CN107610051A - The orthograph of unmanned plane image mosaic is as generation method and device - Google Patents
The orthograph of unmanned plane image mosaic is as generation method and device Download PDFInfo
- Publication number
- CN107610051A CN107610051A CN201710865754.7A CN201710865754A CN107610051A CN 107610051 A CN107610051 A CN 107610051A CN 201710865754 A CN201710865754 A CN 201710865754A CN 107610051 A CN107610051 A CN 107610051A
- Authority
- CN
- China
- Prior art keywords
- pixel
- difference
- distance
- group
- mrow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention provides a kind of orthograph of unmanned plane image mosaic as generation method and device, method include:The first overlapping region and the second overlapping region are determined respectively in the first Aerial Images and the second Aerial Images;Determine in the first distance respectively with the central pixel point of the first Aerial Images of each first pixel in the first overlapping region, the second overlapping region each second pixel second distance with the central pixel point of the second Aerial Images respectively;Determine the color difference and structure difference between each group of mutually corresponding pixel;According to each group of mutually corresponding pixel, corresponding second distance determines optimal suture respectively for corresponding first distance, each second pixel institute respectively for corresponding color difference, structure difference and each first pixel institute respectively;The Aerial Images of splicing first and the second Aerial Images are sutured to generate orthograph picture according to optimal.By technical scheme provided by the invention, the orthograph picture of generation, which has, preferably just penetrates effect.
Description
Technical field
The present invention relates to the orthograph picture generation side of technical field of image processing, more particularly to unmanned plane image mosaic
Method and device.
Background technology
The Aerial Images details shot by unmanned plane is enriched, landforms are clear, multiple images that unmanned plane is continuously shot
A wide viewing angle, high-resolution panoramic picture can be generated by carrying out splicing.
At present, when being spliced for two Aerial Images, it usually needs according in the overlapping region of two Aerial Images
Color difference and structure difference between the mutually corresponding pixel of each two determine optimal suture, and then according to determination most
Excellent suture splicing two opens Aerial Images.
In above-mentioned technical proposal, determine only to consider during optimal suture the mutually corresponding pixel of each two in overlapping region
Between color difference and structure difference, a part may be caused just to penetrate the poor image-region of effect in overlapping region and be retained
Into the image of generation so that it is poor that the image of generation is just penetrating effect.
The content of the invention
The embodiments of the invention provide a kind of orthograph of unmanned plane image mosaic as generation method and device, generation
Orthograph picture have preferably just penetrate effect.
In a first aspect, the invention provides a kind of orthograph of unmanned plane image mosaic as generation method, including:
In the first Aerial Images and the second Aerial Images of unmanned plane, the first overlapping region and are determined respectively
Two overlapping regions;
Determine in first overlapping region each first pixel middle imago with first Aerial Images respectively
The first distance between vegetarian refreshments, and determine that each second pixel navigates with described second respectively in second overlapping region
Clap the second distance between the central pixel point of image;
Determine each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference and knot
Structure difference;
According to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure
Difference and each first pixel distinguish corresponding to first distance, each second pixel distinguish corresponding to second
Distance, determine optimal suture;
According to the optimal suture of determination, splice first Aerial Images and second Aerial Images to generate
Orthograph picture.
Preferably,
It is described according to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to colour-difference
Value, structure difference and each first pixel distinguish corresponding to first apart from, each second pixel it is right respectively
The second distance answered, before determining optimal suture, further comprise:
Color weight coefficient and structure ratio coefficient are set;
According to the first distance corresponding to each first pixel difference, and corresponding to each second pixel difference
Second distance, determine each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to distance difference;
Then,
It is described according to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference,
Structure difference and each first pixel distinguish corresponding to the first distance, corresponding to each second pixel distinguishes
Second distance, optimal suture is determined, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first overlapping region or second overlay region
Optimal suture is determined in domain.
Preferably,
It is described according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to colour-difference
Value, color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first overlapping region or second weight
Optimal suture is determined in folded region, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group mutually corresponding to the first pixel and the
Energy value corresponding to distinguishing between two pixels;
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy value, from institute
State in the first overlapping region or second overlapping region and determine at least one candidate's suture;
The energy value according to corresponding to being distinguished each target pixel points on each candidate's suture, calculate each
Candidate's suture distinguish corresponding to energy total value;
Target candidate suture corresponding to least energy total value in each energy total value is defined as optimal seam
Zygonema.
Preferably,
It is described according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to colour-difference
Value, color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group of mutually corresponding first pixel
Energy value corresponding to distinguishing between point and the second pixel, including:
By equation below calculate each group mutually corresponding to corresponded to respectively between the first pixel and the second pixel
Energy value:
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α are characterized
Color weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color corresponding between first pixel and the second pixel
Difference, β characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding between the first pixel and the second pixel
Corresponding structure difference, Ei-distCharacterize i-th group mutually corresponding between the first pixel and the second pixel it is corresponding away from
Deviation value.
Preferably,
The span of the color weight coefficient, including:More than 0 and less than 1;
And/or
The span of the structure ratio coefficient, including:More than 0 and less than 1.
Second aspect, the embodiments of the invention provide a kind of orthograph of unmanned plane image mosaic as generating means,
Including:
Overlapping region determining module, in the first Aerial Images and the second Aerial Images of unmanned plane, distinguishing
Determine the first overlapping region and the second overlapping region;
Apart from determining module, for determining in first overlapping region each first pixel respectively with described first
The first distance between the central pixel point of Aerial Images, and determine each second pixel in second overlapping region
Second distance between the central pixel point of second Aerial Images respectively;
Difference determining module, for determine each group mutually corresponding between the first pixel and the second pixel it is right respectively
The color difference and structure difference answered;
Suture determining module, for according to each group mutually corresponding between the first pixel and the second pixel distinguish
Corresponding color difference, structure difference and each first pixel distinguish corresponding to first distance, each second picture
Vegetarian refreshments distinguish corresponding to second distance, determine optimal suture;
Splicing module, for the optimal suture according to determination, splice first Aerial Images and described
Second Aerial Images are to generate orthograph picture.
