CN109685839A - Image alignment method, mobile terminal and computer storage medium - Google Patents
Image alignment method, mobile terminal and computer storage medium Download PDFInfo
- Publication number
- CN109685839A CN109685839A CN201811565425.1A CN201811565425A CN109685839A CN 109685839 A CN109685839 A CN 109685839A CN 201811565425 A CN201811565425 A CN 201811565425A CN 109685839 A CN109685839 A CN 109685839A
- Authority
- CN
- China
- Prior art keywords
- image
- feature point
- fisrt feature
- data
- alignment method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of image alignment method, mobile terminal and calculate machine storage medium.Image alignment method includes: to obtain the first image and at least second image;Extract multiple fisrt feature points of the first image and multiple second feature points of the second image;The confidence level for obtaining the second feature point Yu the fisrt feature point filters out the confidence bit in the second feature point of default confidence range;Transformation parameter is calculated according to fisrt feature point and the second feature point filtered out;Multiple second feature points are handled according to transformation parameter, to obtain third image.By above-mentioned image alignment method, automatic aligning can be carried out to image, to obtain the image of multiple alignment.
Description
Technical field
This application involves technical field of image processing, more particularly to a kind of image alignment method, mobile terminal and meter
Calculation machine storage medium.
Background technique
With being constantly progressive for image processing techniques, the equipment for shooting image is also constantly updated.Current photographic equipment is
Through quickly continuous shooting can be carried out to scenery, to obtain multiple images.
But when user uses photographic equipment, due to environmental change acutely or the unconscious body of user itself it is mobile from
And multiple images obtained in Same Scene is caused different degrees of offset occur.These shake and shake all can be to multiple images
The video or dynamic image of synthesis have an adverse effect, such as situations such as restarting, fuzzy occur in the video or dynamic image of synthesis.
Summary of the invention
This application provides a kind of image alignment method, mobile terminal and computer storage medium, the skill mainly solved
Art problem is how to prevent environmental change acutely or the unconscious body of user itself is mobile so as to cause in same field
There is the case where different degrees of offset in multiple images that scape obtains.
In order to solve the above technical problems, this application provides a kind of image alignment method, described image alignment schemes include:
Obtain the first image and at least second image;
Extract multiple fisrt feature points of the first image and multiple second feature points of second image;
The confidence level for obtaining the second feature point Yu the fisrt feature point filters out the confidence bit in pre-seting
The second feature point of reliability range;
Transformation parameter is calculated according to the fisrt feature point and the second feature point filtered out;
Multiple second feature points are handled according to the transformation parameter, to obtain third image.On solving
State technical problem, present invention also provides a kind of mobile terminal, the mobile terminal include processor and with the processor
The memory of coupling, camera module;
Wherein, the camera module is for obtaining the first image and second image;
The memory is for storing program data, and the processor is for executing described program data to realize as above-mentioned
Image alignment method.
In order to solve the above technical problems, the computer storage is situated between present invention also provides a kind of computer storage medium
Matter is for storing program data, and described program data are when being executed by processor, to realize such as above-mentioned image alignment method.
Compared with prior art, the beneficial effect of the application is: obtaining the first image and at least second image;It extracts
Multiple fisrt feature points of first image and multiple second feature points of the second image;Obtain the second feature point and described the
The confidence level of one characteristic point filters out the confidence bit in the second feature point of default confidence range;According to fisrt feature
Point and the second feature point filtered out calculate transformation parameter;Multiple second feature points are handled according to transformation parameter,
To obtain third image.After obtaining characteristic point, using the first image as reference picture, according to high the first image and second of confidence level
The characteristic point of image calculates transformation parameter;According to transformation parameter, by all characteristic point coordinate transforming data of the second image, with life
At the third image with the first image alignment.Therefore, by above-mentioned image alignment method, can at least one second image into
Row adjustment, to obtain the image with the first image alignment.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.Wherein:
Fig. 1 is the flow diagram of the application image alignment method first embodiment;
Fig. 2 is the flow diagram of the application image alignment method second embodiment;
Fig. 3 is the flow diagram of the application image alignment method 3rd embodiment;
Fig. 4 is the flow diagram of the application image alignment method fourth embodiment;
Fig. 5 is the flow diagram for obtaining third image in Fig. 4 in image alignment method;
Fig. 6 is the structural schematic diagram of one embodiment of the application mobile terminal;
Fig. 7 is the structural schematic diagram of one embodiment of the application computer storage medium.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiment of the application, instead of all the embodiments.According to
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Present applicant proposes a kind of image alignment methods, and the batch of multiple images may be implemented by the image alignment method
Processing;For example, image alignment method through this embodiment may be implemented and be used for multiple image synthetic videos or dynamic image
Preceding automatic aligning.Specifically referring to Figure 1, Fig. 1 is the flow diagram of the application image alignment method first embodiment.
