CN106296577A - Image split-joint method and image mosaic device - Google Patents
Image split-joint method and image mosaic device Download PDFInfo
- Publication number
- CN106296577A CN106296577A CN201510257323.3A CN201510257323A CN106296577A CN 106296577 A CN106296577 A CN 106296577A CN 201510257323 A CN201510257323 A CN 201510257323A CN 106296577 A CN106296577 A CN 106296577A
- Authority
- CN
- China
- Prior art keywords
- image
- point
- piece
- subpoint
- region
- 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 97
- 230000009466 transformation Effects 0.000 claims abstract description 76
- 238000006243 chemical reaction Methods 0.000 claims abstract description 26
- 239000000203 mixture Substances 0.000 claims description 40
- 238000009499 grossing Methods 0.000 claims description 35
- 239000000284 extract Substances 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 7
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 9
- 238000012876 topography Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000000654 additive Substances 0.000 description 4
- 230000000996 additive effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006854 communication Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
Disclose a kind of image split-joint method and image mosaic device.This image split-joint method includes: the first image and the second image are carried out coarse alignment, to obtain both rectangle overlapping regions；Using the cornerwise left part between the lower left corner and the upper right corner of overlapping region as the left part of the first piece of the first image, and left part based on the first piece estimates the left part of the second piece in the second image；Using cornerwise right part of overlapping region as the right part of the second piece of the second image, and right part based on the second piece estimates the right part of the first piece in the first image；Based on the first piece and the second piece, overlapping region performed local smooth transformation；Overlapping region after the Non-overlapping Domain of the first image and the second image and conversion is combined, thus forms the first image and the stitching image of the second image.According to embodiment of the disclosure, it is possible to remove local error alignment and be not required to repeatedly changing image.
Description
Technical field
It relates to technical field of data processing, local smoothing method is used to become more particularly, to one
Change the image split-joint method and image mosaic device that image is spliced.
Background technology
Multiple overlay chart pictures can be combined as a high-definition picture by merging algorithm for images, and this algorithm can
It is used in the reconstruction of several scenes such as panorama, 3D digital map navigation, remote sensing images reconstruction etc..
Splicing for large scale file and picture, traditional method uses world model to align image,
Overlapping region the most after alignment carries out the methods such as image co-registration and completes splicing.But, non-rigid
In file and picture splicing, there is local deformation, only will produce Local Structure of Image content by image co-registration
Mistake alignment.Other method uses Two bors d's oeuveres seam to carry out stitching image, if but needing repeatedly group
When closing image, it is often necessary to image is repeatedly converted.It addition, the method for above-mentioned estimation Two bors d's oeuveres seam
Only converting piece topography, this will bring mis-alignment.Fig. 1 is to illustrate that employing is above-mentioned
The schematic diagram of the topography of image after the splicing that existing joining method obtains.Right part such as Fig. 1
Shown in, it is assumed that I1, I2 and I3 are respectively the image of alignment, and rectangle frame A1 represents I1's and I2
Overlapping region, rectangle frame A2 represents the overlapping region of I2 and I3.In the left part of Fig. 1, by
On sequentially show downwards image after the splicing corresponding with four dotted line frames in the right part of Fig. 1
Topography, i.e. respectively illustrate: topography that the A1 after original I 1 and conversion intersects, by
The topography that A1 after conversion is constituted, the topography being made up of the A2 after converting, Yi Jiyuan
The topography that A2 after beginning I3 and conversion intersects.By four shown in the left part of Fig. 1 local
Image can be seen that in overlapping region, can obtain and preferably splice result, but, at original image
The place (as shown in the circle in the left part of Fig. 1) intersected with the overlapping region after conversion, still
Wrong alignment.
As it has been described above, the subject matter of present image stitching algorithm is in spliced image to there is mistake
Miss local alignment and need image is repeatedly converted.
Summary of the invention
The brief overview about the disclosure given below, in order to provide about some of the disclosure
The basic comprehension of aspect.It is understood, however, that this general introduction is not the exhaustive about the disclosure
General introduction.It is not intended to the critical component for determining the disclosure or pith, is not meaning
Figure is used for limiting the scope of the present disclosure.Its purpose is only to be given in simplified form about the disclosure
Some concept, in this, as preamble in greater detail given later.
In view of problem above, the purpose of the disclosure is to provide a kind of mistake that can remove image local content
Mis-alignment, be not required to repeatedly changing image and can effectively keep picture material image split-joint method and
Image mosaic device.
One side according to the disclosure, it is provided that a kind of first image and the second image spliced
Image split-joint method, including: coarse alignment step, the most right for the first image and the second image are carried out
Standard, to obtain both rectangle overlapping regions；First piece extracts and estimating step, is used for extracting weight
Cornerwise left part between the lower left corner and the upper right corner in folded region is as the first of the first image
The left part of piece, and left part based on the first piece estimates that in the second image second spells
The left part of seam；Second piece extracts and estimating step, for extracting the described diagonal angle of overlapping region
The right part of line is as the right part of the second piece of the second image and based on the second piece
Right part estimates the right part of the first piece in the first image；Local smoothing method shift step, uses
In based on the first piece and the second piece, overlapping region being performed local smooth transformation；And combination step
Suddenly, for the overlapping region after the Non-overlapping Domain of the first image and the second image and conversion is carried out group
Close, thus form the first image and the stitching image of the second image.
According to another aspect of the present disclosure, additionally provide one and the first image and the second image are spelled
The image mosaic device connect, including: coarse alignment unit, it is configured to the first image and the second image
Carry out coarse alignment, to obtain both rectangle overlapping regions；First piece extracts and estimation unit, quilt
The cornerwise left part being configured to extract between the lower left corner and the upper right corner of overlapping region is as the
The left part of the first piece of one image, and left part based on the first piece is at the second image
The left part of middle estimation the second piece；Second piece extracts and estimation unit, is configured to extract weight
Fold described cornerwise right part right part as the second piece of the second image in region, and
And right part of based on the second piece estimates the right part of the first piece in the first image；Locally
Smooth transformation unit, is configured to, based on the first piece and the second piece, overlapping region is performed local flat
Sliding conversion；And assembled unit, be configured to by the Non-overlapping Domain of the first image and the second image with
Overlapping region after conversion is combined, thus forms the first image and the stitching image of the second image.
According to the other side of the disclosure, additionally provide for realizing above-mentioned according to disclosed method
Computer program code and computer program and on it record have this to be used for realizing above-mentioned basis
The computer-readable recording medium of the computer program code of disclosed method.
The other side of disclosure embodiment is given, wherein, specifically in following description part
The bright preferred embodiment for disclosing disclosure embodiment fully, and do not apply to limit to it.