Preferably,
Also include:Setup module and computing module;Wherein,
The setup module, for setting color weight coefficient and structure ratio coefficient;
The computing module, for according to each first pixel respectively corresponding to the first distance, and each the
Two pixels respectively corresponding to second distance, determine each group mutually corresponding to divide between the first pixel and the second pixel
Not corresponding distance difference;
Then, the suture determining module, for according to each group mutually corresponding to the first pixel and the second pixel
Between distinguish corresponding to color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference described
Optimal suture is determined in one overlapping region or second overlapping region.
Preferably,
The suture determining module, including:First computing unit, the first determining unit, the second computing unit and second
Determining unit;Wherein,
First computing unit, for according to each group mutually corresponding to institute between the first pixel and the second pixel
Color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference corresponding to respectively, calculate each group of phase
Energy value corresponding to distinguishing corresponding to mutually between the first pixel and the second pixel;
First determining unit, for according to each group mutually corresponding to institute between the first pixel and the second pixel
Energy value corresponding to respectively, determine that at least one candidate sutures from first overlapping region or second overlapping region
Line;
Second computing unit, for right respectively according to each target pixel points institute on each candidate's suture
The energy value answered, calculate each candidate's suture distinguish corresponding to energy total value;
Second determining unit, for the target corresponding to the least energy total value in each energy total value to be waited
Suture is selected to be defined as optimal suture.
Preferably,
First computing unit, for calculating each group of mutually corresponding first pixel and second by equation below
Energy value corresponding to distinguishing between pixel:
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α are characterized
Color weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color corresponding between first pixel and the second pixel
Difference, β characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding between the first pixel and the second pixel
Corresponding structure difference, Ei-distCharacterize i-th group mutually corresponding between the first pixel and the second pixel it is corresponding away from
Deviation value.
Preferably,
The span of the color weight coefficient, including:More than 0 and less than 1;
And/or
The span of the structure ratio coefficient, including:More than 0 and less than 1.
The embodiments of the invention provide a kind of orthograph of unmanned plane image mosaic as generation method and device, the party
In method, by determining the first overlapping region and respectively in the first Aerial Images and the second Aerial Images of unmanned plane
Two overlapping regions, it is understandable, each in each first pixel and the second overlapping region in the first overlapping region
Two pixels correspond;Therefore, each first pixel is taken photo by plane figure with first respectively in the first overlapping region is determined
The first distance between the central pixel point of picture, and determine in the second overlapping region each second pixel respectively with
Second distance between the central pixel point of two Aerial Images, and determine each group of mutually corresponding first pixel and second
Between pixel respectively corresponding to after color difference and structure difference, then can according to each group mutually corresponding to the first pixel
And second between pixel respectively corresponding to color difference, structure difference and each first pixel distinguish corresponding to the
One distance, each second pixel distinguish corresponding to second distance, determine optimal suture, understandable, any picture
Vegetarian refreshments and the distance between the central pixel point on Aerial Images where it are bigger, then explanation includes the image-region of the pixel
The possibility for occurring just penetrating effect difference is higher;Therefore, it is determined that during optimal suture, at the same consider each group mutually corresponding to the
Each pixel in color difference, structure difference and overlapping region corresponding to distinguishing between one pixel and the second pixel
Respectively with the distance between the central pixel point of image where it, according to the optimal suture of determination, splicing in subsequent process
First Aerial Images and the second Aerial Images with generate orthograph as when, the orthograph picture of generation, which has, preferably just penetrates effect.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is a kind of orthograph for unmanned plane image mosaic that one embodiment of the invention provides as the stream of generation method
Cheng Tu;
Fig. 2 is the orthograph for another unmanned plane image mosaic that one embodiment of the invention provides as generation method
Flow chart;
Fig. 3 is a kind of orthograph for unmanned plane image mosaic that one embodiment of the invention provides as the knot of generating means
Structure schematic diagram;
Fig. 4 is the orthograph for another unmanned plane image mosaic that one embodiment of the invention provides as generating means
Structural representation;
Fig. 5 is the orthograph for another unmanned plane image mosaic that one embodiment of the invention provides as generating means
Structural representation.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments, based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained on the premise of creative work is not made, belongs to the scope of protection of the invention.
As shown in figure 1, the embodiments of the invention provide a kind of orthograph of unmanned plane image mosaic as generation method,
Including:
Step 101, in the first Aerial Images and the second Aerial Images of unmanned plane, determine that first is overlapping respectively
Region and the second overlapping region;
Step 102, determine in first overlapping region each first pixel respectively with first Aerial Images
Central pixel point between the first distance, and determine in second overlapping region each second pixel respectively with institute
State the second distance between the central pixel point of the second Aerial Images;
Step 103, determine each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color
Difference and structure difference;
Step 104, according to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color
Difference, structure difference and each first pixel distinguish corresponding to the first distance, each second pixel distinguishes
Corresponding second distance, determine optimal suture;
105 after step, according to the optimal suture of determination, splice first Aerial Images and described second and take photo by plane
Image is to generate orthograph picture.