The image alignment method of the present embodiment is applied to can be used for shooting the mobile terminal of image, in the field of terminal, moves
Dynamic terminal can be the intelligent terminals such as smart phone, tablet computer, photographic camera;In the field of operating system, mobile terminal can be taken
Carry Android operation system or IOS operating system.
As shown in Figure 1, the image alignment method of the present embodiment the following steps are included:
S11: the first image and at least second image are obtained.
Wherein, multiple images of acquisition for mobile terminal, and one image of acquisition is set as the image of benchmark in multiple images, it should
Benchmark image i.e. the first image.Remaining image in multiple images is the second image, and mobile terminal will at least second image
It is converted according to the first image, to realize multiple image alignments.
Mobile terminal can obtain the first image and at least second image, i.e. camera in real time by camera module
Mould group can be used for being continuously shot multiple images, and mobile terminal is using first image in multiple images as the first figure of benchmark
Picture, remaining image is as the second image.Further, mobile terminal can also preset the image preset after number in continuous shooting function
As the first image of benchmark, remaining image is used as the second image.
Mobile terminal can also obtain multiple images from storage medium, and obtain the first image and needs as benchmark
At least second image for transformation, storage medium can be USB flash disk, mobile hard disk etc..Further, mobile terminal can also be from mutual
Similar image is downloaded in networking, and the first image and at least second image of benchmark are provided as according to download time.
Mobile terminal carries out the first image and the second image after getting the first image and at least second image
Pretreatment.In image analysis processing, pre-process for the interference or noise to eliminating in the first image and the second image, from
And improve the reliability and accuracy of feature extraction in following step.
For example, work as acquisition for mobile terminal is facial image, the pretreatment to facial image may include face righting, people
The processing methods such as face image enhancing, and normalization.
S12: multiple fisrt feature points of the first image and multiple second feature points of the second image are extracted.
Wherein, mobile terminal extracts multiple fisrt feature points of the first image, which is used as the
The main mark of one image can be used for the reference marker as the second image.The fisrt feature point of the present embodiment can wrap
Include the one or more of color characteristic, textural characteristics, shape feature or spatial relation characteristics.
Mobile terminal extract fisrt feature point method can for Fourier converter technique, Wavelet transforms (Gabor),
Wavelet Transform, least square method, edge direction histogram method or according to texture feature extraction of Tamura textural characteristics etc.
One of method.
Wherein, mobile terminal extracts multiple second feature points of the second image, extracts the mode and extraction of second feature point
The mode of the fisrt feature point of first image is identical, and details are not described herein.
S13: obtaining the confidence level of second feature point and fisrt feature point, in confidence bit in default confidence range
When, extract corresponding second feature point.
Wherein, mobile terminal extracts fisrt feature point and second feature point, and the default confidence level according to fisrt feature point
Range.In the present embodiment, according to coordinate data, confidence level can be for fisrt feature point on the first image and in the second image
On second feature point coordinate distance.
Mobile terminal extracts each fisrt feature point respectively, then traverses all second feature points, obtains multiple groups the
The confidence level of two characteristic points and fisrt feature point, and judge the confidence level of every group of second feature point and fisrt feature point whether pre-
If confidence range in.If so, extracting the corresponding second feature point of the confidence level.
S14: transformation parameter is obtained according to fisrt feature point and related second feature point.
Wherein, mobile terminal extracts multiple groups fisrt feature point and corresponding second feature point, and to above-mentioned fisrt feature point
Processing calculating is carried out with corresponding second feature point, to obtain the change for being adapted to multiple groups fisrt feature point and related second feature point
Change parameter.
Mobile terminal according to the transformation parameter, by the second feature point transformation on the second image to corresponding fisrt feature
The same or similar coordinate position of point.
S15: according to transformation parameter, multiple second feature points are converted, to obtain third image.
Wherein, after acquisition for mobile terminal transformation parameter, the second feature on the second image is clicked through according to the transformation parameter
Row transformation, transformed multiple second feature points then combined to obtain third image.
