figure
Picture.
Similarly, using third image pixel point transformation mathematical model, rear images and left-side images are respectively converted into
5th image and the 6th image, and the 5th image and the 6th image are spliced with predetermined angle to generate third target figure
Picture.
Similarly, using the 4th image pixel point transformation mathematical model, rear images and image right are respectively converted into
7th image and the 8th image, and the 7th image and the 8th image are spliced with predetermined angle to generate the 4th target figure
Picture.
It continues with and is described in detail by taking forward image and left-side images as an example.
Firstly, being rotated based on transformation mathematical model to left-side images, is obtained in left-side images by transformation and demarcate area
Central point, A point and the B point in domain, carry out 3 lines.Meanwhile to central point, A point and the B in the calibration region in forward image
Point also carries out 3 lines.This two lines are spliced, 90 degree of angle between two lines are made.Further, it is also possible to
Equal proportion scales forward image or left-side images, so that the size of the two is mutually matched.
Similarly, the image on other directions is all made of identical mode and handles, and details are not described herein again.
Target image is spliced into panoramic picture by S105.
Specifically, first object image, the second target image, third target image and the 4th target image can be spelled
It connects, to generate panoramic picture.
The generation method of the vehicle panoramic image of the embodiment of the present invention acquires the original of vehicle's surroundings by multiple cameras
Image, and multiple calibration regions are determined in the overlapping region in the original image based on vehicle's surroundings, and obtain calibration region
In multiple calibration points image pixel point transformation mathematical model, and according to the image pixel point transformation mathematical modulo of multiple calibration points
The original image of the collected vehicle's surroundings of multiple cameras is transformed into target image respectively, and target image is spelled by type
It is connected in panoramic picture, so that the image co-registration Du Genggao being spliced into, avoids inconsistent phenomenon, alignment effect is more preferably.
In another embodiment of the present invention, the angle letter between current vehicle position and predeterminated position can also be obtained
Then breath can be coordinately transformed according to coordinate information of the angle information to multiple calibration regions.In embodiment before this,
It is to be described with vehicle in the position of the center of figure.It is also understood that the position of vehicle is located on predeterminated position.And
In fact, the position of vehicle parking, can there is any discrepancy with predeterminated position, i.e., be between current vehicle position and predeterminated position
There is certain angle.And it is corresponding with predeterminated position for demarcating region then.Therefore, if vehicle is not parked in predeterminated position
On, then needs are coordinately transformed before calibration.As shown in figure 5, the lower left corner of predeterminated position is origin O, and it is real
The lower left corner of border current vehicle position is O '.Coordinate transform between the two can be realized by formula four.
Formula four:
X and Y is the transverse and longitudinal coordinate of certain point in the corresponding coordinate system of origin O, and X ' and Y ' are the corresponding coordinate system of origin O '
In certain point transverse and longitudinal coordinate, a is the angle between two coordinate systems, L1And L2Respectively transformation parameter.
After carrying out above-mentioned coordinate transform, the step of determining calibration region can be continued.
In practical applications, it does not need limitation vehicle to be completely coincident with preset fixed parking stall, only need to simply be sat
Mark transformation, can continue subsequent step, more flexible, conveniently.
In order to realize above-described embodiment, the invention also provides a kind of generation system of vehicle panoramic image, Fig. 6 is basis
The structure chart of the generation system of the vehicle panoramic image of one embodiment of the invention, as shown in fig. 6, the device includes multiple camera shootings
First 610, image received device 620, image conversion device 630 and image splicing device 640.
Wherein, multiple cameras 610, for acquiring the original image of vehicle's surroundings.
Image received device 620, the original image of the vehicle's surroundings for receiving multiple camera acquisitions.
Image conversion device 630 determines multiple calibration for the overlapping region in the original image based on vehicle's surroundings
Region, and the image pixel point transformation mathematical model of multiple calibration points in calibration region is obtained, and according to multiple calibration points
The original image of the collected vehicle's surroundings of multiple cameras is transformed into target figure by image pixel point transformation mathematical model respectively
Picture.
Image splicing device 640, for target image to be spliced into panoramic picture.
It should be noted that the explanation of the aforementioned generation method to vehicle panoramic image, is also applied for of the invention real
The generation system of the vehicle panoramic image of example is applied, unpub details in the embodiment of the present invention, details are not described herein.
The generation system of the vehicle panoramic image of the embodiment of the present invention acquires the original of vehicle's surroundings by multiple cameras
Image, and multiple calibration regions are determined in the overlapping region in the original image based on vehicle's surroundings, and obtain calibration region
In multiple calibration points image pixel point transformation mathematical model, and according to the image pixel point transformation mathematical modulo of multiple calibration points
The original image of the collected vehicle's surroundings of multiple cameras is transformed into target image respectively, and target image is spelled by type
It is connected in panoramic picture, so that the image co-registration Du Genggao being spliced into, avoids inconsistent phenomenon, alignment effect is more preferably.
In order to realize above-described embodiment, the invention also provides a kind of vehicle, which has the vehicle of a upper embodiment
The generation system of full-view image.
The vehicle of the embodiment of the present invention is acquired the original image of vehicle's surroundings by multiple cameras, and is based on vehicle four
Multiple calibration regions are determined in overlapping region in the original image in week, and obtain the image of multiple calibration points in calibration region
Pixel point transformation mathematical model, and according to the image pixel point transformation mathematical model of multiple calibration points, multiple cameras are acquired
To the original images of vehicle's surroundings be transformed into target image respectively, and target image is spliced into panoramic picture, so that spelling
The image co-registration Du Genggao picked out avoids inconsistent phenomenon, and alignment effect is more preferably.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (ram), read-only memory
(rom), erasable edit read-only storage (eprom or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (cdrom).In addition, computer-readable medium can even is that can on it the paper of print routine or other suitable be situated between
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (pga), scene
Programmable gate array (fpga) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
Suddenly be that relevant hardware can be instructed to complete by program, program can store in a kind of computer readable storage medium
In, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.If integrated module with
The form of software function module is realized and when sold or used as an independent product, also can store computer-readable at one
It takes in storage medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as to limit of the invention
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of the invention
Type.
Claims (15)
1. a kind of generation method of vehicle panoramic image characterized by comprising
The original image of vehicle's surroundings is acquired by multiple cameras；
Determine multiple calibration regions in overlapping region in original image based on the vehicle's surroundings；
Obtain the image pixel point transformation mathematical model of multiple calibration points in the calibration region；
According to the image pixel point transformation mathematical model of the multiple calibration point, by the collected vehicle four of the multiple camera
The original image in week is transformed into target image respectively；And
The target image is spliced into panoramic picture.
2. the method as described in claim 1, which is characterized in that the original image of the vehicle's surroundings include forward image, after
Square image, left-side images and image right, the overlapping region in the original image based on the vehicle's surroundings are determined multiple
Demarcate region, comprising:
The first overlapping region between the forward image and the left-side images is obtained, and first overlapping region is carried out
Binary conversion treatment, with the coordinate information in the first calibration region in determination first overlapping region；
The second overlapping region between the forward image and the image right is obtained, and second overlapping region is carried out
Binary conversion treatment, with the coordinate information in the second calibration region in determination second overlapping region；
The third overlapping region between the rear images and the left-side images is obtained, and the third overlapping region is carried out
Binary conversion treatment, with the coordinate information in the third calibration region in the determination third overlapping region；
The 4th overlapping region between the rear images and the image right is obtained, and the 4th overlapping region is carried out
Binary conversion treatment, with the coordinate information in the 4th calibration region in determination the 4th overlapping region.
3. method according to claim 2, which is characterized in that obtain the image pixel of multiple calibration points in the calibration region
Point transformation mathematical model, comprising:
The central point in first calibration region and at least two vertex are determined as to the calibration point in first calibration region, and
Obtain the coordinate of the calibration point in first calibration region, and the Coordinate generation of the calibration point according to first calibration region
First image pixel point transformation mathematical model of multiple calibration points in first calibration region；
The central point in second calibration region and at least two vertex are determined as to the calibration point in second calibration region, and
Obtain the coordinate of the calibration point in second calibration region, and the Coordinate generation of the calibration point according to second calibration region
Second image pixel point transformation mathematical model of multiple calibration points in second calibration region；
The central point in third calibration region and at least two vertex are determined as to the calibration point in third calibration region, and
Obtain the coordinate of the calibration point in third calibration region, and the Coordinate generation of the calibration point according to third calibration region
The third image pixel point transformation mathematical model of multiple calibration points in third calibration region；
The central point in the 4th calibration region and at least two vertex are determined as to the calibration point in the 4th calibration region, and
Obtain the coordinate of the calibration point in the 4th calibration region, and the Coordinate generation of the calibration point according to the 4th calibration region
4th image pixel point transformation mathematical model of multiple calibration points in 4th calibration region.
4. method as claimed in claim 3, which is characterized in that according to the image pixel point transformation mathematics of the multiple calibration point
The original image of the collected vehicle's surroundings of the multiple camera is transformed into target image by model respectively, comprising:
Using the first image pixel point transformation mathematical model, the forward image and the left-side images are respectively converted into
First image and the second image, and the first image and second image are spliced with predetermined angle to generate first
Target image；
Using the second image pixel point transformation mathematical model, the forward image and the image right are respectively converted into
Third image and the 4th image, and the third image and the 4th image are spliced with predetermined angle to generate second
Target image；
Using the third image pixel point transformation mathematical model, the rear images and the left-side images are respectively converted into
5th image and the 6th image, and the 5th image and the 6th image are spliced with predetermined angle to generate third
Target image；
Using the 4th image pixel point transformation mathematical model, the rear images and the image right are respectively converted into
7th image and the 8th image, and the 7th image and the 8th image are spliced with predetermined angle to generate the 4th
Target image.
5. method as claimed in claim 4, which is characterized in that the target image is spliced into panoramic picture, comprising:
By the first object image, second target image, the third target image and the 4th target image into
Row splicing, to generate the panoramic picture.
6. the method as described in claim 1, which is characterized in that the calibration region is polygonal region.
7. method according to claim 2, which is characterized in that further include:
Obtain the angle information between current vehicle position and predeterminated position；
It is coordinately transformed according to coordinate information of the angle information to multiple calibration regions.
8. a kind of generation system of vehicle panoramic image characterized by comprising
Multiple cameras, for acquiring the original image of vehicle's surroundings；
Image received device, the original image of the vehicle's surroundings for receiving the multiple camera acquisition；
Image conversion device determines multiple calibration areas for the overlapping region in the original image based on the vehicle's surroundings
Domain, and the image pixel point transformation mathematical model of multiple calibration points in the calibration region is obtained, and according to the multiple mark
The image pixel point transformation mathematical model of fixed point, the original image of the collected vehicle's surroundings of the multiple camera is become respectively
Change target image into；And
Image splicing device, for the target image to be spliced into panoramic picture.
9. system as claimed in claim 8, which is characterized in that the original image of the vehicle's surroundings include forward image, after
Square image, left-side images and image right, described image converting means, are used for:
The first overlapping region between the forward image and the left-side images is obtained, and first overlapping region is carried out
Binary conversion treatment, with the coordinate information in the first calibration region in determination first overlapping region；
The second overlapping region between the forward image and the image right is obtained, and second overlapping region is carried out
Binary conversion treatment, with the coordinate information in the second calibration region in determination second overlapping region；
The third overlapping region between the rear images and the left-side images is obtained, and the third overlapping region is carried out
Binary conversion treatment, with the coordinate information in the third calibration region in the determination third overlapping region；
The 4th overlapping region between the rear images and the image right is obtained, and the 4th overlapping region is carried out
Binary conversion treatment, with the coordinate information in the 4th calibration region in determination the 4th overlapping region.
10. system as claimed in claim 9, which is characterized in that described image converting means is used for:
The central point in first calibration region and at least two vertex are determined as to the calibration point in first calibration region, and
Obtain the coordinate of the calibration point in first calibration region, and the Coordinate generation of the calibration point according to first calibration region
First image pixel point transformation mathematical model of multiple calibration points in first calibration region；
The central point in second calibration region and at least two vertex are determined as to the calibration point in second calibration region, and
Obtain the coordinate of the calibration point in second calibration region, and the Coordinate generation of the calibration point according to second calibration region
Second image pixel point transformation mathematical model of multiple calibration points in second calibration region；
The central point in third calibration region and at least two vertex are determined as to the calibration point in third calibration region, and
Obtain the coordinate of the calibration point in third calibration region, and the Coordinate generation of the calibration point according to third calibration region
The third image pixel point transformation mathematical model of multiple calibration points in third calibration region；
The central point in the 4th calibration region and at least two vertex are determined as to the calibration point in the 4th calibration region, and
Obtain the coordinate of the calibration point in the 4th calibration region, and the Coordinate generation of the calibration point according to the 4th calibration region
4th image pixel point transformation mathematical model of multiple calibration points in 4th calibration region.
11. system as claimed in claim 10, which is characterized in that described image converting means is used for:
Using the first image pixel point transformation mathematical model, the forward image and the left-side images are respectively converted into
First image and the second image, and the first image and second image are spliced with predetermined angle to generate first
Target image；
Using the second image pixel point transformation mathematical model, the forward image and the image right are respectively converted into
Third image and the 4th image, and the third image and the 4th image are spliced with predetermined angle to generate second
Target image；
Using the third image pixel point transformation mathematical model, the rear images and the left-side images are respectively converted into
5th image and the 6th image, and the 5th image and the 6th image are spliced with predetermined angle to generate third
Target image；
Using the 4th image pixel point transformation mathematical model, the rear images and the image right are respectively converted into
7th image and the 8th image, and the 7th image and the 8th image are spliced with predetermined angle to generate the 4th
Target image.
12. system as claimed in claim 11, which is characterized in that described image splicing apparatus is used for
By the first object image, second target image, the third target image and the 4th target image into
Row splicing, to generate the panoramic picture.
13. system as claimed in claim 8, which is characterized in that the calibration region is polygonal region.
14. system as claimed in claim 9, which is characterized in that described image converting means is also used to:
The angle information between current vehicle position and predeterminated position is obtained, and according to the angle information to multiple calibration regions
Coordinate information be coordinately transformed.
15. a kind of vehicle, which is characterized in that the generation system including the described in any item vehicle panoramic images of such as claim 8-14
System.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810380394.6A CN110400255B (en) | 2018-04-25 | 2018-04-25 | Vehicle panoramic image generation method and system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810380394.6A CN110400255B (en) | 2018-04-25 | 2018-04-25 | Vehicle panoramic image generation method and system and vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110400255A true CN110400255A (en) | 2019-11-01 |
| CN110400255B CN110400255B (en) | 2022-03-15 |
Family
ID=68319973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810380394.6A Active CN110400255B (en) | 2018-04-25 | 2018-04-25 | Vehicle panoramic image generation method and system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400255B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956585A (en) * | 2019-11-29 | 2020-04-03 | 深圳市英博超算科技有限公司 | Panoramic image splicing method and device and computer readable storage medium |
| CN111428616A (en) * | 2020-03-20 | 2020-07-17 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space detection method, device, equipment and storage medium |
| CN112380963A (en) * | 2020-11-11 | 2021-02-19 | 东软睿驰汽车技术（沈阳）有限公司 | Depth information determination method and device based on panoramic all-round looking system |
| CN114399557A (en) * | 2021-12-25 | 2022-04-26 | 深圳市全景达科技有限公司 | Panoramic calibration method and system and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203759754U (en) * | 2014-04-03 | 2014-08-06 | 深圳市德赛微电子技术有限公司 | Vehicular panoramic imaging system calibrator |
| CN104751409A (en) * | 2013-12-27 | 2015-07-01 | 比亚迪股份有限公司 | Auto panoramic image calibration system, forming system and calibration method |
| CN105635551A (en) * | 2014-10-29 | 2016-06-01 | 浙江大华技术股份有限公司 | Method of dome camera for generating panoramic image, and dome camera |
| US9489716B1 (en) * | 2011-09-27 | 2016-11-08 | Google Inc. | Street-level imagery acquisition and selection |
-
2018
- 2018-04-25 CN CN201810380394.6A patent/CN110400255B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9489716B1 (en) * | 2011-09-27 | 2016-11-08 | Google Inc. | Street-level imagery acquisition and selection |
| CN104751409A (en) * | 2013-12-27 | 2015-07-01 | 比亚迪股份有限公司 | Auto panoramic image calibration system, forming system and calibration method |
| CN203759754U (en) * | 2014-04-03 | 2014-08-06 | 深圳市德赛微电子技术有限公司 | Vehicular panoramic imaging system calibrator |
| CN105635551A (en) * | 2014-10-29 | 2016-06-01 | 浙江大华技术股份有限公司 | Method of dome camera for generating panoramic image, and dome camera |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956585A (en) * | 2019-11-29 | 2020-04-03 | 深圳市英博超算科技有限公司 | Panoramic image splicing method and device and computer readable storage medium |
| CN111428616A (en) * | 2020-03-20 | 2020-07-17 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space detection method, device, equipment and storage medium |
| CN111428616B (en) * | 2020-03-20 | 2023-05-23 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space detection method, device, equipment and storage medium |
| CN112380963A (en) * | 2020-11-11 | 2021-02-19 | 东软睿驰汽车技术（沈阳）有限公司 | Depth information determination method and device based on panoramic all-round looking system |
| CN112380963B (en) * | 2020-11-11 | 2024-05-31 | 东软睿驰汽车技术（沈阳）有限公司 | Depth information determining method and device based on panoramic looking-around system |
| CN114399557A (en) * | 2021-12-25 | 2022-04-26 | 深圳市全景达科技有限公司 | Panoramic calibration method and system and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110400255B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400255A (en) | Generation method, system and the vehicle of vehicle panoramic image | |
| CN111369439B (en) | Panoramic all-around image real-time splicing method for automatic parking space identification based on all-around | |
| CN109741455B (en) | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system | |
| US8242895B2 (en) | Method and system for forming surrounding seamless bird-view image | |
| CN103035005B (en) | The scaling method that panorama is parked, and device, a kind of automatic calibration method | |
| KR100882011B1 (en) | Methods of obtaining panoramic images using rotationally symmetric wide-angle lenses and devices thereof | |
| CN109948398B (en) | Image processing method for panoramic parking and panoramic parking device | |
| CN102045546B (en) | Panoramic parking assist system | |
| US20100245574A1 (en) | Vehicle periphery display device and method for vehicle periphery image | |
| CN108263283A (en) | More marshalling varied angle vehicle panoramic viewing system calibration and joining method | |
| US20140114534A1 (en) | Dynamic rearview mirror display features | |
| CN110337386A (en) | For rearview visually after spliced panoramic view | |
| CN103366339A (en) | Vehicle-mounted multi-wide angle camera picture synthesis processing device and method | |
| US9100554B2 (en) | Method for displaying an image on a display device in a vehicle, driver assistance system and vehicle | |
| CN107027329B (en) | Stitching together partial images of the surroundings of a running tool into one image | |
| CN110288527B (en) | Panoramic aerial view generation method of vehicle-mounted panoramic camera | |
| KR101077584B1 (en) | Apparatus and method for processing images obtained by a plurality of cameras | |
| CN112224132A (en) | Vehicle panoramic all-around obstacle early warning method | |
| CN105321160B (en) | The multi-camera calibration that 3 D stereo panorama is parked | |
| CN102574485B (en) | For the method and apparatus of the video data of traffic and the combination visual display of range data | |
| US20100214412A1 (en) | Method for calibrating an assembly using at least one omnidirectional camera and an optical display unit | |
| DE102019131942A1 (en) | Environment monitoring device | |
| CN108174089B (en) | Backing image splicing method and device based on binocular camera | |
| US20200117918A1 (en) | Vehicle lane marking and other object detection using side fisheye cameras and three-fold de-warping | |
| CN206317810U (en) | A kind of vehicle travels 360 degree of panorama driving scaling boards |
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 |