Accompanying drawing explanation
The disclosure can be by with reference to obtaining below in association with the detailed description given by accompanying drawing more preferably
Understanding, employ the most in all of the figs same or analogous reference to represent identical or
Similar parts.Described accompanying drawing comprises in this manual together with detailed description below and is formed
A part for description, is used for being further illustrated by preferred embodiment of the present disclosure and explaining the disclosure
Principle and advantage.Wherein:
Fig. 1 is to illustrate to use the signal of the topography of image after the splicing that obtains of existing joining method
Figure；
Fig. 2 is the flow process illustrating the flow example according to the image split-joint method that embodiment of the disclosure
Figure；
Fig. 3 is to describe the schematic diagram estimated according to the optimum piece that embodiment of the disclosure；
Fig. 4 is to illustrate the schematic diagram according to the local smoothing method conversion that embodiment of the disclosure；
Fig. 5 is to illustrate the concrete mode converting image-region according to embodiment of the disclosure
Schematic diagram；
Fig. 6 is to illustrate the functional configuration example according to the image mosaic device that embodiment of the disclosure
Block diagram；
Fig. 7 is to illustrate that the functional configuration according to the local smoothing method converter unit that embodiment of the disclosure is shown
The block diagram of example；And
Fig. 8 is that in being shown as embodiment of the disclosure, the individual of adoptable messaging device is counted
The block diagram of the exemplary construction of calculation machine.
Detailed description of the invention
It is described hereinafter in connection with accompanying drawing one exemplary embodiment of this disclosure.In order to clear and
For the sake of Jian Ming, all features of actual embodiment are not the most described.But, it should
Solve, must make a lot specific to embodiment during developing any this practical embodiments
Determine, in order to realize the objectives of developer, such as, meet that relevant to system and business
Restrictive conditions, and these restrictive conditions a bit may change along with the difference of embodiment.
Additionally, it also should be appreciated that, although development is likely to be extremely complex and time-consuming, but to benefit
For those skilled in the art of present disclosure, this development is only routine task.
Here, also need to explanation a bit, in order to avoid having obscured these public affairs because of unnecessary details
Open, illustrate only in the accompanying drawings with according to the closely-related device structure of scheme of the disclosure and/or
Process step, and eliminate other details little with disclosure relation.
Describe in detail below in conjunction with the accompanying drawings according to embodiment of the disclosure.
First, show describing the flow process according to the image split-joint method that embodiment of the disclosure with reference to Fig. 2
Example.Fig. 2 is the flow process illustrating the flow example according to the image split-joint method that embodiment of the disclosure
Figure.
As in figure 2 it is shown, coarse alignment step can be included according to the image split-joint method that embodiment of the disclosure
S202, the first piece extraction and estimating step S204, the second piece extraction and estimating step S206,
Local smoothing method shift step S208 and combination step S210.To be described each respectively in detail below
Process in step.
First, in coarse alignment step S202, it is the most right to carry out the first image and the second image
Standard, to obtain both rectangle overlapping regions.
Preferably, in coarse alignment step S202, use the first image as reference picture, can lead to
Cross traditional method (method such as carrying out image conversion by characteristic matching) by the second image and first
Image carries out coarse alignment, thus obtains the rectangle overlapping region of the first image and the second image.
It follows that to extract and to estimate the first image according to the image split-joint method that embodiment of the disclosure
The first piece and the second piece of the second image.To describe according to embodiment of the disclosure with reference to Fig. 3
Extraction and estimate the first piece and the example of the second piece.Fig. 3 is to describe the enforcement according to the disclosure
The schematic diagram that the optimum piece of example is estimated.
As shown in Figure 3, it is assumed that the first image and the second image are respectively I1 and I2, the first piece and
Second piece is respectively the lower left corner that S1 and S2, O1 and O2 are the overlapping region of I1 Yu I2 respectively
And the upper right corner, M and N is the sampled point on the first piece S1, and M ' and N ' is for such as passing through feature
That coupling is estimated on the second piece S2, corresponding with M and N on the first piece S1 respectively
Point.P1 and P2 represents M and N subpoint on the lower boundary of overlapping region respectively.Because figure
Shadow region in 3 should come from I1, and therefore the fracture etc. that misplaces should not occur in the S1 upper left corner.Thus,
By some P1, M ', the region that forms of N ' and P2 should be transformed to by some P1, M, N and
The region of P2 composition.
But, triangle " hole region " Δ O1MP1 will be produced, this region area is:
S∝|O1M|·|O1P1|
In order to minimize this region, there are two kinds of approach:
● minimize | O1P1 |
| O1P1 | between the M and M ' subpoint on the lower boundary of overlapping region away from
From.Therefore, in overlapping region, should take and first poor minimum corresponding sampling of sample point coordinate
Point.
● minimize | O1M |
Can be moved by M as O1, then the area S of above-mentioned zone becomes 0.
Therefore, extract at the first piece and in estimating step S204, a left side for overlapping region can be extracted
Cornerwise left part between inferior horn and the upper right corner is as the left side of the first piece of the first image
Part, and left part based on the first piece can estimate the left side of the second piece in the second image
Side part.
Preferably, extract at the first piece and in estimating step S204, overlapping region can be extracted
The left-half of diagonal O1O2 is as the left part of the first piece S1 of the first image I1.This
Outward, it is also possible to extract 1/4th of left side of diagonal O1O2 of overlapping region, 1/3rd,
The left part of three/second-class the first piece S1 as the first image I1, this is not made by the disclosure
Limit.
Preferably, characteristic matching can be passed through, left part based on the first piece S1 extracted
The left part of the second piece S2 is estimated in the second image I2.It addition, those skilled in the art are also
Can be readily apparent that left part based on the first piece S1 extracted is estimated in the second image I2
The additive method of the left part of the second piece S2, this is not restricted by the disclosure.
Extract at the second piece and in estimating step S206, the described diagonal angle of overlapping region can be extracted
The right part of line is as the right part of the second piece of the second image, and can spell based on second
The right part of seam estimates the right part of the first piece in the first image.
Preferably, extract at the second piece and in estimating step S206, overlapping region can be extracted
The right half part of diagonal O1O2 is as the right part of the second piece S2 of the second image I2.This
Outward, it is also possible to extract 1/4th of right side of diagonal O1O2 of overlapping region, 1/3rd,
The right part of three/second-class the second piece S2 as the second image I2, this is not made by the disclosure
Limit.
Preferably, characteristic matching can be passed through, the second piece based on the second image I2 extracted
The right part of S2 estimates the right part of the first piece S1 in the first image I1.It addition, this
Skilled person can also be readily apparent that the second piece S2's based on the second image I2 extracted
Right part estimates the additive method of the right part of the first piece S1, these public affairs in the first image I1
Open and this is not restricted.
From the foregoing, it will be observed that the first piece S1 can be overlapping region lower left corner O1 to the second piece
Line segment between the point corresponding for terminal O2 of S2.Second piece S2 can be and the first piece S1
Point corresponding to head-end O1 to the line segment between the upper right corner O2 of overlapping region.