In the above embodiment of the present invention, by distinguishing in the first Aerial Images and the second Aerial Images of unmanned plane
Determine the first overlapping region and the second overlapping region, it is understandable, each first pixel in the first overlapping region with
Each second pixel in second overlapping region corresponds;Therefore, in the first overlapping region is determined each first
Pixel the first distance between the central pixel point of the first Aerial Images, and determining every in the second overlapping region respectively
One the second pixel second distance between the central pixel point of the second Aerial Images respectively, and determine each group it is mutual
, then can be according to each after color difference corresponding to distinguishing between corresponding first pixel and the second pixel and structure difference
Group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure difference and each the
One pixel distinguish corresponding to first distance, each second pixel distinguish corresponding to second distance, determine optimal seam
Zygonema, understandable, any pixel point and the distance between the central pixel point on Aerial Images where it are bigger, then illustrate
The possibility that effect difference occurs just penetrating in image-region including the pixel is higher;Therefore, it is determined that during optimal suture, simultaneously
Consider each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure difference and
Each pixel the distance between central pixel point with image where it respectively, the basis in subsequent process in overlapping region
The optimal suture determined, splice the first Aerial Images and the second Aerial Images with generate orthograph as when, the orthograph of generation
Preferably effect is just penetrated as having.
In one embodiment of the invention, it is described according to each group mutually corresponding to the first pixel and the second pixel it
Between respectively corresponding to color difference, structure difference and each first pixel distinguish corresponding to first apart from, each
Second pixel distinguish corresponding to second distance, before determining optimal suture, further comprise:
Color weight coefficient and structure ratio coefficient are set;
According to the first distance corresponding to each first pixel difference, and corresponding to each second pixel difference
Second distance, determine each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to distance difference;
Then,
It is described according to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference,
Structure difference and each first pixel distinguish corresponding to the first distance, corresponding to each second pixel distinguishes
Second distance, optimal suture is determined, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first overlapping region or second overlay region
Optimal suture is determined in domain.
In the above embodiment of the present invention, determine each group mutually corresponding between the first pixel and the second pixel
After distance difference corresponding to distinguishing, according to each group mutually corresponding to distinguish between the first pixel and the second pixel
Corresponding color difference, structure difference, distance difference and the color weight coefficient of setting and structure ratio coefficient are in the first weight
Optimal suture is determined in folded region or the second overlapping region;The demand that user can combine practical business scene sets difference big
Small color weight coefficient and structure ratio coefficient, with balance each group mutually corresponding to the first pixel and the second pixel it
Between respectively corresponding color difference and structure difference on determine optimal suture when institute respectively caused by influence intensity.
In one embodiment of the invention, color weight coefficient and/or structure ratio coefficient may be greater than 0 and appointing less than 1
Meaning value.For example, when user goes out colour-difference in the first Aerial Images and the second Aerial Images with reference to practical business demand estimation
When influence intensity is identical caused by when value and structure difference are to determining optimal suture, the value and knot of color weight coefficient can be set
The value of structure weight coefficient is equal, for example color weight coefficient and structure ratio coefficient are disposed as into 0.8;Accordingly, judgement is worked as
Go out color difference relative to structure difference to determine optimal suture when caused by influence intensity it is bigger when, can be set color weight
Coefficient is more than structure ratio coefficient, for example color weight coefficient is arranged into 0.9, and structure ratio coefficient is arranged into 0.4;Conversely
Ground, when influence intensity caused by when judging color difference relative to structure difference to determining optimal suture is smaller, it can set
Put color weight coefficient and be less than structure ratio coefficient, for example color weight coefficient is arranged to 0.3, structure ratio coefficient is set
For 0.8.
In one embodiment of the invention, it is described according to each group mutually corresponding between the first pixel and the second pixel
Color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first weight corresponding to distinguishing
Optimal suture is determined in folded region or second overlapping region, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group mutually corresponding to the first pixel and the
Energy value corresponding to distinguishing between two pixels;
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy value, from institute
State in the first overlapping region or second overlapping region and determine at least one candidate's suture;
The energy value according to corresponding to being distinguished each target pixel points on each candidate's suture, calculate each
Candidate's suture distinguish corresponding to energy total value;
Target candidate suture corresponding to least energy total value in each energy total value is defined as optimal seam
Zygonema.
In the embodiment of the present invention, one group of mutually corresponding energy value corresponding between first pixel and the second pixel
Lower, then the similarity on explanation mutually corresponding first pixel and the second pixel color and structure is of a relatively high, and the
One pixel in the first overlapping region just penetrate effect and the second pixel in a second overlap region just to penetrate effect more flat
Weighing apparatus, therefore, energy value corresponding to each pixel difference is relatively small in each candidate's suture for causing to determine that should try one's best;
Accordingly, the target candidate suture corresponding to the least energy total value in each energy total value is defined as optimal suture,
Subsequently according to optimal suture splicing generation orthograph as when, the first overlapping region and the second weight can be removed according to optimal suture
The relatively poor image-region of effect is just being penetrated in folded region, merely with just penetrating effect in the first Aerial Images and the second Aerial Images
Relatively good a part of image-region splicing generation orthograph picture, the orthograph picture for improving generation just penetrate effect.
Specifically, in one embodiment of the invention, it is described according to each group mutually corresponding to the first pixel and the second picture
Color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference corresponding to distinguishing between vegetarian refreshments, meter
Calculate each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy value, including:
By equation below calculate each group mutually corresponding to corresponded to respectively between the first pixel and the second pixel
Energy value:
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α are characterized
Color weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color corresponding between first pixel and the second pixel
Difference, β characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding between the first pixel and the second pixel
Corresponding structure difference, Ei-distCharacterize i-th group mutually corresponding between the first pixel and the second pixel it is corresponding away from
Deviation value.
In the above embodiment of the present invention, calculate each group mutually corresponding to divide between the first pixel and the second pixel
Not corresponding energy value when, the color difference corresponding to this group of pixel is associated with distance difference, avoid each group of pixel
Point institute corresponding color difference is larger respectively and when causing when distance difference is smaller the energy value that is calculated relatively small, general
A pixel in this group of pixel enters to choose in optimal suture.