In the present embodiment, the first image of acquisition for mobile terminal and at least second image, and to the first image and
Two images are pre-processed, so that the characteristic point of the first image and the second image is easier to extract;Extract fisrt feature point and the
After two characteristic points, related second spy of the acquisition for mobile terminal to the confidence level of each fisrt feature point in default confidence range
Point is levied, and transformation parameter is obtained to corresponding related second feature point according to multiple groups fisrt feature point, to obtain the second image
Transform to the transformation parameter of the first image;Finally, mobile terminal converts multiple second feature points, according to transformation parameter to obtain
Third image;Wherein, third image is according to transformed second image of the first image;By above-mentioned image alignment method, move
Dynamic terminal can carry out automatic aligning to remaining image according to benchmark image, to obtain multiple figures being aligned with benchmark image
Picture.
Present invention also provides another image alignment methods, specifically refer to Fig. 2, and Fig. 2 is the application image alignment side
The flow diagram of method second embodiment.
On the basis of the step S11 of above-mentioned method for managing resource first embodiment and step S12, the image of the present embodiment
Alignment schemes further comprise following steps:
S21: the first image and at least one second image are obtained.
S22: the first image and the second image are subjected to gray proces.
Wherein, mobile terminal further carries out gray proces to the first image and the second image, to improve feature extraction
Accuracy.
Since the picture that the prior art summarizes shooting is mostly color image, the color of each pixel in color image have R,
G, tri- components of B determine, and each component has 255 kinds of values desirable, and such a pixel can have more than 1,600 ten thousand color
Variation range, this can cause very big interference to feature extraction.And gray level image is that the identical one kind of tri- components of R, G, B is special
Color image, the description of gray level image still reflected as color image entire image entirety and part coloration and
The distribution and feature of brightness degree, but the variation range of one pixel of gray level image only has 255 kinds.So in the present embodiment
In image procossing, the color image of various formats is changed into gray level image by mobile terminal, so that mobile whole in subsequent processing
The calculation amount to the first image and the second image into figure feature extraction is held to reduce.
Further, mobile terminal is during carrying out gray proces to the first image and the second image, can also be into
Row picture smooth treatment is able to suppress the noise of the first image and the second image, improving image quality.Then mobile terminal will be located
The first image and the second image after reason carry out histogram equalization, i.e., convert the intensity profile of the first image and the second image
To be uniformly distributed, so that the details of the first image and the second image is clearer, the distribution of each tonal gradation of histogram is also more
Balance.Last mobile terminal carries out greyscale transformation, i.e. contrast stretching to the first image and the second image, uses simplest point
Section linear transformation function, expands to specified range or entire dynamic model by linear relationship for original image brightness value dynamic range
It encloses.
S23: according to ORB algorithm, multiple fisrt feature points of the first image are extracted.
Wherein, mobile terminal extracts multiple fisrt feature points in the first image using ORB algorithm.Specifically, mobile whole
Characteristic point is detected using FAST (features from accelerated segment test) algorithm in end, i.e., any selection
Pixel in first image, and the pixel is made comparisons with multiple pixels in its preset range;If the pixel
Different from the pixel of wherein most, then mobile terminal determines that the pixel is the fisrt feature point in the first image.
S24: according to ORB algorithm, multiple second feature points of the second image are extracted.
Wherein, mobile terminal equally uses ORB algorithm to extract multiple second feature points in the second image, no longer superfluous herein
It states.
S25: according to the coordinate data of fisrt feature point, definition square data, barycenter data and the master of fisrt feature point are obtained
Bearing data.
Wherein, mobile terminal extracts the coordinate data of fisrt feature point from the first image, and according to the coordinate data, meter
Calculation obtains definition square data, barycenter data and the principal direction data of the fisrt feature point.The definition square data of characteristic point, mass center number
According to being able to reflect out the property of this feature point with principal direction data, and then reflect image substantive characteristics, can be identified for that in image
Target object.The matching of characteristic point can also be completed by definition square data, barycenter data and the principal direction data of characteristic point, become
Change equal image processing operations.
Specifically, mobile terminal is according to the definition square number of the available fisrt feature point of coordinate data of fisrt feature point
According to the calculation formula of definition square data are as follows:
Wherein, MijFor the definition square of the fisrt feature point, (x, y) is the coordinate of the fisrt feature point, and I (x, y) is
The coordinate function relationship of the fisrt feature point.
The barycenter data that defines the square data available fisrt feature point of the mobile terminal according to fisrt feature point, mass center
The calculation formula of data are as follows:
Wherein, cxFor the abscissa of the mass center, cyFor the ordinate of the mass center, zeroth order square
First moment
Further, mobile terminal it is special can also to obtain corresponding first according to the second moment for defining square of fisrt feature point
The shape bearing data of point is levied, details are not described herein.
Mobile terminal may further obtain the principal direction of the fisrt feature point according to the definition square data of fisrt feature point
Data, the calculation formula of principal direction data are as follows:
Wherein, coriFor the principal direction data of the fisrt feature point.
S26: according to the coordinate data of second feature point, definition square data, barycenter data and the master of second feature point are obtained
Bearing data.
Wherein, mobile terminal extracts the coordinate data of second feature point from the second image, and according to the coordinate data, meter
Calculation obtains definition square data, barycenter data and the principal direction data of the second feature point.
In the present embodiment, mobile terminal is after obtaining the first image and the second image, to the first image and the second image
Gray proces are carried out, to extract the characteristic point of the first image and the second image respectively;Further, mobile terminal is according to first
Definition square data, barycenter data and the principal direction data of fisrt feature point, above-mentioned data are calculated in the coordinate data of characteristic point
The substantive characteristics of image can be further reacted, the accuracy of the present embodiment image alignment method is improved.
Present invention also provides another image alignment methods, specifically refer to Fig. 3, and Fig. 3 is the application image alignment side
The flow diagram of method 3rd embodiment.
On the basis of the step S13 of above-mentioned image alignment method 3rd embodiment, the image alignment method of the present embodiment into
One step is further comprising the steps of:
S31: according to fisrt feature point, definition square data, barycenter data and the principal direction with the fisrt feature point are obtained
The relevant preset condition of data, and obtain the multiple second feature points for meeting the preset condition.
Wherein, mobile terminal presets a model according to the definition square data, barycenter data and principal direction data of fisrt feature point
Foxing part.Mobile terminal obtains the multiple second feature for meeting the range of condition according to the fisrt feature point and the range of condition
Point.
Specifically, mobile terminal can define square range of condition according to square data default one are defined, pre- according to barycenter data
If a mass center range of condition, a principal direction range of condition is preset according to principal direction data, when some second feature point meets simultaneously
Above-mentioned definition square range of condition, mass center range of condition and principal direction range of condition, then mobile terminal thinks that the second feature point is full
The preset range of condition of foot.
S32: the multiple second feature points of traversal obtain related the within the scope of the fisrt feature point pre-determined distance
Two characteristic points.
Wherein, mobile terminal obtains the multiple second feature points for meeting preset range condition in step S31, and calculates every
A second feature point and fisrt feature point on the image at a distance from.Mobile terminal presets a distance range, when some second feature
Point with fisrt feature point on the image at a distance within the scope of pre-determined distance when, mobile terminal thinks that the second feature point is set for height
The characteristic point of reliability.By above-mentioned determination method, mobile terminal can obtain at least one high confidence level according to fisrt feature point
Second feature point.
Further, mobile terminal can also compare multiple groups range data, and by with fisrt feature point on the image away from
Second feature point from shortest second feature point as high confidence level.By above-mentioned determination method, mobile terminal can basis
Fisrt feature point obtains the second feature point of a high confidence level.
For example, extracting fisrt feature point f0-1, two closest characteristic point f1- in multiple second feature points are then extracted
A, f1-b.Mobile terminal calculate two closest characteristic point f1-a, f1-b on the image with fisrt feature point f0-1 distance L
(1a), the size of L (1b), as L (1a) > L (1b), mobile terminal thinks that f1-b is fisrt feature point f0-1 on the second image
The highest second feature point of confidence level.
In the present embodiment, mobile terminal is by preset range condition, and according to fisrt feature point, extraction meets preset range
The second feature point of one or more high confidence levels of condition.
Present invention also provides another image alignment methods, specifically refer to Fig. 4, and Fig. 4 is the application image alignment side
The flow diagram of method fourth embodiment.
On the basis of the step S14 of above-mentioned image alignment method first embodiment, the image alignment method of the present embodiment
Further comprise following steps:
S41: transformation parameter is obtained according at least three groups of fisrt feature points and related second feature point.
Wherein, mobile terminal obtains transformation parameter, transformation according at least three groups of fisrt feature points and related second feature point
The calculation formula of parameter are as follows:
Wherein,For the transformation parameter, (x, y) is the coordinate data of fisrt feature point, and (x ', y ') is the
The coordinate data of two characteristic points.
In transformation parameter,For affine transformation matrix, mobile terminal applies the non-rigid transformation to the second image
Matrix can convert the second image;[a, c] characterizes the angular transformation parameter of second feature point, and [b, d] characterization second is special
The size conversion parameter of point is levied, [e, f] characterizes the shift transformation parameter of second feature point.
S42: according to transformation parameter, multiple second feature points are converted, to obtain third image.
Wherein, as shown in figure 5, after obtaining transformation parameter, mobile terminal is according to the transformation parameter to the on the second image
Two characteristic points are converted, and then combine to obtain third image by transformed multiple second feature points.
S43: according to the first image and at least one third image, synthesis includes the video or dynamic image of multiple image.
Wherein, after converting to multiple second images, mobile terminal obtains the first image and at least one third image.
Mobile terminal and then video or dynamic image including multiple image by the first image and the synthesis of at least one third image.
In the present embodiment, according to transformation parameter, the second image is transformed to third image by mobile terminal, and by the first figure
Picture and the synthesis of at least one third image include the video or dynamic image of multiple image, shine to reduce user and shoot sequence
The threshold of piece, can image alignment method through this embodiment solve the jitter problem of sequence image, promoted synthetic video or
The quality of dynamic image.
To realize above-mentioned image alignment method, present invention also provides a kind of mobile terminals, specifically refer to Fig. 6, and Fig. 6 is
The structural schematic diagram of one embodiment of the application mobile terminal.
Mobile terminal 100 is the revealed mobile terminal that can be used for shooting image of above-described embodiment, as shown in fig. 6, moving
Dynamic terminal 100 includes processor 11 and the memory 12 coupled with processor 11, camera module 13.
Wherein, camera module 13 is for obtaining the first image and the second image;
Memory 12 is for storing program data, and processor 11 is for executing program data to realize above-mentioned image alignment
Method.
In the present embodiment, processor 11 can also be known as CPU (Central Processing Unit, central processing list
Member).Processor 11 may be a kind of IC chip, the processing capacity with signal.Processor 11 can also be general place
Manage device, digital signal processor (DSP), specific integrated circuit (ASIC), ready-made programmable gate array (FPGA) or other can
Programmed logic device, discrete gate or transistor logic, discrete hardware components.General processor can be microprocessor or
Person's processor 11 is also possible to any conventional processor etc..
The application also provides a kind of computer storage medium, as shown in fig. 7, computer storage medium 200 is stored with program
Data, program data can be performed in the method as described in the application image alignment embodiment of the method for realization.
Involved method in the application image alignment embodiment of the method, when realizing in the form of SFU software functional unit
In the presence of and when sold or used as an independent product, can store in a device, such as a computer-readable storage is situated between
In matter.According to such understanding, the technical solution of the application substantially in other words the part that contributes to existing technology or
The all or part of the technical solution can be embodied in the form of software products, which is stored in one
In storage medium, including some instructions are used so that a computer equipment (can be personal computer, server or net
Network equipment etc.) or processor (processor) execute all or part of the steps of each embodiment the method for the present invention.And
Storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as device (RAM, Random Access Memory), magnetic or disk.
The foregoing is merely presently filed embodiments, are not intended to limit the scope of the patents of the application, all to utilize this
Equivalent structure or equivalent flow shift made by application specification and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field similarly includes in the scope of patent protection of the application.
Claims (10)
1. a kind of image alignment method, which is characterized in that described image alignment schemes include:
Obtain the first image and at least second image;
Extract multiple fisrt feature points of the first image and multiple second feature points of second image;
The confidence level for obtaining the second feature point Yu the fisrt feature point filters out the confidence bit in default confidence level
The second feature point of range;
Transformation parameter is calculated according to the fisrt feature point and the second feature point filtered out;
Multiple second feature points are handled according to the transformation parameter, to obtain third image.
2. image alignment method according to claim 1, which is characterized in that the first image of the acquisition and at least one
After the step of two images, described image alignment schemes further include:
The first image and second image are pre-processed, wherein pretreatment includes gray proces;
The step of multiple second feature points of the multiple fisrt feature points for extracting the first image and second image,
Further comprise:
According to ORB algorithm, multiple second feature of multiple the fisrt feature points and second image of the first image are extracted
Point.
3. image alignment method according to claim 2, which is characterized in that the fisrt feature point includes coordinate data;
The step of multiple fisrt feature points for extracting the first image, further comprise:
According to the coordinate data of the fisrt feature point, definition square data, barycenter data and the master of the fisrt feature point are obtained
Bearing data.
4. image alignment method according to claim 3, which is characterized in that described image alignment schemes further include:
According to the coordinate data of the fisrt feature point, the definition square data of the fisrt feature point, the definition square number are obtained
According to calculation formula are as follows:
Wherein, MijFor the definition square of the fisrt feature point, (x, y) is the coordinate of the fisrt feature point, and I (x, y) is described
The coordinate function relationship of fisrt feature point;
The coordinate data according to the fisrt feature point, obtains definition square data, the barycenter data of the fisrt feature point
The step of with principal direction data, further comprise:
According to the definition square data of the fisrt feature point, the barycenter data of the fisrt feature point, the barycenter data are obtained
Calculation formula are as follows:
Wherein, cxFor the abscissa of the mass center, cyFor the ordinate of the mass center;
According to the barycenter data of the fisrt feature point, the principal direction data of the fisrt feature point, the principal direction number are obtained
According to calculation formula are as follows:
Wherein, coriFor the principal direction data of the fisrt feature point.
5. image alignment method according to claim 3, which is characterized in that it is described obtain the second feature point with it is described
The confidence level of fisrt feature point filters out the confidence bit in the second feature point of default confidence range the step of, into one
Step includes:
Preset condition relevant to the definition square data of the fisrt feature point, barycenter data and principal direction data is obtained, and is obtained
Take the multiple second feature points for meeting the preset condition.
6. image alignment method according to claim 5, which is characterized in that the acquisition is determined with the fisrt feature point
Adopted square data, barycenter data and the relevant preset condition of principal direction data, and obtain and meet the multiple described of the preset condition
After the step of second feature point, further comprise:
Traverse multiple second feature points, obtain the second feature point at a distance from the fisrt feature point, it is described away from
It offs normal when within the scope of pre-determined distance, filters out corresponding second feature point.
7. image alignment method according to claim 1, which is characterized in that described according to the fisrt feature point and described
Related second feature point obtains transformation parameter, further comprises:
The point of the fisrt feature according at least three groups obtains the transformation parameter, the transformation ginseng to the related second feature point
Several calculation formula are as follows:
Wherein,For the transformation parameter, x is the abscissa of the fisrt feature point, and y is the fisrt feature point
Ordinate, x ' be the second feature point abscissa, y ' be the second feature point ordinate.
8. image alignment method according to claim 1, which is characterized in that it is described according to the transformation parameter, it converts more
A second feature point, the step of to obtain third image after, described image alignment schemes further include:
According to the first image and an at least third image, synthesis include the video or dynamic image of multiple image.
9. a kind of mobile terminal, which is characterized in that the mobile terminal includes processor and deposits with what the processor coupled
Reservoir, camera module;
Wherein, the camera module is for obtaining the first image and second image;
The memory is for storing program data, and the processor is for executing described program data to realize such as claim
Image alignment method described in any one of 1-8.
10. a kind of computer storage medium, which is characterized in that the computer storage medium is described for storing program data
Program data is when being executed by processor, to realize such as image alignment method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811565425.1A CN109685839B (en) | 2018-12-20 | 2018-12-20 | Image alignment method, mobile terminal and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811565425.1A CN109685839B (en) | 2018-12-20 | 2018-12-20 | Image alignment method, mobile terminal and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109685839A true CN109685839A (en) | 2019-04-26 |
CN109685839B CN109685839B (en) | 2023-04-18 |
Family
ID=66188148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811565425.1A Active CN109685839B (en) | 2018-12-20 | 2018-12-20 | Image alignment method, mobile terminal and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685839B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110856014A (en) * | 2019-11-05 | 2020-02-28 | 北京奇艺世纪科技有限公司 | Moving image generation method, moving image generation device, electronic device, and storage medium |
Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5859921A (en) * | 1995-05-10 | 1999-01-12 | Mitsubishi Denki Kabushiki Kaisha | Apparatus for processing an image of a face |
US20050089213A1 (en) * | 2003-10-23 | 2005-04-28 | Geng Z. J. | Method and apparatus for three-dimensional modeling via an image mosaic system |
US20080063298A1 (en) * | 2006-09-13 | 2008-03-13 | Liming Zhou | Automatic alignment of video frames for image processing |
JP2009195306A (en) * | 2008-02-19 | 2009-09-03 | Toshiba Corp | Medical image display device and medical image display method |
US20090238464A1 (en) * | 2008-03-21 | 2009-09-24 | Masakazu Ohira | Image processing method, image processing apparatus, image forming apparatus and storage medium |
US20110305405A1 (en) * | 2010-06-11 | 2011-12-15 | Fujifilm Corporation | Method, apparatus, and program for aligning images |
US20120051665A1 (en) * | 2010-08-26 | 2012-03-01 | Sony Corporation | Image processing system with image alignment mechanism and method of operation thereof |
US20140072231A1 (en) * | 2012-09-10 | 2014-03-13 | Nokia Corporation | Method, apparatus and computer program product for processing of images |
JP2014126892A (en) * | 2012-12-25 | 2014-07-07 | Fujitsu Ltd | Image processing method, image processing apparatus, and image processing program |
CN103973958A (en) * | 2013-01-30 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Image processing method and image processing equipment |
US20150199585A1 (en) * | 2014-01-14 | 2015-07-16 | Samsung Techwin Co., Ltd. | Method of sampling feature points, image matching method using the same, and image matching apparatus |
US20150294490A1 (en) * | 2014-04-13 | 2015-10-15 | International Business Machines Corporation | System and method for relating corresponding points in images with different viewing angles |
US20170280055A1 (en) * | 2016-03-23 | 2017-09-28 | Canon Kabushiki Kaisha | Image processing apparatus, imaging apparatus, and control method of image processing apparatus |
CN107305682A (en) * | 2016-04-22 | 2017-10-31 | 富士通株式会社 | Method and apparatus for being spliced to image |
CN107465882A (en) * | 2017-09-22 | 2017-12-12 | 维沃移动通信有限公司 | A kind of image capturing method and mobile terminal |
CN107527360A (en) * | 2017-08-23 | 2017-12-29 | 维沃移动通信有限公司 | A kind of image alignment method and mobile terminal |
US20180005394A1 (en) * | 2016-06-30 | 2018-01-04 | Synaptics Incorporated | Systems and methods for point-based image alignment |
CN107909600A (en) * | 2017-11-04 | 2018-04-13 | 南京奇蛙智能科技有限公司 | The unmanned plane real time kinematics target classification and detection method of a kind of view-based access control model |
WO2018104609A1 (en) * | 2016-12-06 | 2018-06-14 | B<>Com | Method for tracking a target in a sequence of medical images, associated device, terminal apparatus and computer programs |
US20180211445A1 (en) * | 2015-07-17 | 2018-07-26 | Sharp Kabushiki Kaisha | Information processing device, terminal, and remote communication system |
CN108537845A (en) * | 2018-04-27 | 2018-09-14 | 腾讯科技(深圳)有限公司 | Pose determines method, apparatus and storage medium |
WO2018180550A1 (en) * | 2017-03-30 | 2018-10-04 | 富士フイルム株式会社 | Image processing device and image processing method |
CN108764024A (en) * | 2018-04-09 | 2018-11-06 | 平安科技(深圳)有限公司 | Generating means, method and the computer readable storage medium of human face recognition model |
-
2018
- 2018-12-20 CN CN201811565425.1A patent/CN109685839B/en active Active
Patent Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5859921A (en) * | 1995-05-10 | 1999-01-12 | Mitsubishi Denki Kabushiki Kaisha | Apparatus for processing an image of a face |
US20050089213A1 (en) * | 2003-10-23 | 2005-04-28 | Geng Z. J. | Method and apparatus for three-dimensional modeling via an image mosaic system |
US20080063298A1 (en) * | 2006-09-13 | 2008-03-13 | Liming Zhou | Automatic alignment of video frames for image processing |
JP2009195306A (en) * | 2008-02-19 | 2009-09-03 | Toshiba Corp | Medical image display device and medical image display method |
US20090238464A1 (en) * | 2008-03-21 | 2009-09-24 | Masakazu Ohira | Image processing method, image processing apparatus, image forming apparatus and storage medium |
US20110305405A1 (en) * | 2010-06-11 | 2011-12-15 | Fujifilm Corporation | Method, apparatus, and program for aligning images |
US20120051665A1 (en) * | 2010-08-26 | 2012-03-01 | Sony Corporation | Image processing system with image alignment mechanism and method of operation thereof |
US20140072231A1 (en) * | 2012-09-10 | 2014-03-13 | Nokia Corporation | Method, apparatus and computer program product for processing of images |
JP2014126892A (en) * | 2012-12-25 | 2014-07-07 | Fujitsu Ltd | Image processing method, image processing apparatus, and image processing program |
CN103973958A (en) * | 2013-01-30 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Image processing method and image processing equipment |
US20150199585A1 (en) * | 2014-01-14 | 2015-07-16 | Samsung Techwin Co., Ltd. | Method of sampling feature points, image matching method using the same, and image matching apparatus |
US20150294490A1 (en) * | 2014-04-13 | 2015-10-15 | International Business Machines Corporation | System and method for relating corresponding points in images with different viewing angles |
US20180211445A1 (en) * | 2015-07-17 | 2018-07-26 | Sharp Kabushiki Kaisha | Information processing device, terminal, and remote communication system |
US20170280055A1 (en) * | 2016-03-23 | 2017-09-28 | Canon Kabushiki Kaisha | Image processing apparatus, imaging apparatus, and control method of image processing apparatus |
CN107305682A (en) * | 2016-04-22 | 2017-10-31 | 富士通株式会社 | Method and apparatus for being spliced to image |
US20180005394A1 (en) * | 2016-06-30 | 2018-01-04 | Synaptics Incorporated | Systems and methods for point-based image alignment |
WO2018104609A1 (en) * | 2016-12-06 | 2018-06-14 | B<>Com | Method for tracking a target in a sequence of medical images, associated device, terminal apparatus and computer programs |
WO2018180550A1 (en) * | 2017-03-30 | 2018-10-04 | 富士フイルム株式会社 | Image processing device and image processing method |
CN107527360A (en) * | 2017-08-23 | 2017-12-29 | 维沃移动通信有限公司 | A kind of image alignment method and mobile terminal |
CN107465882A (en) * | 2017-09-22 | 2017-12-12 | 维沃移动通信有限公司 | A kind of image capturing method and mobile terminal |
CN107909600A (en) * | 2017-11-04 | 2018-04-13 | 南京奇蛙智能科技有限公司 | The unmanned plane real time kinematics target classification and detection method of a kind of view-based access control model |
CN108764024A (en) * | 2018-04-09 | 2018-11-06 | 平安科技(深圳)有限公司 | Generating means, method and the computer readable storage medium of human face recognition model |
CN108537845A (en) * | 2018-04-27 | 2018-09-14 | 腾讯科技(深圳)有限公司 | Pose determines method, apparatus and storage medium |
Non-Patent Citations (2)
Title |
---|
徐国庆: "在线模板的人脸特征点对齐", 《计算机工程与设计》 * |
葛永新等: "基于边缘特征点对对齐度的图像配准方法", 《中国图象图形学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110856014A (en) * | 2019-11-05 | 2020-02-28 | 北京奇艺世纪科技有限公司 | Moving image generation method, moving image generation device, electronic device, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109685839B (en) | 2023-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110163235B (en) | Training of image enhancement model, image enhancement method, device and storage medium | |
US9251589B2 (en) | Depth measurement apparatus, image pickup apparatus, and depth measurement program | |
KR101881243B1 (en) | Method and apparatus for processing a depth image | |
CN111064904A (en) | Dark light image enhancement method | |
CN109308463A (en) | A kind of video object recognition methods, device and equipment | |
JP4098021B2 (en) | Scene identification method, apparatus, and program | |
US20090207260A1 (en) | Image pickup apparatus and image pickup method | |
CN111597933B (en) | Face recognition method and device | |
WO2021135702A1 (en) | Video denoising method and electronic device | |
RU2694148C2 (en) | Alignment method for obtaining images with extended dynamic range | |
CN107360377B (en) | Vehicle-mounted video image stabilization method | |
CN113744307A (en) | Image feature point tracking method and system based on threshold dynamic adjustment | |
CN109040579A (en) | A kind of filming control method, terminal and computer-readable medium | |
CN109859142B (en) | Image brightness adjusting method and device, computer equipment and storage medium | |
CN109685839A (en) | Image alignment method, mobile terminal and computer storage medium | |
CN117152182B (en) | Ultralow-illumination network camera image processing method and device and electronic equipment | |
CN107564013B (en) | Scene segmentation correction method and system fusing local information | |
CN112463999A (en) | Visual position identification method and device, computer equipment and readable storage medium | |
KR20160000533A (en) | The method of multi detection and tracking with local feature point for providing information of an object in augmented reality | |
CN115830513A (en) | Method, device and system for determining image scene change and storage medium | |
KR20170011454A (en) | Method and apparatus for detecting forged image | |
CN113112531B (en) | Image matching method and device | |
US9692982B2 (en) | System for controlling exposure of camera and method thereof | |
CN113947686A (en) | Method and system for dynamically adjusting feature point extraction threshold of image | |
CN111527518B (en) | Method for processing light field video based on use of hyper-ray representations |
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 | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190426 Assignee: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Assignor: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. Contract record no.: X2021440000031 Denomination of invention: Image alignment method, mobile terminal and computer storage medium License type: Common License Record date: 20210125 |
|
EE01 | Entry into force of recordation of patent licensing contract | ||
GR01 | Patent grant | ||
GR01 | Patent grant |