It follows that in local smoothing method shift step S208, can spell based on the first piece and second
Stitch and overlapping region is performed local smooth transformation.
To describe according to the local smoothing method conversion that embodiment of the disclosure with reference to Fig. 4.Fig. 4 is to illustrate root
Schematic diagram according to the local smoothing method conversion that embodiment of the disclosure.
In the diagram, two pieces of shadow regions represent two image sections to be spliced respectively.Assume first
Piece includes sampled point M and N, estimates that its corresponding point are respectively by characteristic matching on the second piece
For M ' and N '；Second piece includes sampled point Q ' and H ' (the i.e. upper right corner of overlapping region in Fig. 3
O2), on the first piece, estimate that its corresponding point are respectively Q and H by characteristic matching.P1、P2、
P3 and P6 is a M ', N ', Q ' and the H ' subpoint on the lower boundary of overlapping region respectively；P4、
P5 and P7 is some Q, H and N subpoint on the coboundary of overlapping region respectively.
Preferably, local smoothing method shift step S208 may include that the left side for overlapping region
Point, performing the first smooth transformation with pre-determined number, the first smooth transformation farther includes: spell first
Sew on and choose and second point at first, and choose on the second piece the most right with first and second point
The first corresponding point answered and the second corresponding point, wherein, the first corresponding point and the second corresponding point are in overlay region
Projection on the lower boundary in territory is respectively the first corresponding subpoint and the second corresponding subpoint；And will be by
First corresponding point, the second corresponding point, the first corresponding subpoint and the region of the second corresponding subpoint composition
Transform to the region being made up of the first point, second point, the first corresponding subpoint and the second corresponding subpoint.
As a example by point M and N in the left part of overlapping region first piece, at the second piece
On choose corresponding point M respectively the most corresponding with putting M and N ' and N ', wherein, corresponding point M ' and N '
Projection on the lower boundary of overlapping region is respectively corresponding subpoint P1 and P2.Since it is desired that carry out
Smooth transformation, need to ensure not rupture in the place that the overlapping region after original image and conversion is intersected.Cause
This, will be by corresponding point M according to the image split-joint method that embodiment of the disclosure ' and N ' and correspondence
Subpoint P1 and P2 composition region (being abbreviated as P1M ' N ' P2) transform to by M and N,
And the region (being abbreviated as P1MNP2) of correspondence subpoint P1 and P2 composition.Successively by overlay region
In the left part in territory, each sampled point on the first piece is as M and N, thus with predetermined time
Several left part to overlapping region perform above-mentioned first smooth transformation.
Preferably, local smoothing method shift step S208 can also include: for the right side of overlapping region
Part, performs the second smooth transformation with pre-determined number, and the second smooth transformation farther includes: second
Choose on piece thirdly with the 4th point, and choose on the first piece with the thirdly and four difference
The 3rd corresponding corresponding point and the 4th corresponding point, wherein, the 3rd corresponding point and the 4th corresponding point are in overlap
Projection on the coboundary in region is respectively the 3rd corresponding subpoint and the 4th corresponding subpoint；And will
The district being made up of the 3rd corresponding point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th corresponding subpoint
Territory transform to by thirdly, the district that forms of the 4th point, the 3rd corresponding subpoint and the 4th corresponding subpoint
Territory.
As shown in Figure 4, as a example by some Q ' on the in the right part of overlapping region second piece and H ',
First piece is chosen corresponding point Q the most corresponding with putting Q ' and H ' and H, wherein, corresponding point
Q and H projection on the coboundary of overlapping region is respectively corresponding subpoint P4 and P5.For protecting
Card right-hand member image occurs without splicing fracture, will be by right according to the image split-joint method that embodiment of the disclosure
Q and H and the region (being abbreviated as P4P5HQ) of corresponding subpoint P4 and P5 composition should be put
Transform to the region being made up of a Q ' and H ' and corresponding subpoint P4 and P5 (to be abbreviated as
P4P5H’Q’).Successively using each sampled point on the second piece in the right part of overlapping region as
Point Q ' and H ', thus with pre-determined number, the right part of overlapping region is performed above-mentioned second and smooth change
Change.
Preferably, local smoothing method shift step S208 can also be wrapped after performing the first smooth transformation
Including and perform the 3rd smooth transformation as transition processing, the 3rd smooth transformation farther includes: first
Choose and the 6th point on piece at the 5th, and choose on the second piece and the 5th and the 6th difference
The 5th corresponding corresponding point and the 6th corresponding point, wherein, the 5th and the 6th upper in overlapping region
Borderline projection is respectively the 5th subpoint and the 6th subpoint, the 5th corresponding point and the 6th corresponding point
Projection on the lower boundary of overlapping region is respectively the 5th corresponding subpoint and the 6th corresponding subpoint,
And the 6th be midpoint with the intermediate point of the 6th corresponding point；Will be by the 5th point, the 6th point, the 5th throwing
The region of shadow point and the 6th subpoint composition transforms to by midpoint, the 5th point, the 5th subpoint and the 6th
The region of subpoint composition；And will be by the 5th corresponding point, the 6th corresponding point, the 5th corresponding subpoint
With the region of the 6th corresponding subpoint composition transform to by midpoint, the 5th point, the 5th corresponding subpoint and
The region of the 6th corresponding subpoint composition.
As shown in Figure 4, when using the first smooth transformation will be by some P2, P3, N ' and Q ' form
Region (being abbreviated as P2P3N ' Q ') transform to the region being made up of some P2, P3, N and Q
Time (being abbreviated as P2P3NQ), will appear between the first smooth transformation and the second smooth transformation being interrupted.
For solving this problem, performing the first smooth change according to the image split-joint method that embodiment of the disclosure
Can also carry out the 3rd smooth transformation as transition processing the most afterwards.That is, with the point on the first piece
As a example by N and Q, the second piece is chosen corresponding point N the most corresponding with putting N and Q ' and Q ',
Point N and Q projection on the coboundary of overlapping region is respectively subpoint P7 and P4, corresponding point
The N ' and Q ' projection on the lower boundary of overlapping region is respectively corresponding subpoint P2 and P3, and counts
Calculation obtains a Q and its corresponding point Q ' midpoint G.According to the image mosaic side that embodiment of the disclosure
The region (being abbreviated as P7P4QN) that method will be made up of N and Q and subpoint P7 and P4
Transform to the region (being abbreviated as P7P4GN) being made up of midpoint G, some N, subpoint P7 and P4；
And by by corresponding point N ' and the region that forms of Q ' and corresponding subpoint P2 and P3 (be abbreviated as
P2P3Q ' N ') transform to the region (letter being made up of midpoint G, some N, corresponding subpoint P2 and P3
It is written as P2P3GN).