Illustrate technical scheme and advantage in order to more clear, below the Aerial Images to be shot to unmanned plane
A and b is spliced exemplified by generating orthograph picture, as shown in Fig. 2 can specifically include following each step:
Step 201, the first overlapping region and the second overlapping region are determined respectively in Aerial Images a and Aerial Images b.
, can be by detecting the characteristic point on Aerial Images a and Aerial Images b, to Aerial Images a in the embodiment of the present invention
Matched with each characteristic point detected respectively on Aerial Images b, with true respectively in Aerial Images a and Aerial Images b
The first overlapping region and the second overlapping region are made, in each first pixel and the second overlapping region in the first overlapping region
Each second pixel correspond.
In order to facilitate description, the embodiment of the present invention is specifically represented with the first overlapping region on Aerial Images a using matrix
It is the matrix A of 5 rows 11 row during each first pixel, is represented with the second overlapping region on Aerial Images b using matrix
It is the matrix B of 5 rows 11 row during each second pixel, and the element a of the row of m rows n-th in matrix AM, nWith in matrix B
The element b that m rows n-th arrangeM, nExemplified by corresponding.
Step 202, each first pixel middle imago with the first Aerial Images respectively is determined in the first overlapping region
The first distance between vegetarian refreshments, and determine the second overlapping region in each second pixel respectively with the second Aerial Images
Second distance between central pixel point.
In the embodiment of the present invention, that is, calculate each pixel aM, nIt is right respectively between Aerial Images a central pixel point
The Euclidean distance A answeredM, n, calculate each pixel bM, nDistinguish between Aerial Images b central pixel point corresponding European
Distance BM, n。
Step 203, determine each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color
Difference and structure difference.
In this distribution embodiment, each group of mutually corresponding first pixel and the second picture can be calculated by equation below
Color difference E corresponding to distinguishing between vegetarian refreshmentscolor(m, n):
Ecolor(m, n)
=[| Ra(m, n)-Rb(m, n) |+| Ga(m, n)-Gb(m, n) |
+|Ba(m, n)-Bb(m, n) |]/3
Wherein, Ecolor(m, n) characterizes two the first pixel a that m rows n-th arrange in matrix A and matrix BM, nWith the second picture
Vegetarian refreshments bM, nBetween color difference, Ra(m, n) characterizes the first pixel a that m rows n-th arrange in matrix AM, nCorresponding
R values, Ga(m, m) characterizes the first pixel a that m rows n-th arrange in matrix AM, nCorresponding G values, Ba(m, n) characterizes matrix
The first pixel a that m rows n-th arrange in AM, nCorresponding B values;Rb(m, n) characterizes m rows n-th arrange in matrix B one
Individual second pixel bM, mCorresponding R values, Gb(m, n) characterizes the second pixel b that m rows n-th arrange in matrix BM, nInstitute
Corresponding G values, Bb(m, n) characterizes the second pixel b that m rows n-th arrange in matrix BM, nCorresponding B values.
In the embodiment of the present invention, each two mutually corresponding first can be calculated by changing Sobel operators gradient to realize
Structure difference corresponding to distinguishing between pixel and the second pixel, can be specifically diagonal centered on current pixel point
The correlation of 4 edge pixel points in line direction, the template in x directions and y directions is rewritten into respectively matrix Sx:[(-2,0,2)、
(- 1,0,1), (- 2,0,2)] and matrix Sy:[(- 2, -1,2), (0,0,0), (2,1,2)];So as to according to matrix SxWith matrix Sy
Calculate each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to structure difference.
Step 204, color weight coefficient and structure ratio coefficient are set.
In the embodiment of the present invention, color weight coefficient and structure ratio coefficient can be entered by user with reference to practical business scene
Row is rationally set, the span of color weight coefficient and structure ratio coefficient should positioned at 0 to 1 between, such as, can general
Color weight coefficient and structure ratio coefficient are disposed as 0.8.
Step 205, the first distance according to corresponding to each first pixel difference, and each second pixel point
Not corresponding second distance, determine each group mutually corresponding to distinguish between the first pixel and the second pixel it is corresponding away from
Deviation value.
It will be apparent that each group of mutually corresponding first pixel aM, nWith the second pixel bM, nCorresponding to distinguishing away from
Deviation value can be the first distance A corresponding to the first pixel in the mutually corresponding pixel of the groupM, nIt is corresponding with the second pixel
Second distance BM, nBetween difference absolute value Ei-dist。
Step 206, according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to face
Value of chromatism, color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group mutually corresponding first
Energy value corresponding to distinguishing between pixel and the second pixel.
Step 206 can specifically calculate each group of mutually corresponding first pixel a by equation belowM, nWith the second picture
Vegetarian refreshments bM, nBetween respectively corresponding to energy value:
Wherein, EiI-th group of mutually corresponding first pixel aM, nWith the second pixel bM, nBetween corresponding energy value,
α characterizes color weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding first pixel and aM, nSecond pixel bM, nBetween institute
Corresponding color difference, β characterize structure ratio coefficient, Ei-geometryCharacterize i-th group of mutually corresponding first pixel aM, nWith
Two pixel bM, nBetween corresponding structure difference, Ei-distCharacterize i-th group of mutually corresponding first pixel aM, nWith the second picture
Vegetarian refreshments bM, nBetween corresponding distance difference.
Step 207, according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy
Value, at least one candidate's suture is determined from the first overlapping region or the second overlapping region.