Preferably, after carrying out above-mentioned 3rd smooth transformation, for ensureing to occur without spelling with right-hand member image
Connect fracture, will be by P4, P5, H and G group according to the image split-joint method that embodiment of the disclosure
The region (being abbreviated as P4P5HG) become transforms to by some P4, P5, H ' and the region that forms of G
(being abbreviated as P4P5H ' G).
Below the concrete mode of conversion is entered as a example by the conversion of P1M ' N ' P2 to P1MNP2
Row is introduced.Preferably, the conversion from P1M ' N ' P2 to P1MNP2 can be in the following way:
Region to be transformed is divided into triangle, uses affine transformation diabolo to convert.Fig. 5
It is that the schematic diagram according to the concrete mode converting image-region that embodiment of the disclosure is shown.
In Figure 5, region P1M ' N ' P2 to be transformed is divided into two triangle P1P2N ' and P1N ' M ',
Then use affine transformation that triangle P1P2N ' is transformed to triangle P1P2N, and by triangle
P1N ' M ' is transformed to triangle P1NM.Additionally, from the conversion of P1M ' N ' P2 to P1MNP2 also
Can be in the way of using perspective transform, this is not restricted by the disclosure.
Finally, in combination step S210, by the Non-overlapping Domain of the first image and the second image with
Overlapping region after conversion is combined, thus forms the first image and the stitching image of the second image.
Preferably, can successively using each image in multiple images as the first image and the second image
Splice, thus form the stitching image of multiple image.Specifically, can be by image capture device
Obtaining a series of images, use first image as reference picture, other images can pass through feature
Join aligned.The boundary rectangle being size be defined as a series of alignment image of splicing document.Afterwards,
Can successively each image in a series of images be used above-mentioned as the first image and the second image
Method is spliced, thus forms the stitching image of this series of images.
From the above description, it can be seen that figure can be removed according to the image split-joint method that embodiment of the disclosure
As the mistake of local content is directed at, is not required to repeatedly changing image and can effectively keep picture material.
With said method embodiment accordingly, the disclosure additionally provides following device embodiment.
Fig. 6 is to illustrate the functional configuration example according to the image mosaic device that embodiment of the disclosure
Block diagram.
As shown in Figure 6, can include according to the image mosaic device 600 that embodiment of the disclosure the most right
Quasi-unit the 602, first piece extract and estimation unit the 604, second piece extract and estimation unit 606,
Local smoothing method converter unit 608 and assembled unit 610.It is described below the merit of unit
Can configuration example.
Coarse alignment unit 602 may be configured to the first image and the second image are carried out coarse alignment, with
Obtain both rectangle overlapping regions.
Preferably, coarse alignment unit 602 may be configured to use the first image as reference picture,
By traditional method (method such as carrying out image conversion by characteristic matching) by the second image and
One image carries out coarse alignment, thus obtains the rectangle overlapping region of the first image and the second image.
First piece extracts and estimation unit 604 may be configured to extract the lower left corner of overlapping region
And the cornerwise left part between the upper right corner is as the left part of the first piece of the first image,
And left part based on the first piece can estimate the left side of the second piece in the second image
Point.
Preferably, the first piece extracts and estimation unit 604 may be configured to extract overlapping region
Described cornerwise left-half is as the left part of the first piece of the first image.In addition, it is possible to
Using extract cornerwise left side, overlapping region 1/4th, 1/3rd, three/second-class as the
The left part of the first piece of one image, this is not restricted by the disclosure.
Preferably, can pass through characteristic matching, left part based on the first piece extracted is
Two images are estimated the left part of the second piece.It addition, those skilled in the art can also easily think
In the second image, the left side of the second piece is estimated to left part based on the first piece extracted
The additive method of part, this is not restricted by the disclosure.
Second piece extracts and estimation unit 606 may be configured to extract the described right of overlapping region
The right part of linea angulata, and can be based on second as the right part of the second piece of the second image
The right part of piece estimates the right part of the first piece in the first image.
Preferably, the second piece extracts and estimation unit 606 may be configured to extract overlapping region
Described cornerwise right half part is as the right part of the second piece of the second image.In addition, it is possible to
With extract 1/4th of described cornerwise right side of overlapping region, 1/3rd, three/second-class
As the right part of the second piece of the second image, this is not restricted by the disclosure.
Preferably, characteristic matching, the right side of the second piece based on the second image extracted can be passed through
Side part estimates the right part of the first piece in the first image.It addition, those skilled in the art are also
Can be readily apparent that the right part of the second piece based on the second image extracted is at the first image
The additive method of the right part of middle estimation the first piece, this is not restricted by the disclosure.
Local smoothing method converter unit 608 is configured to the first piece and the second piece counterweight
Folded region performs local smooth transformation.
Fig. 7 is to illustrate the functional configuration according to the local smoothing method converter unit 608 that embodiment of the disclosure
The block diagram of example.
As it is shown in fig. 7, local smoothing method converter unit 608 can include the first smooth transformation unit
6082.First smooth transformation unit 6082 may be configured to the left part for overlapping region,
Performing the first smooth transformation with pre-determined number, the first smooth transformation farther includes: on the first piece
Choose and second point at first, and choose the most corresponding with and second point on the second piece at first
First corresponding point and the second corresponding point, wherein, the first corresponding point and the second corresponding point are in overlapping region
Projection on lower boundary is respectively the first corresponding subpoint and the second corresponding subpoint；And will be by first
Corresponding point, the second corresponding point, the first corresponding subpoint and the region conversion of the second corresponding subpoint composition
To the region being made up of the first point, second point, the first corresponding subpoint and the second corresponding subpoint.
Preferably, local smoothing method converter unit 608 can also include the second smooth transformation unit 6084.
Second smooth transformation unit 6084 may be configured to the right part for overlapping region, with predetermined
Number of times performs the second smooth transformation, and the second smooth transformation farther includes: choose on the second piece
3 and the 4th point, and it is right to choose threeth the most corresponding with the thirdly and four on the first piece
Should o'clock and the 4th corresponding point, wherein, the 3rd corresponding point and the 4th corresponding point are in the coboundary of overlapping region
On projection be respectively the 3rd corresponding subpoint and the 4th corresponding subpoint；And will be corresponding by the 3rd
The region of the corresponding subpoint composition of point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th transform to by
Thirdly, the 4th point, the 3rd corresponding subpoint and the region of the 4th corresponding subpoint composition.
Preferably, local smoothing method converter unit 608 can also include the 3rd smooth transformation unit 6086.
3rd smooth transformation unit 6086 may be configured to perform first at the first smooth transformation unit 6082
Performing the 3rd smooth transformation as transition processing after smooth transformation, the 3rd smooth transformation wraps further
Include: on the first piece, choose and the 6th point at the 5th, and choose on the second piece with the 5th and
6th the 5th corresponding point the most corresponding and the 6th corresponding point, wherein, the 5th and the 6th at weight
Projection on the coboundary in folded region is respectively the 5th subpoint and the 6th subpoint, the 5th corresponding point and
The projection on the lower boundary of overlapping region of 6th corresponding point is respectively the 5th corresponding subpoint and the 6th
Corresponding subpoint, and the 6th be midpoint with the intermediate point of the 6th corresponding point；Will by the 5th point,
6 points, the 5th subpoint and the 6th subpoint composition region transform to by midpoint, the 5th point, the 5th
Subpoint and the region of the 6th subpoint composition；And will by the 5th corresponding point, the 6th corresponding point,
The region of five corresponding subpoints and the 6th corresponding subpoint composition transform to by midpoint, the 5th point, the 5th
Corresponding subpoint and the region of the 6th corresponding subpoint composition.
Concrete alternative approach can be found in the description of relevant position in above method embodiment, at this no longer
Repeat.
Assembled unit 610 may be configured to by the Non-overlapping Domain of the first image and the second image with
Overlapping region after conversion is combined, thus forms the first image and the stitching image of the second image.
Although it is noted that the foregoing describing the function according to the image mosaic device that embodiment of the disclosure
Configuration, but this is only exemplary rather than limiting, and those skilled in the art can former according to the disclosure
Above example is modified by reason, such as the functional module in each embodiment can be added,
Delete or combination etc., and such amendment each falls within the scope of the present disclosure.
It is furthermore to be noted that, device embodiment here is corresponding with said method embodiment,
Therefore the content not described in detail in device embodiment can be found in relevant position in embodiment of the method
Describe, be not repeated at this to describe.
Should be understood that and can perform according to the machine in the storage medium that embodiment of the disclosure and program product
Instruction can be configured to perform above-mentioned image split-joint method, in therefore not describing in detail at this
Hold the description referring to previous relevant position, be not repeated at this to be described.
Correspondingly, for carrying the storage medium of the above-mentioned program product including the executable instruction of machine
It is also included within disclosure of the invention.This storage medium include but not limited to floppy disk, CD, magneto-optic disk,
Storage card, memory stick etc..
It addition, should also be noted that above-mentioned series of processes and device can also by software and/or
Firmware realizes.In the case of being realized by software and/or firmware, from storage medium or network to tool
Have the computer of specialized hardware structure, the such as general purpose personal computer 800 shown in Fig. 8 to install to constitute
The program of this software, this computer is when being provided with various program, it is possible to perform various function etc..
In fig. 8, CPU (CPU) 801 is according to read only memory (ROM) 802
The program of middle storage or be loaded into random access memory (RAM) 803 from storage part 808
Program performs various process.In RAM 803, perform respectively as CPU 801 also according to needs storage
Data required during kind of process etc..
CPU 801, ROM 802 and RAM 803 are connected to each other via bus 804.Input/defeated
Outgoing interface 805 is also connected to bus 804.
Components described below is connected to input/output interface 805: importation 806, including keyboard, mouse
Deng；Output part 807, including display, such as cathode ray tube (CRT), liquid crystal display
Etc., and speaker etc. (LCD)；Storage part 808, including hard disk etc.；With communications portion 809,
Including NIC such as LAN card, modem etc..Communications portion 809 is via network ratio
As the Internet performs communication process.
As required, driver 810 is also connected to input/output interface 805.Detachable media 811
Such as disk, CD, magneto-optic disk, semiconductor memory etc. are installed in driver as required
On 810 so that the computer program read out is installed to store in part 808 as required.
In the case of realizing above-mentioned series of processes by software, it is situated between from network such as the Internet or storage
Matter such as detachable media 811 installs the program constituting software.
It will be understood by those of skill in the art that this storage medium is not limited to shown in Fig. 8 wherein
Have program stored therein and equipment distributes the detachable media 811 of the program that provides a user with separately.
The example of detachable media 811 comprises disk (comprising floppy disk (registered trade mark)), CD (comprises light
Dish read only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (comprise mini
Dish (MD) (registered trade mark)) and semiconductor memory.Or, storage medium can be ROM 802,
Hard disk of comprising etc. in storage part 808, wherein computer program stored, and with comprise their equipment
It is distributed to user together.
Describe preferred embodiment of the present disclosure above by reference to accompanying drawing, but the disclosure be certainly not limited to
Upper example.Those skilled in the art can obtain various change within the scope of the appended claims and repair
Change, and it should be understood that these changes and amendment nature will fall in scope of the presently disclosed technology.
Such as, include that multiple functions in a unit can be by separate dress in the embodiment above
Put and realize.As an alternative, the multiple functions realized by multiple unit in the embodiment above can respectively by
Separate device realizes.It addition, one of function above can be realized by multiple unit.Needless to say,
Such configuration is included in scope of the presently disclosed technology.
In this specification, the step described in flow chart not only includes with described order temporally sequence
The process that row perform, and the place including concurrently or individually rather than must performing in temporal sequence
Reason.Additionally, even in the step processed in temporal sequence, it is not necessary to say, it is also possible to suitably change
This order.
It addition, configuration can also be carried out as follows according to the technology of the disclosure.
The image split-joint method that first image and the second image are spliced by remarks 1. 1 kinds, including:
Coarse alignment step, for carrying out coarse alignment to the first image and the second image, to obtain both
Rectangle overlapping region；
First piece extracts and estimating step, for extracting the lower left corner and the upper right corner of described overlapping region
Between cornerwise left part as the left part of the first piece of the first image, and based on
The left part of the first piece estimates the left part of the second piece in the second image；
Second piece extracts and estimating step, for extracting described cornerwise right side of described overlapping region
Sidepiece is allocated as being the right part of the second piece of the second image, and right side based on the second piece
Divide the right part estimating the first piece in the first image；
Local smoothing method shift step, for holding described overlapping region based on the first piece and the second piece
Row local smoothing method converts；And
Combination step, for overlapping with after conversion by the Non-overlapping Domain of the first image and the second image
Region is combined, thus forms the first image and the stitching image of the second image.
Remarks 2. is according to the image split-joint method described in remarks 1, and wherein, described local smoothing method converts
Step includes:
For the left part of described overlapping region, perform the first smooth transformation with pre-determined number, first
Smooth transformation farther includes:
First piece is chosen first and second point, and chooses on the second piece and first
Point and second point distinguish the most corresponding the first corresponding point and the second corresponding point, wherein, and the first corresponding point and the
The projection on the lower boundary of described overlapping region of two corresponding point is respectively the first corresponding subpoint and the
Two corresponding subpoints；And
Will be by the first corresponding point, the second corresponding point, the first corresponding subpoint and the second corresponding projection
The region of some composition transforms to by the first point, second point, the first corresponding subpoint and the second corresponding projection
The region of some composition.