, can be to exemplified by least one candidate's suture is determined in the first overlapping region in the embodiment of the present invention
Each first pixel a in one overlapping regionM, nCarry out News Search.Specifically, can be first by first in the first overlapping region
Capable each first pixel is directed to each initial reconnaissance respectively as the initial reconnaissance of candidate's suture, can edge
Row longitudinal searching where it, it is the pixel a in the first overlapping region with initial reconnaissance1,3Exemplified by, the row longitudinal direction where along it
During search, it can will be not more than each first picture of setting numerical value (such as 2) in the second row with the distance for arranging the 3rd row where it
Vegetarian refreshments is defined as candidate pixel point, i.e., by a2,1、a2,2、a2,3、a2,4And a2,5It is defined as candidate pixel point, by this 5 candidate pixels
A minimum candidate pixel of energy value is corresponded in point click and enter and elect a as1,3An object pixel in candidate's suture at place
Point, this, which is sentenced, determines to correspond to initial reconnaissance a in a second row1,3Target pixel points be a2,4Exemplified by, then continue with a2,4Institute
Row carry out longitudinal searching in the same way, until each first pixel of the 2nd row to the 5th row from the first overlapping region
One and initial reconnaissance a are determined in point respectively1,3Untill corresponding target pixel points, here specifically with determine with initially
Reconnaissance a1,3Corresponding each target pixel points include a2,4、a3,4、a4,2、a5,1Exemplified by, the first pixel a1,3、a2,4、a3,4、
a4,2、a5,1The line formed in the first overlapping region is then initial reconnaissance a1,3Corresponding candidate's suture.
Step 208, the energy total value of each candidate's suture is calculated.
In the embodiment of the present invention, each first pixel included with candidate's suture is a successively1,3、a2,4、
a3,4、a4,2、a5,1Exemplified by, when calculating energy total value, as calculate a1,3With b1,3Between corresponding energy value, a2,4With b2,4It
Between corresponding energy value, a3,4With b3,4Between corresponding energy value, a4,2With b4,2Between corresponding energy value, a5,1With
b5,1Between corresponding energy value sum.
Step 209, the target candidate suture corresponding to the least energy total value in each energy total value is defined as most
Excellent suture.
Step 210, according to the optimal suture of determination, Aerial Images a and Aerial Images b is spliced to generate orthograph picture.
In the embodiment of the present invention, a is included with the optimal suture of determination1,3、a2,4、a3,4、a4,2、a5,15 pixels, and
By the first overlapping region be exemplified by Aerial Images a right side area, the second overlapping region are Aerial Images b left fields, then
The image-region that each pixel in Aerial Images a on the right side of optimal suture is formed can be directed to and carry out delete processing,
Simultaneously for being located at b in Aerial Images bIsosorbide-5-Nitrae、b2,5、b3,5、b4,3、b5,2What each pixel on the left of the line corresponding to 5 was formed
Image-region carries out delete processing, is correspondingly spliced into just using the Aerial Images a after progress delete processing respectively and Aerial Images b
Penetrate image.
It should be appreciated that splicing is corresponded to generate using the Aerial Images a after progress delete processing respectively and Aerial Images b
Orthograph as when, can be by way of multi-band fusion to carrying out Aerial Images a and Aerial Images b after delete processing respectively
Carry out corresponding splicing.
As shown in figure 3, the embodiments of the invention provide a kind of orthograph of unmanned plane image mosaic as generating means,
Including:
Overlapping region determining module 301, in the first Aerial Images and the second Aerial Images of unmanned plane, dividing
The first overlapping region and the second overlapping region are not determined;
Apart from determining module 302, for determine in first overlapping region each first pixel respectively with it is described
The first distance between the central pixel point of first Aerial Images, and determine each second picture in second overlapping region
The vegetarian refreshments second distance between the central pixel point of second Aerial Images respectively;
Difference determining module 303, for determining each group mutual corresponding between first pixel and the second pixel points
Not corresponding color difference and structure difference;
Suture determining module 304, for according to each group mutually corresponding between the first pixel and the second pixel
Color difference, structure difference and each first pixel corresponding to respectively distinguish corresponding to first apart from, each the
Two pixels distinguish corresponding to second distance, determine optimal suture;
Splicing module 305, for the optimal suture according to determination, splice first Aerial Images and institute
The second Aerial Images are stated to generate orthograph picture.
As shown in figure 4, in a preferred embodiment of the invention, described device, in addition to:Setup module 401 and calculating mould
Block 402;Wherein,
The setup module 401, for setting color weight coefficient and structure ratio coefficient;
The computing module 402, for the first distance according to corresponding to each first pixel difference, and each
Second distance corresponding to second pixel difference, determine each group of mutually corresponding institute between first pixel and the second pixel
Distance difference corresponding to respectively;
Then, the suture determining module 304, for according to each group mutually corresponding to the first pixel and the second pixel
Color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference are described corresponding to distinguishing between point
Optimal suture is determined in first overlapping region or second overlapping region.
As shown in figure 5, in a preferred embodiment of the invention, the suture determining module, including:First computing unit
3041st, the first determining unit 3042, the second computing unit 3043 and the second determining unit 3044;Wherein,
First computing unit 3041, for according to each group mutually corresponding to the first pixel and the second pixel it
Between distinguish corresponding to color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate it is each
Energy value corresponding to distinguishing corresponding to group is mutual between first pixel and the second pixel;
First determining unit 3042, for according to each group mutually corresponding to the first pixel and the second pixel it
Between distinguish corresponding to energy value, determine at least one candidate from first overlapping region or second overlapping region
Suture;
Second computing unit 3043, for being divided according to each target pixel points on each candidate's suture
Not corresponding energy value, calculate each candidate's suture distinguish corresponding to energy total value;
Second determining unit 3044, for the mesh corresponding to by the least energy total value in each energy total value
Mark candidate's suture is defined as optimal suture.