Remarks 3. is according to the image split-joint method described in remarks 1, and wherein, described local smoothing method converts
Step also includes:
For the right part of described overlapping region, perform the second smooth transformation with pre-determined number, second
Smooth transformation farther includes:
Second piece is chosen thirdly with the 4th point, and choose and the 3rd on the first piece
Point and the 4th the 3rd corresponding point corresponding to difference and the 4th corresponding point, wherein, the 3rd corresponding point and the
The projection on the coboundary of described overlapping region of four corresponding point is respectively the 3rd corresponding subpoint and the
Four corresponding subpoints；And
Will be by the 3rd corresponding point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition transform to by thirdly, the 4th point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition.
Remarks 4. is according to the image split-joint method described in remarks 2, and wherein, described local smoothing method converts
Step also includes performing the 3rd smooth transformation as transition processing after performing the first smooth transformation,
3rd smooth transformation farther includes:
First piece chooses the 5th and the 6th point, and choose on the second piece with the 5th and
6th the 5th corresponding point the most corresponding and the 6th corresponding point, wherein, the 5th and the 6th in institute
Stating the projection on the coboundary of overlapping region and be respectively the 5th subpoint and the 6th subpoint, the 5th is corresponding
Point and the projection on the lower boundary of described overlapping region of the 6th corresponding point are respectively the 5th corresponding projection
Point and the 6th corresponding subpoint, and the 6th be midpoint with the intermediate point of the 6th corresponding point；
The region being made up of the 5th point, the 6th point, the 5th subpoint and the 6th subpoint is transformed to by
Described midpoint, the 5th point, the 5th subpoint and the region of the 6th subpoint composition；And
Will be by the 5th corresponding point, the 6th corresponding point, the 5th corresponding subpoint and the 6th corresponding subpoint group
The region become transforms to by described midpoint, the 5th point, the 5th corresponding subpoint and the 6th corresponding subpoint
The region of composition.
Remarks 5. is according to the image split-joint method according to any one of remarks 2 to 4, wherein, will treat
The region of conversion is divided into triangle, uses affine transformation to convert described triangle.
Remarks 6., according to the image split-joint method described in remarks 1, also includes:
Successively each image in multiple images is spliced as the first image and the second image, from
And form the stitching image of the plurality of image.
The image mosaic device that first image and the second image are spliced by remarks 7. 1 kinds, including:
Coarse alignment unit, is configured to the first image and the second image are carried out coarse alignment, to obtain two
The rectangle overlapping region of person；
First piece extracts and estimation unit, is configured to the lower left corner extracting described overlapping region with right
Cornerwise left part between upper angle as the left part of the first piece of the first image, and
Left part based on the first piece estimates the left part of the second piece in the second image；
Second piece extracts and estimation unit, is configured to extract the described diagonal of described overlapping region
Right part as the right part of the second piece of the second image, and the right side based on the second piece
Side part estimates the right part of the first piece in the first image；
Local smoothing method converter unit, is configured to based on the first piece and the second piece described overlay region
Territory performs local smooth transformation；And
Assembled unit, is configured to after the Non-overlapping Domain of the first image and the second image and conversion
Overlapping region is combined, thus forms the first image and the stitching image of the second image.
Remarks 8. is according to the image mosaic device described in remarks 7, and wherein, described local smoothing method converts
Unit includes:
First smooth transformation unit, is configured to the left part for described overlapping region, with predetermined
Number of times performs the first smooth transformation, and the first smooth transformation farther includes:
First piece is chosen first and second point, and chooses on the second piece and first
Point and second point distinguish the most corresponding the first corresponding point and the second corresponding point, wherein, and the first corresponding point and the
The projection on the lower boundary of described overlapping region of two corresponding point is respectively the first corresponding subpoint and the
Two corresponding subpoints；And
Will be by the first corresponding point, the second corresponding point, the first corresponding subpoint and the second corresponding projection
The region of some composition transforms to by the first point, second point, the first corresponding subpoint and the second corresponding projection
The region of some composition.
Remarks 9. is according to the image mosaic device described in remarks 7, and wherein, described local smoothing method converts
Unit also includes:
Second smooth transformation unit, is configured to the right part for described overlapping region, with predetermined
Number of times performs the second smooth transformation, and the second smooth transformation farther includes:
Second piece is chosen thirdly with the 4th point, and choose and the 3rd on the first piece
Point and the 4th the 3rd corresponding point corresponding to difference and the 4th corresponding point, wherein, the 3rd corresponding point and the
The projection on the coboundary of described overlapping region of four corresponding point is respectively the 3rd corresponding subpoint and the
Four corresponding subpoints；And
Will be by the 3rd corresponding point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition transform to by thirdly, the 4th point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition.
Remarks 10. is according to the image mosaic device described in remarks 8, and wherein, described local smoothing method converts
Unit also includes that the 3rd smooth transformation unit, described 3rd smooth transformation unit are configured to described
One smooth transformation unit performs the as transition processing the 3rd smooth change after performing the first smooth transformation
Changing, the 3rd smooth transformation farther includes:
First piece chooses the 5th and the 6th point, and choose on the second piece with the 5th and
6th the 5th corresponding point the most corresponding and the 6th corresponding point, wherein, the 5th and the 6th in institute
Stating the projection on the coboundary of overlapping region and be respectively the 5th subpoint and the 6th subpoint, the 5th is corresponding
Point and the projection on the lower boundary of described overlapping region of the 6th corresponding point are respectively the 5th corresponding projection
Point and the 6th corresponding subpoint, and the 6th be midpoint with the intermediate point of the 6th corresponding point；
The region being made up of the 5th point, the 6th point, the 5th subpoint and the 6th subpoint is transformed to by
Described midpoint, the 5th point, the 5th subpoint and the region of the 6th subpoint composition；And
Will be by the 5th corresponding point, the 6th corresponding point, the 5th corresponding subpoint and the 6th corresponding subpoint group
The region become transforms to by described midpoint, the 5th point, the 5th corresponding subpoint and the 6th corresponding subpoint
The region of composition.
Remarks 11. is according to the image mosaic device according to any one of remarks 8 to 10, wherein, and will
Region to be transformed is divided into triangle, uses affine transformation to convert described triangle.
Remarks 12. is according to the image mosaic device described in remarks 7, wherein,
Successively each image in multiple images is spliced as the first image and the second image, from
And form the stitching image of the plurality of image.