In a preferred embodiment of the invention, first computing unit 3041 is each for being calculated by equation below
Energy value corresponding to distinguishing corresponding to group is mutual between first pixel and the second pixel:
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α are characterized
Color weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color corresponding between first pixel and the second pixel
Difference, β characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding between the first pixel and the second pixel
Corresponding structure difference, Ei-distCharacterize i-th group mutually corresponding between the first pixel and the second pixel it is corresponding away from
Deviation value.
In a preferred embodiment of the invention, the span of the color weight coefficient, including:More than 0 and less than 1;
And/or the span of the structure ratio coefficient, including:More than 0 and less than 1.
The contents such as the information exchange between each unit, implementation procedure in said apparatus, due to implementing with the inventive method
Example is based on same design, and particular content can be found in the narration in the inventive method embodiment, and here is omitted.
The embodiments of the invention provide a kind of computer-readable recording medium, including execute instruction, when the computing device of storage control
During the execute instruction, the storage control performs the method provided in any one embodiment of the invention.
The embodiments of the invention provide a kind of storage control, including:Processor, memory and bus;
The processor is connected with the memory by the bus;
The memory, when the storage control is run, memory storage is described described in the computing device
Execute instruction, so that the storage control performs the method provided in any one embodiment of the invention.
In summary, each embodiment of the present invention at least has the advantages that:
1st, in one embodiment of the invention, by distinguishing in the first Aerial Images and the second Aerial Images of unmanned plane
Determine the first overlapping region and the second overlapping region, it is understandable, each first pixel in the first overlapping region with
Each second pixel in second overlapping region corresponds;Therefore, in the first overlapping region is determined each first
Pixel the first distance between the central pixel point of the first Aerial Images, and determining every in the second overlapping region respectively
One the second pixel second distance between the central pixel point of the second Aerial Images respectively, and determine each group it is mutual
, then can be according to each after color difference corresponding to distinguishing between corresponding first pixel and the second pixel and structure difference
Group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure difference and each the
One pixel distinguish corresponding to first distance, each second pixel distinguish corresponding to second distance, determine optimal seam
Zygonema, understandable, any pixel point and the distance between the central pixel point on Aerial Images where it are bigger, then illustrate
The possibility that effect difference occurs just penetrating in image-region including the pixel is higher;Therefore, it is determined that during optimal suture, simultaneously
Consider each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure difference and
Each pixel the distance between central pixel point with image where it respectively, the basis in subsequent process in overlapping region
The optimal suture determined, splice the first Aerial Images and the second Aerial Images with generate orthograph as when, the orthograph of generation
Preferably effect is just penetrated as having.
2nd, in one embodiment of the invention, the demand that user can combine practical business scene sets different size of color weight
Coefficient and structure ratio coefficient, with balance each group mutually corresponding between the first pixel and the second pixel respectively corresponding to
When color difference and structure difference are on determining optimal suture institute respectively caused by influence intensity.
3rd, in one embodiment of the invention, one group mutually corresponding to it is corresponding between the first pixel and the second pixel
Energy value is lower, then explanation mutually corresponding to similarity on the first pixel and the second pixel color and structure relatively
Height, and the first pixel in the first overlapping region just penetrate effect and the second pixel in a second overlap region just penetrate effect
Fruit more balances, therefore, energy value phase corresponding to each pixel difference in each candidate's suture for causing to determine that should try one's best
To smaller;Accordingly, the target candidate suture corresponding to the least energy total value in each energy total value is defined as optimal
Suture, subsequently according to it is optimal suture splicing generation orthograph as when, can according to optimal suture remove the first overlapping region
With the relatively poor image-region of effect is just being penetrated in the second overlapping region, merely with the first Aerial Images and the second Aerial Images
Just penetrating the relatively good a part of image-region splicing generation orthograph picture of effect, the orthograph picture for improving generation just penetrates effect
Fruit.
4th, in one embodiment of the invention, each group of mutually corresponding institute between first pixel and the second pixel is calculated
It is corresponding to respectively during energy value, the color difference corresponding to this group of pixel is associated with distance difference, avoid each group of picture
Vegetarian refreshments respectively corresponding color difference it is larger and when causing when distance difference is smaller the energy value that is calculated relatively small,
A pixel in this group of pixel is entered to choose in optimal suture.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity
Or operation makes a distinction with another entity or operation, and not necessarily require or imply and exist between these entities or operation
Any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant be intended to it is non-
It is exclusive to include, so that process, method, article or equipment including a series of elements not only include those key elements,
But also the other element including being not expressly set out, or also include solid by this process, method, article or equipment
Some key elements.In the absence of more restrictions, the key element limited by sentence " including one ", is not arranged
Except other identical factor in the process including the key element, method, article or equipment being also present.
It is last it should be noted that:Presently preferred embodiments of the present invention is the foregoing is only, is merely to illustrate the skill of the present invention
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made within the spirit and principles of the invention,
Equivalent substitution, improvement etc., are all contained in protection scope of the present invention.
Claims (10)
1. a kind of orthograph of unmanned plane image mosaic is as generation method, it is characterised in that including:
In the first Aerial Images and the second Aerial Images of unmanned plane, the first overlapping region and the second weight are determined respectively
Folded region;
Determine in first overlapping region each first pixel central pixel point with first Aerial Images respectively
Between the first distance, and determine in second overlapping region that each second pixel is taken photo by plane figure with described second respectively
Second distance between the central pixel point of picture;
Determine each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference and structure it is poor
Value;
According to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure difference
And each first pixel distinguish corresponding to first distance, each second pixel distinguish corresponding to second away from
From determining optimal suture;
According to the optimal suture of determination, splice first Aerial Images and second Aerial Images are just penetrated with generating
Image.