Claims (10)
1. the image split-joint method the first image and the second image spliced, including:
Coarse alignment step, for carrying out coarse alignment to the first image and the second image, to obtain both
Rectangle overlapping region；
First piece extracts and estimating step, for extracting the lower left corner and the upper right corner of described overlapping region
Between cornerwise left part as the left part of the first piece of the first image, and based on
The left part of the first piece estimates the left part of the second piece in the second image；
Second piece extracts and estimating step, for extracting described cornerwise right side of described overlapping region
Sidepiece is allocated as being the right part of the second piece of the second image, and right side based on the second piece
Divide the right part estimating the first piece in the first image；
Local smoothing method shift step, for holding described overlapping region based on the first piece and the second piece
Row local smoothing method converts；And
Combination step, for overlapping with after conversion by the Non-overlapping Domain of the first image and the second image
Region is combined, thus forms the first image and the stitching image of the second image.
Image split-joint method the most according to claim 1, wherein, described local smoothing method converts
Step includes:
For the left part of described overlapping region, perform the first smooth transformation with pre-determined number, first
Smooth transformation farther includes:
First piece is chosen first and second point, and chooses on the second piece and first
Point and second point distinguish the most corresponding the first corresponding point and the second corresponding point, wherein, and the first corresponding point and the
The projection on the lower boundary of described overlapping region of two corresponding point is respectively the first corresponding subpoint and the
Two corresponding subpoints；And
Will be by the first corresponding point, the second corresponding point, the first corresponding subpoint and the second corresponding projection
The region of some composition transforms to by the first point, second point, the first corresponding subpoint and the second corresponding projection
The region of some composition.
Image split-joint method the most according to claim 1, wherein, described local smoothing method converts
Step also includes:
For the right part of described overlapping region, perform the second smooth transformation with pre-determined number, second
Smooth transformation farther includes:
Second piece is chosen thirdly with the 4th point, and choose and the 3rd on the first piece
Point and the 4th the 3rd corresponding point corresponding to difference and the 4th corresponding point, wherein, the 3rd corresponding point and the
The projection on the coboundary of described overlapping region of four corresponding point is respectively the 3rd corresponding subpoint and the
Four corresponding subpoints；And
Will be by the 3rd corresponding point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition transform to by thirdly, the 4th point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition.
Image split-joint method the most according to claim 2, wherein, described local smoothing method converts
Step also includes performing the 3rd smooth transformation as transition processing after performing the first smooth transformation,
3rd smooth transformation farther includes:
First piece chooses the 5th and the 6th point, and choose on the second piece with the 5th and
6th the 5th corresponding point the most corresponding and the 6th corresponding point, wherein, the 5th and the 6th in institute
Stating the projection on the coboundary of overlapping region and be respectively the 5th subpoint and the 6th subpoint, the 5th is corresponding
Point and the projection on the lower boundary of described overlapping region of the 6th corresponding point are respectively the 5th corresponding projection
Point and the 6th corresponding subpoint, and the 6th be midpoint with the intermediate point of the 6th corresponding point；
The region being made up of the 5th point, the 6th point, the 5th subpoint and the 6th subpoint is transformed to by
Described midpoint, the 5th point, the 5th subpoint and the region of the 6th subpoint composition；And
Will be by the 5th corresponding point, the 6th corresponding point, the 5th corresponding subpoint and the 6th corresponding subpoint group
The region become transforms to by described midpoint, the 5th point, the 5th corresponding subpoint and the 6th corresponding subpoint
The region of composition.
5. according to the image split-joint method according to any one of claim 2 to claim 4, its
In, region to be transformed is divided into triangle, uses affine transformation that described triangle is converted.
Image split-joint method the most according to claim 1, also includes:
Successively each image in multiple images is spliced as the first image and the second image, from
And form the stitching image of the plurality of image.
7. the image mosaic device the first image and the second image spliced, including:
Coarse alignment unit, is configured to the first image and the second image are carried out coarse alignment, to obtain two
The rectangle overlapping region of person；
First piece extracts and estimation unit, is configured to the lower left corner extracting described overlapping region with right
Cornerwise left part between upper angle as the left part of the first piece of the first image, and
Left part based on the first piece estimates the left part of the second piece in the second image；
Second piece extracts and estimation unit, is configured to extract the described diagonal of described overlapping region
Right part as the right part of the second piece of the second image, and the right side based on the second piece
Side part estimates the right part of the first piece in the first image；
Local smoothing method converter unit, is configured to based on the first piece and the second piece described overlay region
Territory performs local smooth transformation；And
Assembled unit, is configured to after the Non-overlapping Domain of the first image and the second image and conversion
Overlapping region is combined, thus forms the first image and the stitching image of the second image.
Image mosaic device the most according to claim 7, wherein, described local smoothing method converts
Unit includes:
First smooth transformation unit, is configured to the left part for described overlapping region, with predetermined
Number of times performs the first smooth transformation, and the first smooth transformation farther includes:
First piece is chosen first and second point, and chooses on the second piece and first
Point and second point distinguish the most corresponding the first corresponding point and the second corresponding point, wherein, and the first corresponding point and the
The projection on the lower boundary of described overlapping region of two corresponding point is respectively the first corresponding subpoint and the
Two corresponding subpoints；And
Will be by the first corresponding point, the second corresponding point, the first corresponding subpoint and the second corresponding projection
The region of some composition transforms to by the first point, second point, the first corresponding subpoint and the second corresponding projection
The region of some composition.
Image mosaic device the most according to claim 7, wherein, described local smoothing method converts
Unit also includes:
Second smooth transformation unit, is configured to the right part for described overlapping region, with predetermined
Number of times performs the second smooth transformation, and the second smooth transformation farther includes:
Second piece is chosen thirdly with the 4th point, and choose and the 3rd on the first piece
Point and the 4th the 3rd corresponding point corresponding to difference and the 4th corresponding point, wherein, the 3rd corresponding point and the
The projection on the coboundary of described overlapping region of four corresponding point is respectively the 3rd corresponding subpoint and the
Four corresponding subpoints；And
Will be by the 3rd corresponding point, the 4th corresponding point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition transform to by thirdly, the 4th point, the 3rd corresponding subpoint and the 4th corresponding projection
The region of some composition.