2. according to the method for claim 1, it is characterised in that
It is described according to each group mutually corresponding between the first pixel and the second pixel distinguish corresponding to color difference, tie
Structure difference and each first pixel distinguish corresponding to the first distance, each second pixel distinguish corresponding to the
Two distances, before determining optimal suture, further comprise:
Color weight coefficient and structure ratio coefficient are set;
According to the first distance corresponding to each first pixel difference, and second corresponding to each second pixel difference
Distance, determine each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to distance difference;
Then,
It is described according to each group mutually corresponding between the first pixel and the second pixel respectively corresponding to color difference, structure
Difference and each first pixel distinguish corresponding to first distance, each second pixel distinguish corresponding to second
Distance, optimal suture is determined, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, color weigh
Weight coefficient, structure difference, structure ratio coefficient and distance difference are in first overlapping region or second overlapping region
Determine optimal suture.
3. according to the method for claim 2, it is characterised in that
It is described according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first overlapping region or second overlay region
Optimal suture is determined in domain, including:
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, color weigh
Weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group of mutually corresponding first pixel and the second picture
Energy value corresponding to distinguishing between vegetarian refreshments;
According to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy value, from described the
At least one candidate's suture is determined in one overlapping region or second overlapping region;
The energy value according to corresponding to being distinguished each target pixel points on each candidate's suture, calculate described in each
Candidate's suture distinguish corresponding to energy total value;
Target candidate suture corresponding to least energy total value in each energy total value is defined as optimal suture.
4. according to the method for claim 3, it is characterised in that
It is described according to each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to color difference, face
Color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group mutually corresponding to the first pixel and the
Energy value corresponding to distinguishing between two pixels, including:
By equation below calculate each group mutually corresponding to distinguish between the first pixel and the second pixel corresponding to energy
Value:
<mrow>
<msub>
<mi>E</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mo>&lsqb;</mo>
<mi>&alpha;</mi>
<mo>*</mo>
<msubsup>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<mi>&beta;</mi>
<mo>*</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>g</mi>
<mi>e</mi>
<mi>o</mi>
<mi>m</mi>
<mi>e</mi>
<mi>t</mi>
<mi>r</mi>
<mi>y</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>*</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>d</mi>
<mi>i</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<mo>&rsqb;</mo>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mi>&alpha;</mi>
<mo>+</mo>
<mi>&beta;</mi>
<mo>+</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α characterize color power
Weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color difference corresponding between first pixel and the second pixel, β
Characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding to it is corresponding between the first pixel and the second pixel
Structure difference, Ei-distCharacterize i-th group of mutually corresponding range difference corresponding between first pixel and the second pixel
Value.
5. according to any described method in claim 2 to 4, it is characterised in that
The span of the color weight coefficient, including:More than 0 and less than 1;
And/or
The span of the structure ratio coefficient, including:More than 0 and less than 1.
6. a kind of orthograph of unmanned plane image mosaic is as generating means, it is characterised in that including:
Overlapping region determining module, in the first Aerial Images and the second Aerial Images of unmanned plane, determining respectively
Go out the first overlapping region and the second overlapping region;
Apart from determining module, for determining that each first pixel is taken photo by plane with described first respectively in first overlapping region
The first distance between the central pixel point of image, and determine that each second pixel is distinguished in second overlapping region
Second distance between the central pixel point of second Aerial Images;
Difference determining module, for determine each group mutually corresponding between the first pixel and the second pixel respectively corresponding to
Color difference and structure difference;
Suture determining module, for according to each group mutually corresponding to corresponded to respectively between the first pixel and the second pixel
Color difference, structure difference and each first pixel distinguish corresponding to first distance, each second pixel
Second distance corresponding to distinguishing, determine optimal suture;
Splicing module, for the optimal suture according to determination, splice first Aerial Images and described second
Aerial Images are to generate orthograph picture.
7. device according to claim 6, it is characterised in that
Also include:Setup module and computing module;Wherein,
The setup module, for setting color weight coefficient and structure ratio coefficient;
The computing module, for the first distance according to corresponding to each first pixel difference, and each second picture
Second distance corresponding to vegetarian refreshments difference, determine that each group of mutually corresponding institute between first pixel and the second pixel is right respectively
The distance difference answered;
Then, the suture determining module, for according to each group mutually corresponding between the first pixel and the second pixel
Color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference are in first weight corresponding to distinguishing
Optimal suture is determined in folded region or second overlapping region.
8. device according to claim 7, it is characterised in that
The suture determining module, including:First computing unit, the first determining unit, the second computing unit and second determine
Unit;Wherein,
First computing unit, for according to each group mutually corresponding to distinguish between the first pixel and the second pixel
Corresponding color difference, color weight coefficient, structure difference, structure ratio coefficient and distance difference, calculate each group it is mutually right
Energy value corresponding to distinguishing between the first pixel and the second pixel answered;
First determining unit, for according to each group mutually corresponding to distinguish between the first pixel and the second pixel
Corresponding energy value, at least one candidate's suture is determined from first overlapping region or second overlapping region;
Second computing unit, for according to corresponding to being distinguished each target pixel points on each candidate's suture
Energy value, calculate each candidate's suture distinguish corresponding to energy total value;
Second determining unit, for the target candidate corresponding to the least energy total value in each energy total value to be stitched
Zygonema is defined as optimal suture.
9. device according to claim 8, it is characterised in that
First computing unit, for calculating each group of mutually corresponding first pixel and the second pixel by equation below
Energy value corresponding to distinguishing between point:
<mrow>
<msub>
<mi>E</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mo>&lsqb;</mo>
<mi>&alpha;</mi>
<mo>*</mo>
<msubsup>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<mi>&beta;</mi>
<mo>*</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>g</mi>
<mi>e</mi>
<mi>o</mi>
<mi>m</mi>
<mi>e</mi>
<mi>t</mi>
<mi>r</mi>
<mi>y</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>*</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>d</mi>
<mi>i</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<mo>&rsqb;</mo>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mi>&alpha;</mi>
<mo>+</mo>
<mi>&beta;</mi>
<mo>+</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>o</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein, EiI-th group of mutually corresponding energy value corresponding between first pixel and the second pixel, α characterize color power
Weight coefficient, Ei-colorCharacterize i-th group of mutually corresponding color difference corresponding between first pixel and the second pixel, β
Characterize structure ratio coefficient, Ei-geometryCharacterize i-th group mutually corresponding to it is corresponding between the first pixel and the second pixel
Structure difference, Ei-distCharacterize i-th group of mutually corresponding range difference corresponding between first pixel and the second pixel
Value.
10. according to any described device in claim 7 to 9, it is characterised in that
The span of the color weight coefficient, including:More than 0 and less than 1;
And/or
The span of the structure ratio coefficient, including:More than 0 and less than 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710865754.7A CN107610051A (en) | 2017-09-22 | 2017-09-22 | The orthograph of unmanned plane image mosaic is as generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710865754.7A CN107610051A (en) | 2017-09-22 | 2017-09-22 | The orthograph of unmanned plane image mosaic is as generation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107610051A true CN107610051A (en) | 2018-01-19 |
Family
ID=61061714
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710865754.7A Pending CN107610051A (en) | 2017-09-22 | 2017-09-22 | The orthograph of unmanned plane image mosaic is as generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107610051A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110837839A (en) * | 2019-11-04 | 2020-02-25 | 嘉兴职业技术学院 | High-precision unmanned aerial vehicle orthoimage manufacturing and data acquisition method |
WO2022170824A1 (en) * | 2021-02-09 | 2022-08-18 | 北京迈格威科技有限公司 | Image splicing processing method and apparatus, electronic system and device, and readable medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103533266A (en) * | 2013-10-01 | 2014-01-22 | 中国人民解放军国防科学技术大学 | 360-degree stitched-type panoramic camera with wide view field in vertical direction |
CN106204437A (en) * | 2016-06-28 | 2016-12-07 | 深圳市凌云视迅科技有限责任公司 | A kind of image interfusion method |
CN107146213A (en) * | 2017-05-08 | 2017-09-08 | 西安电子科技大学 | Unmanned plane image split-joint method based on suture |
-
2017
- 2017-09-22 CN CN201710865754.7A patent/CN107610051A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103533266A (en) * | 2013-10-01 | 2014-01-22 | 中国人民解放军国防科学技术大学 | 360-degree stitched-type panoramic camera with wide view field in vertical direction |
CN106204437A (en) * | 2016-06-28 | 2016-12-07 | 深圳市凌云视迅科技有限责任公司 | A kind of image interfusion method |
CN107146213A (en) * | 2017-05-08 | 2017-09-08 | 西安电子科技大学 | Unmanned plane image split-joint method based on suture |
Non-Patent Citations (2)
Title |
---|
LE YU,ET AL.: "Towards the automatic selection of optimal seam line locations when merging optical remote-sensing images", 《INTERNATIONAL JOURNAL OF REMOTE SENSING》 * |
方贤勇 等: "图像拼接的改进算法", 《计算机辅助设计与图形学学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110837839A (en) * | 2019-11-04 | 2020-02-25 | 嘉兴职业技术学院 | High-precision unmanned aerial vehicle orthoimage manufacturing and data acquisition method |
CN110837839B (en) * | 2019-11-04 | 2023-09-26 | 嘉兴职业技术学院 | High-precision unmanned aerial vehicle orthographic image manufacturing and data acquisition method |
WO2022170824A1 (en) * | 2021-02-09 | 2022-08-18 | 北京迈格威科技有限公司 | Image splicing processing method and apparatus, electronic system and device, and readable medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | RoadNet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images | |
CN105205781B (en) | Transmission line of electricity Aerial Images joining method | |
CN105096283B (en) | The acquisition methods and device of panoramic picture | |
CN106791623A (en) | A kind of panoramic video joining method and device | |
CN108021923A (en) | A kind of image characteristic extracting method for deep neural network | |
CN109829853A (en) | A kind of unmanned plane image split-joint method | |
CN105787876B (en) | One kind being based on the matched panoramic video method for automatically split-jointing of SURF signature tracking | |
CN104820965A (en) | Geocoding-free rapid image splicing method of low-altitude unmanned plane | |
CN103985133A (en) | Search method and system for optimal splicing lines among images based on graph-cut energy optimization | |
CN103258321A (en) | Image stitching method | |
CN106504194A (en) | A kind of image split-joint method based on most preferably splicing plane and local feature | |
CN110490271A (en) | Images match and joining method, device, system, readable medium | |
CN109949227A (en) | Image split-joint method, system and electronic equipment | |
CN107886512A (en) | A kind of method for determining training sample | |
CN110163208A (en) | A kind of scene character detecting method and system based on deep learning | |
CN105488777A (en) | System and method for generating panoramic picture in real time based on moving foreground | |
WO2022042352A1 (en) | Image recognition method, electronic device and readable storage medium | |
CN108171735A (en) | 1,000,000,000 pixel video alignment schemes and system based on deep learning | |
CN110443170A (en) | A kind of human body key point determines method, apparatus and electronic equipment | |
CN107610051A (en) | The orthograph of unmanned plane image mosaic is as generation method and device | |
CN106331848A (en) | Panoramic video identification method and device, and video playing method and device | |
CN106327531A (en) | Panorama video identification method and device, and video playing method and device | |
CN116596815A (en) | Image stitching method based on multi-stage alignment network | |
CN105893578A (en) | Method and device for selecting photos | |
CN115860139A (en) | Deep learning-based multi-scale ship target detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |
|
RJ01 | Rejection of invention patent application after publication |