Image mosaic device the most according to claim 8, wherein, described local smoothing method converts
Unit also includes that the 3rd smooth transformation unit, described 3rd smooth transformation unit are configured to described
One smooth transformation unit performs the as transition processing the 3rd smooth change after performing the first smooth transformation
Changing, the 3rd smooth transformation farther includes:
First piece chooses the 5th and the 6th point, and choose on the second piece with the 5th and
6th the 5th corresponding point the most corresponding and the 6th corresponding point, wherein, the 5th and the 6th in institute
Stating the projection on the coboundary of overlapping region and be respectively the 5th subpoint and the 6th subpoint, the 5th is corresponding
Point and the projection on the lower boundary of described overlapping region of the 6th corresponding point are respectively the 5th corresponding projection
Point and the 6th corresponding subpoint, and the 6th be midpoint with the intermediate point of the 6th corresponding point；
The region being made up of the 5th point, the 6th point, the 5th subpoint and the 6th subpoint is transformed to by
Described midpoint, the 5th point, the 5th subpoint and the region of the 6th subpoint composition；And
Will be by the 5th corresponding point, the 6th corresponding point, the 5th corresponding subpoint and the 6th corresponding subpoint group
The region become transforms to by described midpoint, the 5th point, the 5th corresponding subpoint and the 6th corresponding subpoint
The region of composition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510257323.3A CN106296577B (en) | 2015-05-19 | 2015-05-19 | Image split-joint method and image mosaic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510257323.3A CN106296577B (en) | 2015-05-19 | 2015-05-19 | Image split-joint method and image mosaic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106296577A true CN106296577A (en) | 2017-01-04 |
| CN106296577B CN106296577B (en) | 2019-11-29 |
Family
ID=57632629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510257323.3A Active CN106296577B (en) | 2015-05-19 | 2015-05-19 | Image split-joint method and image mosaic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296577B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934769A (en) * | 2019-04-26 | 2019-06-25 | 努比亚技术有限公司 | Method, terminal and the storage medium of the long screenshot of screen |
| WO2020143090A1 (en) * | 2019-01-10 | 2020-07-16 | 深圳市沃特沃德股份有限公司 | Image acquisition method, apparatus and device based on multiple cameras |
| CN113139905A (en) * | 2021-04-29 | 2021-07-20 | 北京百度网讯科技有限公司 | Image splicing method, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060238536A1 (en) * | 1999-07-30 | 2006-10-26 | Canon Kabushiki Kaisha | Image synthesis method, image synthesis apparatus, and storage medium |
| JP4552115B2 (en) * | 2004-06-15 | 2010-09-29 | ソニー株式会社 | Image processing apparatus and method, recording medium, and program |
| CN101923709A (en) * | 2009-06-16 | 2010-12-22 | 日电（中国）有限公司 | Image splicing method and equipment |
| CN103501415A (en) * | 2013-10-01 | 2014-01-08 | 中国人民解放军国防科学技术大学 | Overlap structural deformation-based video real-time stitching method |
| CN104361569A (en) * | 2014-11-11 | 2015-02-18 | 浙江宇视科技有限公司 | Method and device for splicing images |
| US20150228060A1 (en) * | 2012-10-24 | 2015-08-13 | Fuji Xerox Co., Ltd. | Information processing apparatus, information processing method, information processing system, and non-transitory computer readable medium |
-
2015
- 2015-05-19 CN CN201510257323.3A patent/CN106296577B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060238536A1 (en) * | 1999-07-30 | 2006-10-26 | Canon Kabushiki Kaisha | Image synthesis method, image synthesis apparatus, and storage medium |
| JP4552115B2 (en) * | 2004-06-15 | 2010-09-29 | ソニー株式会社 | Image processing apparatus and method, recording medium, and program |
| CN101923709A (en) * | 2009-06-16 | 2010-12-22 | 日电（中国）有限公司 | Image splicing method and equipment |
| US20150228060A1 (en) * | 2012-10-24 | 2015-08-13 | Fuji Xerox Co., Ltd. | Information processing apparatus, information processing method, information processing system, and non-transitory computer readable medium |
| CN103501415A (en) * | 2013-10-01 | 2014-01-08 | 中国人民解放军国防科学技术大学 | Overlap structural deformation-based video real-time stitching method |
| CN104361569A (en) * | 2014-11-11 | 2015-02-18 | 浙江宇视科技有限公司 | Method and device for splicing images |
Non-Patent Citations (3)
| Title |
|---|
| A. CAN 等: "A feature-based technique for joint, linear estimation of high-order image-to-mosaic transformations: mosaicing the curved human retina", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| 荆根强 等: "局部自适应序列图像拼接算法", 《红外与激光工程》 * |
| 蔡丽欢 等: "图像拼接方法及其关键技术研究", 《计算机技术与发展》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020143090A1 (en) * | 2019-01-10 | 2020-07-16 | 深圳市沃特沃德股份有限公司 | Image acquisition method, apparatus and device based on multiple cameras |
| CN109934769A (en) * | 2019-04-26 | 2019-06-25 | 努比亚技术有限公司 | Method, terminal and the storage medium of the long screenshot of screen |
| CN109934769B (en) * | 2019-04-26 | 2023-09-19 | 努比亚技术有限公司 | Method, terminal and storage medium for long screenshot of screen |
| CN113139905A (en) * | 2021-04-29 | 2021-07-20 | 北京百度网讯科技有限公司 | Image splicing method, device, equipment and medium |
| WO2022227773A1 (en) * | 2021-04-29 | 2022-11-03 | 北京百度网讯科技有限公司 | Image splicing method and apparatus, device, and medium |
| CN113139905B (en) * | 2021-04-29 | 2024-02-13 | 北京百度网讯科技有限公司 | Image stitching method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106296577B (en) | 2019-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102521808B (en) | Robust recovery method and system of transform invariant low-rank textures | |
| US20200372609A1 (en) | Super-resolution video reconstruction method, device, apparatus and computer-readable storage medium | |
| CN104903934B (en) | Augmented reality is reproduced based on foreground object | |
| CN108093221B (en) | Suture line-based real-time video splicing method | |
| US10909703B2 (en) | Image processing method, electronic device and computer-readable storage medium | |
| US9495606B2 (en) | Method for product recognition from multiple images | |
| TW200913687A (en) | Moving body image extraction apparatus and program | |
| JP5351971B2 (en) | Method, apparatus and software for determining motion vectors | |
| JP2010122934A (en) | Image processing apparatus, image processing method, and program | |
| CN106296577A (en) | Image split-joint method and image mosaic device | |
| CN110781823B (en) | Screen recording detection method and device, readable medium and electronic equipment | |
| CN107292826A (en) | Image processing equipment, image processing method and image processing apparatus | |
| CN108986569A (en) | A kind of desktop AR interactive learning method and device | |
| CN103473543B (en) | For extracting device, method and the electronic equipment on objects in images border | |
| CN111179159A (en) | Method and device for eliminating target image in video, electronic equipment and storage medium | |
| KR101434776B1 (en) | Method and apparatus for correcting corner point of image and image processing device | |
| US8731326B2 (en) | Object recognition system and method | |
| JP2006350680A (en) | Image processing apparatus, image processing method, and computer program | |
| US9141861B2 (en) | Video image feature generation system and video image feature generation method | |
| CN106611406B (en) | Method for correcting image and image correcting device | |
| US20150227798A1 (en) | Image processing device, image processing method and program | |
| JP2006067541A (en) | Video converting apparatus and method, and recording medium | |
| JPH10149449A (en) | Picture division method, picture identification method, picture division device and picture identification device | |
| CN106569765B (en) | Picture display process and device | |
| CN117173012A (en) | Unsupervised multi-view image generation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |