CN110189368A - Method for registering images, mobile terminal and computer readable storage medium - Google Patents
Method for registering images, mobile terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN110189368A CN110189368A CN201910472038.1A CN201910472038A CN110189368A CN 110189368 A CN110189368 A CN 110189368A CN 201910472038 A CN201910472038 A CN 201910472038A CN 110189368 A CN110189368 A CN 110189368A
- Authority
- CN
- China
- Prior art keywords
- matching
- registration
- image
- feature point
- reference picture
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
Method for registering images disclosed by the invention slightly matches the reference picture and the image subject to registration, and the fisrt feature point obtained between the set of characteristic points P1 of reference picture and image P2 subject to registration is matched to set M1；The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；Smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1, the second feature point obtained between set of characteristic points P1 and P2 is matched to set M2；The second homography matrix H2 is calculated to set M2 according to second feature point matching；The image subject to registration is corrected using the second homography matrix H2, obtains target image.In addition, invention additionally discloses a kind of mobile terminal and computer readable storage mediums.In this way, method for registering images provided by the invention carries out the matching of characteristic point essence according to mappings characteristics point, the matching precision of Feature Points Matching centering can be greatlyd improve, to improve the precision of image registration.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of method for registering images, mobile terminal and computer
Readable storage medium storing program for executing.
Background technique
With the continuous development of electronic technology, the function of mobile terminal (such as smart phone, tablet computer etc.) is increasingly
Powerful, user can be used mobile terminal and take pictures whenever and wherever possible, record the drop in work or life.It is desirable to scheme
As processing scene (such as multiple image noise reduction, image mosaic, image panorama splicing etc.) needs to carry out image registration.
Image registration generally refers to two that obtain (different imaging devices, camera position and angle etc.) under different condition
Or the process that multiple images are matched, are superimposed, it can also refer to an images match subject to registration to another reference picture
Process.For example, when user's hand-held mobile terminal or photographic device are shot, due to the hand-held shake occurred, meeting
Lead between two captured images that there are deviations, without perfectly aligned, then needs to scheme two using image registration techniques
As being handled.
However, in the prior art, the error of image registration is larger, and precision is smaller.
Summary of the invention
In view of this, the present invention proposes a kind of method for registering images, mobile terminal and computer readable storage medium, with solution
Certainly above-mentioned technical problem.
Firstly, to achieve the above object, the present invention proposes a kind of method for registering images, it is applied to mobile terminal, the side
Method includes:
Characteristic point detection and description are carried out to reference picture and image subject to registration respectively, obtain the spy of the reference picture
Levy the description subclass D1 of point set P1 and each characteristic point and the set of characteristic points P2 and each spy of the image subject to registration
Levy the description subclass D2 of point；
The reference picture and the image subject to registration are slightly matched, obtained between set of characteristic points P1 and P2
Fisrt feature point match to set M1；
The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；
Smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1, is obtained
Second feature point between set of characteristic points P1 and P2 is matched to set M2；
The second homography matrix H2 is calculated to set M2 according to second feature point matching；
The image subject to registration is corrected using the second homography matrix H2, obtains target image.
It is optionally, described that second homography matrix H2 is calculated to set M2 according to second feature point matching, comprising:
LS-SVM sparseness is carried out to set M2 to second feature point matching, obtains the matching of third feature point to set
M3；
The second homography matrix H2 is calculated to set M3 according to third feature point matching.
Optionally, described that LS-SVM sparseness is carried out to set M2 to second feature point matching, obtain third feature point
Matching is to set M3, comprising:
The reference picture is divided into N1*N2 image subblock；
For each image subblock, the second feature point matching is counted to the spy for falling into the image subblock in set M2
Sign point matching is to quantity；
Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains third
Feature Points Matching is to set M3.
Optionally, the Nm retained in each image subblock is to Feature Points Matching pair, comprising:
According to the detection ordering in characteristic point detection process, retain the preceding Nm in each image subblock to Feature Points Matching
It is right.
It is optionally, described that the reference picture and the image subject to registration are slightly matched, comprising:
Using the arest neighbors based on first threshold than secondary neighbour's mode to the reference picture and the image subject to registration
Slightly matched；
It is described that smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1,
Include:
According to the first homography matrix H1, using the arest neighbors based on second threshold than secondary neighbour's mode to the reference
Image and the image subject to registration carry out smart matching, wherein the second threshold is less than the first threshold.
It is optionally, described that first homography matrix H1 is calculated to set M1 according to fisrt feature point matching, comprising:
To fisrt feature point matching to set M1, it is single that first is calculated using the consistent RANSAC algorithm of the first stochastical sampling
Answer matrix H 1, wherein the first RANSAC algorithm uses first error threshold value；
It is described that the second homography matrix H2 is calculated to set M3 according to third feature point matching, comprising:
To third feature point matching to set M3, the second homography matrix is calculated using the 2nd RANSAC algorithm, wherein
The 2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than the first error threshold value.
Optionally, described that the reference picture and the image subject to registration are carried out according to the first homography matrix H1
Essence matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2, comprising:
For each characteristic point of the set of characteristic points P1 of the reference pictureIt is calculated in the image subject to registration
In initial mapping point
Calculate characteristic pointWith it in the set of characteristic points P2 of the image subject to registration corresponding characteristic pointIt is right respectively
The first Euclidean distance d between description answered1；
According to the first Euclidean distance d between description1And the Euclidean distance weight between descriptionCalculate the second Euclidean distance d between description2=wd1, wherein range pointsCloser feature
PointCorresponding weight w is smaller, and range pointsRemoter characteristic pointCorresponding weight w is bigger；
According to the second Euclidean distance between description, using the arest neighbors based on second threshold than secondary neighbour's mode pair
The reference picture and the image subject to registration carry out smart matching, obtain the second feature between set of characteristic points P1 and P2
Point matching is to set M2.
It is optionally, described that characteristic point detection and description are carried out respectively to reference picture and image subject to registration, comprising:
Using accelerate robust feature SURF algorithm to reference picture and image subject to registration carry out respectively characteristic point detection and
Description.
Further, to achieve the above object, the present invention also provides a kind of mobile terminal, the mobile terminal includes storage
Device, at least one processor and at least one journey that is stored on the memory and can be executed at least one described processor
Sequence, at least one described program realize the step in method described in any of the above embodiments when being executed by least one described processor
Suddenly.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
Readable storage medium storing program for executing is stored at least one executable program of computer, at least one described program is executed by the computer
When so that the computer is executed the step in the above method.
Compared to the prior art, method for registering images proposed by the invention distinguishes reference picture and image subject to registration
Characteristic point detection and description are carried out, the set of characteristic points P1 of the reference picture and the description subclass of each characteristic point are obtained
The description subclass D2 of the set of characteristic points P2 and each characteristic point of D1 and the image subject to registration；To the reference picture
And the image subject to registration is slightly matched, the fisrt feature point obtained between set of characteristic points P1 and P2 is matched to set
M1；The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；According to described H1 pairs of first homography matrix
The reference picture and the image subject to registration carry out smart matching, obtain the second feature point between set of characteristic points P1 and P2
Matching is to set M2；The second homography matrix H2 is calculated to set M2 according to second feature point matching；It is single using described second
It answers matrix H 2 to correct the image subject to registration, obtains target image.Method for registering images provided by the invention is according to reflecting
It penetrates characteristic point and carries out the matching of characteristic point essence, the matching precision of Feature Points Matching centering can be greatlyd improve, to improve image
The precision of registration.
Detailed description of the invention
Fig. 1 is the hardware structural diagram for realizing a kind of mobile terminal of each embodiment of the present invention；
Fig. 2 is a kind of communications network system architecture diagram provided in an embodiment of the present invention；
Fig. 3 is one of the flow diagram of method for registering images provided in an embodiment of the present invention；
Fig. 4 is the schematic diagram of reference picture provided in an embodiment of the present invention and image subject to registration；
Fig. 5 is schematic diagram of the fisrt feature point matching provided in an embodiment of the present invention to set M1；
Fig. 6 is schematic diagram of the second feature point matching provided in an embodiment of the present invention to set M2；
Fig. 7 is the schematic diagram of image subject to registration and target image provided in an embodiment of the present invention；
Fig. 8 is the two of the flow diagram of method for registering images provided in an embodiment of the present invention；
Fig. 9 is schematic diagram of the third feature point matching provided in an embodiment of the present invention to set M3；
Figure 10 is the three of the flow diagram of method for registering images provided in an embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of element
Be conducive to explanation of the invention, itself there is no a specific meaning.Therefore, " module ", " component " or " unit " can mix
Ground uses.
Terminal can be implemented in a variety of manners.For example, terminal described in the present invention may include such as mobile phone, plate
Computer, laptop, palm PC, personal digital assistant (Personal Digital Assistant, PDA), portable
Media player (Portable Media Player, PMP), navigation device, wearable device, Intelligent bracelet, pedometer etc. move
The fixed terminals such as dynamic terminal, and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to special
Except element for moving purpose, the construction of embodiment according to the present invention can also apply to the terminal of fixed type.
Referring to Fig. 1, a kind of hardware structural diagram of its mobile terminal of each embodiment to realize the present invention, the shifting
Dynamic terminal 100 may include: RF (Radio Frequency, radio frequency) unit 101, WiFi module 102, audio output unit
103, A/V (audio/video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit
108, the components such as memory 109, processor 110 and power supply 111, the number of the processor 110 are at least one.Ability
Field technique personnel are appreciated that mobile terminal structure shown in Fig. 1 does not constitute the restriction to mobile terminal, and mobile terminal can
To include perhaps combining certain components or different component layouts than illustrating more or fewer components.
It is specifically introduced below with reference to all parts of the Fig. 1 to mobile terminal:
Radio frequency unit 101 can be used for receiving and sending messages or communication process in, signal sends and receivees, specifically, by base station
Downlink information receive after, to processor 110 handle；In addition, the data of uplink are sent to base station.In general, radio frequency unit 101
Including but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, penetrating
Frequency unit 101 can also be communicated with network and other equipment by wireless communication.Any communication can be used in above-mentioned wireless communication
Standard or agreement, including but not limited to GSM (Global System of Mobile communication, global system for mobile telecommunications
System), GPRS (General Packet Radio Service, general packet radio service), CDMA2000 (Code
Division Multiple Access 2000, CDMA 2000), WCDMA (Wideband Code Division
Multiple Access, wideband code division multiple access), TD-SCDMA (Time Division-Synchronous Code
Division Multiple Access, TD SDMA), FDD-LTE (Frequency Division
Duplexing-Long Term Evolution, frequency division duplex long term evolution) and TDD-LTE (Time Division
Duplexing-Long Term Evolution, time division duplex long term evolution) etc..
WiFi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch electricity by WiFi module 102
Sub- mail, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 1 shows
Go out WiFi module 102, but it is understood that, and it is not belonging to must be configured into for mobile terminal, it completely can be according to need
It to omit within the scope of not changing the essence of the invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100
When under the isotypes such as formula, speech recognition mode, broadcast reception mode, by radio frequency unit 101 or WiFi module 102 it is received or
The audio data that person stores in memory 109 is converted into audio signal and exports to be sound.Moreover, audio output unit
103 can also provide executed to mobile terminal 100 the relevant audio output of specific function (for example, call signal receive sound,
Message sink sound etc.).Audio output unit 103 may include loudspeaker, buzzer etc..
A/V input unit 104 is for receiving audio or video signal.A/V input unit 104 may include graphics processor
(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 capture mould in video
The image data of the static images or video that are obtained in formula or image capture mode by image capture apparatus (such as camera) carries out
Processing.Treated, and picture frame may be displayed on display unit 106.It can be with through treated the picture frame of graphics processor 1041
It is stored in memory 109 (or other storage mediums) or is sent via radio frequency unit 101 or WiFi module 102.Wheat
Gram wind 1042 can be in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042
It receives sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data
It is defeated that the format that can be sent to mobile communication base station via radio frequency unit 101 can be converted in the case where telephone calling model
Out.Microphone 1042 can be implemented various types of noises elimination (or inhibition) algorithms and sended and received with eliminating (or inhibition)
The noise generated during audio signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographies
Sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's ear
Display panel 1061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (general
For three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify the application of mobile phone posture
(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；
The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,
The other sensors such as hygrometer, thermometer, infrared sensor, details are not described herein.
Display unit 106 is for showing information input by user or being supplied to the information of user.Display unit 106 can
Including display panel 1061, liquid crystal display (Liquid Crystal Display, LCD), organic light-emitting diodes can be used
Forms such as (Organic Light-Emitting Diode, OLED) are managed to configure display panel 1061.
User input unit 107 can be used for receiving the number or character information of input, and generate the use with mobile terminal
Family setting and the related key signals input of function control.Specifically, user input unit 107 may include touch panel 1071 with
And other input equipments 1072.Touch panel 1071, also referred to as touch screen collect the touch operation of user on it or nearby
(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 1071 or in touch panel 1071
Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detection
Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band
The signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it
It is converted into contact coordinate, then gives processor 110, and order that processor 110 is sent can be received and executed.In addition, can
To realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel
1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrap
It includes but is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc.
It is one or more, specifically herein without limitation.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it or
After neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thing
The type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel
1061 be the function that outputs and inputs of realizing mobile terminal as two independent components, but in certain embodiments, it can
The function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specifically
It limits.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,
External device (ED) may include wired or wireless headphone port, external power supply (or battery charger) port, wired or nothing
Line data port, memory card port, the port for connecting the device with identification module, audio input/output (I/O) end
Mouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, number
It is believed that breath, electric power etc.) and by least one element that the input received is transferred in mobile terminal 100 or can use
In transmitting data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storing software program and various data.Memory 109 can mainly include storing program area
The storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one function
Sound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such as
Audio data, phone directory etc.) etc..In addition, memory 109 may include high-speed random access memory, it can also include non-easy
The property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connection
A part by running or execute the software program and/or module that are stored in memory 109, and calls and is stored in storage
Data in device 109 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.Place
Managing device 110 may include at least one processing unit；Preferably, processor 110 can integrate application processor and modulation /demodulation processing
Device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainly located
Reason wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111
Can be logically contiguous by power-supply management system and processor 110, to realize management charging by power-supply management system, put
The functions such as electricity and power managed.
Although Fig. 1 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
Embodiment to facilitate the understanding of the present invention, the communications network system that mobile terminal of the invention is based below into
Row description.
Referring to Fig. 2, Fig. 2 is a kind of communications network system architecture diagram provided in an embodiment of the present invention, the communication network system
System be universal mobile communications technology LTE system, the LTE system include successively communication connection UE (User Equipment,
User equipment) 201, E-UTRAN (Evolved UMTS Terrestrial Radio Access Network, evolved UMTS
Land radio access web) 202, EPC (Evolved Packet Core, evolved packet-based core networks) 203 and operator IP industry
Business 204.
Specifically, UE201 can be above-mentioned terminal 100, and details are not described herein again.
E-UTRAN202 includes eNodeB2021 and other eNodeB2022 etc..Wherein, eNodeB2021 can be by returning
Journey (backhaul) (such as X2 interface) is connect with other eNodeB2022, and eNodeB2021 is connected to EPC203,
ENodeB2021 can provide the access of UE201 to EPC203.
EPC203 may include MME (Mobility Management Entity, mobility management entity) 2031, HSS
(Home Subscriber Server, home subscriber server) 2032, other MME2033, SGW (Serving Gate
Way, gateway) 2034, PGW (PDN Gate Way, grouped data network gateway) 2035 and PCRF (Policy and
Charging Rules Function, policy and rate functional entity) 2036 etc..Wherein, MME2031 be processing UE201 and
The control node of signaling, provides carrying and connection management between EPC203.HSS2032 is all to manage for providing some registers
Such as the function of home location register (not shown) etc, and preserves some related service features, data rates etc. and use
The dedicated information in family.All customer data can be sent by SGW2034, and PGW2035 can provide the IP of UE 201
Address distribution and other functions, PCRF2036 are strategy and the charging control strategic decision-making of business data flow and IP bearing resource
Point, it selects and provides available strategy and charging control decision with charge execution function unit (not shown) for strategy.
IP operation 204 may include internet, Intranet, IMS (IP Multimedia Subsystem, IP multimedia
Subsystem) or other IP operations etc..
Although above-mentioned be described by taking LTE system as an example, those skilled in the art should know the present invention is not only
Suitable for LTE system, be readily applicable to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA with
And the following new network system etc., herein without limitation.
Based on above-mentioned 100 hardware configuration of mobile terminal and communications network system, each embodiment of the method for the present invention is proposed.
Mobile terminal in the embodiment of the present invention can be any mobile terminal with shooting function.
It is a kind of step flow chart of method for registering images provided in an embodiment of the present invention, the method refering to Fig. 3, Fig. 3
Applied in a mobile terminal, as shown in Figure 3, which comprises
Step 301 carries out characteristic point detection and description to reference picture and image subject to registration respectively, obtains the reference
The set of characteristic points P2 of the set of characteristic points P1 of image and the description subclass D1 of each characteristic point and the image subject to registration
With the description subclass D2 of each characteristic point.
In the step, the mobile terminal carries out characteristic point detection to reference picture and image subject to registration respectively and retouches
It states, obtains the set of characteristic points of the reference pictureWith the description subclass of each characteristic pointAnd the set of characteristic points of the image subject to registrationWith each characteristic point
Description subclassWherein, n1For the sum of characteristic point in the reference picture, n2For it is described to
It is registrated the sum of characteristic point in image.In some embodiments of the invention, the mobile terminal can be used SURF and (accelerate steady special
Sign) algorithm carries out characteristic point detection and description to reference picture and image subject to registration respectively.
Step 302 slightly matches the reference picture and the image subject to registration, obtain set of characteristic points P1 and
Fisrt feature point between P2 is matched to set M1.
In the step, the mobile terminal slightly matches the reference picture and the image subject to registration, obtains
Fisrt feature point between the set of characteristic points P1 and P2 is matched to set
Specifically, the mobile terminal can be used the arest neighbors based on first threshold than secondary neighbour's mode to the reference picture and
The image subject to registration is slightly matched, and obtains the fisrt feature point matching to set M1.
For example, Fig. 4 and Fig. 5 are please referred to, it is assumed that the reference picture is image shown in (4a) in Fig. 4, it is described to
Being registrated image is in Fig. 4 (image shown in 4b), then the fisrt feature point obtained by step 302 is matched to set M1 such as Fig. 5
In lines shown in.
Step 303 calculates the first homography matrix H1 to set M1 according to fisrt feature point matching.
In the step, the mobile terminal matches according to the fisrt feature point and calculates the first homography matrix to set M1
H1.Specifically, the mobile terminal can match the fisrt feature point to set M1, consistent using the first stochastical sampling
RANSAC algorithm calculates the first homography matrix H1, wherein the first RANSAC algorithm uses first error threshold value.
Step 304 carries out essence to the reference picture and the image subject to registration according to the first homography matrix H1
Matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2.
In the step, the mobile terminal is according to the first homography matrix H1 to the reference picture and described wait match
Quasi- image carries out smart matching, and the second feature point obtained between set of characteristic points P1 and P2 is matched to setSpecifically, the mobile terminal can be used based on second threshold most
Neighbour slightly matches the reference picture and the image subject to registration than secondary neighbour's mode, obtains the fisrt feature point
Matching is to set M2, wherein the second threshold is less than the first threshold.
It is understood that after slightly match to the reference picture and the image subject to registration, due to accidentally
The presence of difference, it may appear that more erroneous matching pair, such as cross spider as shown in Figure 5.By the step 304 to the reference
Image and the image subject to registration carry out smart matching, can obtain matching matching error rate lower second feature point and gather
M2, as shown in fig. 6, the lines in Fig. 6 reduce many cross spiders compared to the lines in Fig. 5.
Step 305 calculates the second homography matrix H2 to set M2 according to second feature point matching.
In the step, the mobile terminal matches according to the second feature point and calculates the second homography matrix to set M2
H2.Specifically, the mobile terminal can match the second feature point to set M2, be calculated using the 2nd RANSAC algorithm
Second homography matrix H2, wherein the 2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than institute
State first error threshold value.
In some embodiments of the invention, the mobile terminal matches according to the second feature point and calculates institute to set M2
The mode for stating the second homography matrix H2 can specifically include: carry out at rarefaction to second feature point matching to set M2
Reason obtains the matching of third feature point to set M3；Described second is calculated to set M3 according to third feature point matching singly to answer
Matrix H 2.
Step 306 is corrected the image subject to registration using the second homography matrix H2, obtains target image.
In the step, the mobile terminal is corrected the image subject to registration using the second homography matrix H2,
Obtain target image.Referring to Fig. 7, image shown in (7a) is image subject to registration in Fig. 7, image shown in (7b) is to pass through
Method for registering images provided in an embodiment of the present invention be registrated after target image.
In the present embodiment, described image method for registering carries out characteristic point detection to reference picture and image subject to registration respectively
And description, obtain the set of characteristic points P1 of the reference picture and the description subclass D1 of each characteristic point and described wait match
The set of characteristic points P2 of the quasi- image and description subclass D2 of each characteristic point；To the reference picture and described subject to registration
Image is slightly matched, and the fisrt feature point obtained between set of characteristic points P1 and P2 is matched to set M1；According to described first
Feature Points Matching calculates the first homography matrix H1 to set M1；According to the first homography matrix H1 to the reference picture and
The image subject to registration carries out smart matching, and the second feature point obtained between set of characteristic points P1 and P2 is matched to set M2；Root
The second homography matrix H2 is calculated to set M2 according to second feature point matching；Using the second homography matrix H2 will it is described to
Registration image is corrected, and target image is obtained.In this way, described image method for registering carries out characteristic point essence according to mappings characteristics point
Matching, can greatly improve the matching precision of Feature Points Matching centering, to improve the precision of image registration.
Optionally, described that the reference picture and the image subject to registration are carried out according to the first homography matrix H1
Essence matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2, comprising:
For each characteristic point of the set of characteristic points P1 of the reference pictureIt is calculated in the image subject to registration
In initial mapping point
Calculate characteristic pointWith it in the set of characteristic points P2 of the image subject to registration corresponding characteristic pointIt is right respectively
The first Euclidean distance d between description answered1；
According to the first Euclidean distance d between description1And the Euclidean distance weight between descriptionCalculate the second Euclidean distance d between description2=wd1, wherein range pointsCloser feature
PointCorresponding weight w is smaller, and range pointsRemoter characteristic pointCorresponding weight w is bigger；
According to the second Euclidean distance between description, using the arest neighbors based on second threshold than secondary neighbour's mode pair
The reference picture and the image subject to registration carry out smart matching, obtain the second feature between set of characteristic points P1 and P2
Point matching is to set M2.
In the embodiment, the mobile terminal specifically can be in the above manner to the reference picture and described wait match
Quasi- image carries out smart matching.
It is the two of the flow diagram of method for registering images provided in an embodiment of the present invention, described image referring to Fig. 8, Fig. 8
Method for registering is applied to a mobile terminal, as shown in Figure 8, which comprises
Step 801 carries out characteristic point detection and description to reference picture and image subject to registration respectively, obtains the reference
The set of characteristic points P2 of the set of characteristic points P1 of image and the description subclass D1 of each characteristic point and the image subject to registration
With the description subclass D2 of each characteristic point.
Step 802 slightly matches the reference picture and the image subject to registration, obtain set of characteristic points P1 and
Fisrt feature point between P2 is matched to set M1.
Step 803 calculates the first homography matrix H1 to set M1 according to fisrt feature point matching.
Step 804 carries out essence to the reference picture and the image subject to registration according to the first homography matrix H1
Matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2.
The step 801 is identical to step 304 to step 804 and the step 301 in present invention embodiment shown in Fig. 3,
Details are not described herein again.
Step 805 carries out LS-SVM sparseness to set M2 to second feature point matching, obtains the matching of third feature point
To set M3.
In the step, the mobile terminal matches the second feature point and carries out LS-SVM sparseness to set M2, obtains
Third feature point is matched to set M3.Specifically, the reference picture can be divided into N1*N2 image by the mobile terminal
Sub-block；For each image subblock, the second feature point matching is counted to the feature for falling into the image subblock in set M2
Point matching is to quantity；Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains
Third feature point is matched to set M3.
It is understood that since the characteristic point of detection is there may be being unevenly distributed, such as shown in fig. 6,
By the step 805, LS-SVM sparseness is carried out to second feature point set M2, obtains the matching of third feature point to set M3, such as
Shown in lines in Fig. 9, the third feature point matching is distributed the second feature point set to the characteristic point in set M3
The characteristic point distribution closed in M2 is more uniform.
Step 806 calculates the second homography matrix H2 to set M3 according to third feature point matching.
In the step, the mobile terminal matches according to the third feature point and singly answers square to set M3 calculating described second
Battle array H2.Specifically, the mobile terminal can match to set M3 the third feature point, use the 2nd RANSAC algorithm
Calculate the second homography matrix, wherein the 2nd RANSAC algorithm uses the second error threshold, and second error threshold is small
In the first error threshold value.
Step 807 is corrected the image subject to registration using the second homography matrix H2, obtains target image.
The step 807 is identical as the step 306 in present invention embodiment shown in Fig. 3, and details are not described herein again.
In the present embodiment, described image method for registering carries out characteristic point detection to reference picture and image subject to registration respectively
And description, obtain the set of characteristic points P1 of the reference picture and the description subclass D1 of each characteristic point and described wait match
The set of characteristic points P2 of the quasi- image and description subclass D2 of each characteristic point；To the reference picture and described subject to registration
Image is slightly matched, and the fisrt feature point obtained between set of characteristic points P1 and P2 is matched to set M1；According to described first
Feature Points Matching calculates the first homography matrix H1 to set M1；According to the first homography matrix H1 to the reference picture with
And the image subject to registration carries out smart matching, the second feature point obtained between set of characteristic points P1 and P2 is matched to set M2；
LS-SVM sparseness is carried out to set M2 to second feature point matching, obtains the matching of third feature point to set M3；According to institute
It states the matching of third feature point and the second homography matrix H2 is calculated to set M3；Using the second homography matrix H2 will it is described to
Registration image is corrected, and target image is obtained.In this way, described image method for registering carries out characteristic point essence according to mappings characteristics point
Matching, can greatly improve the matching precision of Feature Points Matching centering, to improve the precision of image registration.Using characteristic point
Rarefaction strategy enables to the distribution of Feature Points Matching pair in registration process relatively uniform.
Optionally, described that LS-SVM sparseness is carried out to set M2 to second feature point matching, obtain third feature point
Matching is to set M3, comprising:
The reference picture is divided into N1*N2 image subblock；
For each image subblock, the second feature point matching is counted to the spy for falling into the image subblock in set M2
Sign point matching is to quantity；
Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains third
Feature Points Matching is to set M3.
In the embodiment, the mobile terminal matches the second feature point using aforesaid way and carries out to set M2
LS-SVM sparseness obtains the matching of third feature point to set M3.
Optionally, the Nm retained in each image subblock is to Feature Points Matching pair, comprising:
According to the detection ordering in characteristic point detection process, retain the preceding Nm in each image subblock to Feature Points Matching
It is right.
In the embodiment, the mobile terminal can retain each figure according to the detection ordering in characteristic point detection process
Preceding Nm is to Feature Points Matching pair in picture sub-block.
It is optionally, described that the reference picture and the image subject to registration are slightly matched, comprising:
Using the arest neighbors based on first threshold than secondary neighbour's mode to the reference picture and the image subject to registration
Slightly matched；
It is described that smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1,
Include:
According to the first homography matrix H1, using the arest neighbors based on second threshold than secondary neighbour's mode to the reference
Image and the image subject to registration carry out smart matching, wherein the second threshold is less than the first threshold.
In the embodiment of the present invention, the value of the first threshold is specifically as follows α1=0.9, the value of the second threshold
It is specifically as follows α1=0.5.
It is optionally, described that first homography matrix H1 is calculated to set M1 according to fisrt feature point matching, comprising:
To fisrt feature point matching to set M1, it is single that first is calculated using the consistent RANSAC algorithm of the first stochastical sampling
Answer matrix H 1, wherein the first RANSAC algorithm uses first error threshold value；
It is described that the second homography matrix H2 is calculated to set M3 according to third feature point matching, comprising:
To third feature point matching to set M3, the second homography matrix is calculated using the 2nd RANSAC algorithm, wherein
The 2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than the first error threshold value.
In the embodiment of the present invention, the value of the first error threshold value is specifically as follows β1=20, second error threshold
The value of value is specifically as follows β1=10.
It is the three of the flow diagram of method for registering images provided in an embodiment of the present invention, the figure referring to Figure 10, Figure 10
Picture method for registering is applied to a mobile terminal, as shown in Figure 10, which comprises
Step 1001 carries out feature to reference picture and image subject to registration using acceleration robust feature SURF algorithm respectively
Point detection and description, obtain the set of characteristic points P1 of the reference picture and description subclass D1 of each characteristic point, Yi Jisuo
State the set of characteristic points P2 of image subject to registration and the description subclass D2 of each characteristic point.
In the step, the mobile terminal carries out characteristic point inspection to reference picture and image subject to registration using SURF algorithm
It surveys and describes.
Step 1002 slightly matches the reference picture and the image subject to registration, obtains set of characteristic points P1
Fisrt feature point between P2 is matched to set M1.
Step 1003 calculates the first homography matrix H1 to set M1 according to fisrt feature point matching.
Step 1004 carries out essence to the reference picture and the image subject to registration according to the first homography matrix H1
Matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2.
Step 1005 calculates the second homography matrix H2 to set M2 according to second feature point matching.
Step 1006 is corrected the image subject to registration using the second homography matrix H2, obtains target image.
Step 302 of the step 1002 into step 1006 and present invention embodiment shown in Fig. 3 is to step 306 phase
Together, details are not described herein again.
In the present embodiment, described image method for registering is using acceleration robust feature SURF algorithm to reference picture and wait match
Quasi- image carries out characteristic point detection and description respectively, obtains the set of characteristic points P1 of the reference picture and retouching for each characteristic point
State the set of characteristic points P2 of subclass D1 and the image subject to registration and the description subclass D2 of each characteristic point；To described
Reference picture and the image subject to registration are slightly matched, and the fisrt feature point matching between set of characteristic points P1 and P2 is obtained
To set M1；The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；Square is singly answered according to described first
Battle array H1 carries out smart matching to the reference picture and the image subject to registration, obtains the between set of characteristic points P1 and P2
Two Feature Points Matchings are to set M2；The second homography matrix H2 is calculated to set M2 according to second feature point matching；Using institute
It states the second homography matrix H2 to correct the image subject to registration, obtains target image.In this way, described image method for registering root
The matching of characteristic point essence is carried out according to mappings characteristics point, the matching precision of Feature Points Matching centering can be greatlyd improve, to improve
The precision of image registration.
It can be with those of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment method is
It is completed by the relevant hardware of at least one program instruction, at least one described program can store in shifting as shown in Figure 1
It in the memory 109 of dynamic terminal 100, and can be executed by the processor 110, at least one described program is by the processing
Device 110 realizes following steps when executing:
Characteristic point detection and description are carried out to reference picture and image subject to registration respectively, obtain the spy of the reference picture
Levy the description subclass D1 of point set P1 and each characteristic point and the set of characteristic points P2 and each spy of the image subject to registration
Levy the description subclass D2 of point；
The reference picture and the image subject to registration are slightly matched, obtained between set of characteristic points P1 and P2
Fisrt feature point match to set M1；
The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；
Smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1, is obtained
Second feature point between set of characteristic points P1 and P2 is matched to set M2；
The second homography matrix H2 is calculated to set M2 according to second feature point matching；
The image subject to registration is corrected using the second homography matrix H2, obtains target image.
It is optionally, described that second homography matrix H2 is calculated to set M2 according to second feature point matching, comprising:
LS-SVM sparseness is carried out to set M2 to second feature point matching, obtains the matching of third feature point to set
M3；
The second homography matrix H2 is calculated to set M3 according to third feature point matching.
Optionally, described that LS-SVM sparseness is carried out to set M2 to second feature point matching, obtain third feature point
Matching is to set M3, comprising:
The reference picture is divided into N1*N2 image subblock；
For each image subblock, the second feature point matching is counted to the spy for falling into the image subblock in set M2
Sign point matching is to quantity；
Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains third
Feature Points Matching is to set M3.
Optionally, the Nm retained in each image subblock is to Feature Points Matching pair, comprising:
According to the detection ordering in characteristic point detection process, retain the preceding Nm in each image subblock to Feature Points Matching
It is right.
It is optionally, described that the reference picture and the image subject to registration are slightly matched, comprising:
Using the arest neighbors based on first threshold than secondary neighbour's mode to the reference picture and the image subject to registration
Slightly matched；
It is described that smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1,
Include:
According to the first homography matrix H1, using the arest neighbors based on second threshold than secondary neighbour's mode to the reference
Image and the image subject to registration carry out smart matching, wherein the second threshold is less than the first threshold.
It is optionally, described that first homography matrix H1 is calculated to set M1 according to fisrt feature point matching, comprising:
To fisrt feature point matching to set M1, it is single that first is calculated using the consistent RANSAC algorithm of the first stochastical sampling
Answer matrix H 1, wherein the first RANSAC algorithm uses first error threshold value；
It is described that the second homography matrix H2 is calculated to set M3 according to third feature point matching, comprising:
To third feature point matching to set M3, the second homography matrix is calculated using the 2nd RANSAC algorithm, wherein
The 2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than the first error threshold value.
Optionally, described that the reference picture and the image subject to registration are carried out according to the first homography matrix H1
Essence matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2, comprising:
For each characteristic point of the set of characteristic points P1 of the reference pictureIt is calculated in the image subject to registration
In initial mapping point
Calculate characteristic pointWith it in the set of characteristic points P2 of the image subject to registration corresponding characteristic pointIt is right respectively
The first Euclidean distance d between description answered1；
According to the first Euclidean distance d between description1And the Euclidean distance weight between descriptionCalculate the second Euclidean distance d between description2=wd1, wherein range pointsCloser feature
PointCorresponding weight w is smaller, and range pointsRemoter characteristic pointCorresponding weight w is bigger；
According to the second Euclidean distance between description, using the arest neighbors based on second threshold than secondary neighbour's mode pair
The reference picture and the image subject to registration carry out smart matching, obtain the second feature between set of characteristic points P1 and P2
Point matching is to set M2.
It is optionally, described that characteristic point detection and description are carried out respectively to reference picture and image subject to registration, comprising:
Using accelerate robust feature SURF algorithm to reference picture and image subject to registration carry out respectively characteristic point detection and
Description.
In the present embodiment, the mobile terminal carries out characteristic point detection to reference picture and image subject to registration respectively and retouches
It states, obtains the set of characteristic points P1 of the reference picture and the description subclass D1 of each characteristic point and the figure subject to registration
The set of characteristic points P2 of the picture and description subclass D2 of each characteristic point；To the reference picture and the image subject to registration into
The thick matching of row, the fisrt feature point obtained between set of characteristic points P1 and P2 are matched to set M1；According to the fisrt feature point
Matching calculates the first homography matrix H1 to set M1；According to the first homography matrix H1 to the reference picture and it is described to
It is registrated image and carries out smart matching, the second feature point obtained between set of characteristic points P1 and P2 is matched to set M2；According to described
The matching of second feature point calculates the second homography matrix H2 to set M2；Using the second homography matrix H2 by the figure subject to registration
As being corrected, target image is obtained.In this way, the mobile terminal carries out the matching of characteristic point essence according to mappings characteristics point, it can
The matching precision of Feature Points Matching centering is greatlyd improve, to improve the precision of image registration.
It can be with those of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment method is
It is completed by the relevant hardware of at least one program instruction, at least one described program can store computer-readable deposits in one
In storage media, which is performed, comprising the following steps:
Characteristic point detection and description are carried out to reference picture and image subject to registration respectively, obtain the spy of the reference picture
Levy the description subclass D1 of point set P1 and each characteristic point and the set of characteristic points P2 and each spy of the image subject to registration
Levy the description subclass D2 of point；
The reference picture and the image subject to registration are slightly matched, obtained between set of characteristic points P1 and P2
Fisrt feature point match to set M1；
The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；
Smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1, is obtained
Second feature point between set of characteristic points P1 and P2 is matched to set M2；
The second homography matrix H2 is calculated to set M2 according to second feature point matching；
The image subject to registration is corrected using the second homography matrix H2, obtains target image.
It is optionally, described that second homography matrix H2 is calculated to set M2 according to second feature point matching, comprising:
LS-SVM sparseness is carried out to set M2 to second feature point matching, obtains the matching of third feature point to set
M3；
The second homography matrix H2 is calculated to set M3 according to third feature point matching.
Optionally, described that LS-SVM sparseness is carried out to set M2 to second feature point matching, obtain third feature point
Matching is to set M3, comprising:
The reference picture is divided into N1*N2 image subblock；
For each image subblock, the second feature point matching is counted to the spy for falling into the image subblock in set M2
Sign point matching is to quantity；
Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains third
Feature Points Matching is to set M3.
Optionally, the Nm retained in each image subblock is to Feature Points Matching pair, comprising:
According to the detection ordering in characteristic point detection process, retain the preceding Nm in each image subblock to Feature Points Matching
It is right.
It is optionally, described that the reference picture and the image subject to registration are slightly matched, comprising:
Using the arest neighbors based on first threshold than secondary neighbour's mode to the reference picture and the image subject to registration
Slightly matched；
It is described that smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1,
Include:
According to the first homography matrix H1, using the arest neighbors based on second threshold than secondary neighbour's mode to the reference
Image and the image subject to registration carry out smart matching, wherein the second threshold is less than the first threshold.
It is optionally, described that first homography matrix H1 is calculated to set M1 according to fisrt feature point matching, comprising:
To fisrt feature point matching to set M1, it is single that first is calculated using the consistent RANSAC algorithm of the first stochastical sampling
Answer matrix H 1, wherein the first RANSAC algorithm uses first error threshold value；
It is described that the second homography matrix H2 is calculated to set M3 according to third feature point matching, comprising:
To third feature point matching to set M3, the second homography matrix is calculated using the 2nd RANSAC algorithm, wherein
The 2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than the first error threshold value.
Optionally, described that the reference picture and the image subject to registration are carried out according to the first homography matrix H1
Essence matching, the second feature point obtained between set of characteristic points P1 and P2 are matched to set M2, comprising:
For each characteristic point of the set of characteristic points P1 of the reference pictureIt is calculated in the image subject to registration
In initial mapping point
Calculate characteristic pointWith it in the set of characteristic points P2 of the image subject to registration corresponding characteristic pointIt is right respectively
The first Euclidean distance d between description answered1；
According to the first Euclidean distance d between description1And the Euclidean distance weight between descriptionCalculate the second Euclidean distance d between description2=wd1, wherein range pointsCloser feature
PointCorresponding weight w is smaller, and range pointsRemoter characteristic pointCorresponding weight w is bigger；
According to the second Euclidean distance between description, using the arest neighbors based on second threshold than secondary neighbour's mode pair
The reference picture and the image subject to registration carry out smart matching, obtain the second feature between set of characteristic points P1 and P2
Point matching is to set M2.
It is optionally, described that characteristic point detection and description are carried out respectively to reference picture and image subject to registration, comprising:
Using accelerate robust feature SURF algorithm to reference picture and image subject to registration carry out respectively characteristic point detection and
Description.
In the present embodiment, at least one described program is performed, and is carried out respectively to reference picture and image subject to registration
Characteristic point detection and description, obtain the set of characteristic points P1 of the reference picture and the description subclass D1 of each characteristic point, with
And the image subject to registration set of characteristic points P2 and each characteristic point description subclass D2；To the reference picture and institute
It states image subject to registration slightly to be matched, the fisrt feature point obtained between set of characteristic points P1 and P2 is matched to set M1；According to
The fisrt feature point matching calculates the first homography matrix H1 to set M1；According to the first homography matrix H1 to the reference
Image and the image subject to registration carry out smart matching, obtain the second feature point pairing set between set of characteristic points P1 and P2
Close M2；The second homography matrix H2 is calculated to set M2 according to second feature point matching；Use the second homography matrix H2
The image subject to registration is corrected, target image is obtained.In this way, at least one described program is performed, according to mapping
Characteristic point carries out the matching of characteristic point essence, can greatly improve the matching precision of Feature Points Matching centering, match to improve image
Quasi- precision.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone, computer,
Server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of method for registering images is applied to mobile terminal, which is characterized in that the described method includes:
Characteristic point detection and description are carried out to reference picture and image subject to registration respectively, obtain the characteristic point of the reference picture
Set of characteristic points P2 and each characteristic point of the description subclass D1 and the image subject to registration of set P1 and each characteristic point
Description subclass D2；
The reference picture and the image subject to registration are slightly matched, first between set of characteristic points P1 and P2 is obtained
Feature Points Matching is to set M1；
The first homography matrix H1 is calculated to set M1 according to fisrt feature point matching；
Smart matching is carried out to the reference picture and the image subject to registration according to the first homography matrix H1, obtains feature
Second feature point between point set P1 and P2 is matched to set M2；
The second homography matrix H2 is calculated to set M2 according to second feature point matching；
The image subject to registration is corrected using the second homography matrix H2, obtains target image.
2. method for registering images according to claim 1, which is characterized in that described according to second feature point matching pair
Set M2 calculates the second homography matrix H2, comprising:
LS-SVM sparseness is carried out to set M2 to second feature point matching, obtains the matching of third feature point to set M3；
The second homography matrix H2 is calculated to set M3 according to third feature point matching.
3. method for registering images according to claim 2, which is characterized in that described to the second feature point pairing set
It closes M2 and carries out LS-SVM sparseness, obtain the matching of third feature point to set M3, comprising:
The reference picture is divided into N1*N2 image subblock；
For each image subblock, the second feature point matching is counted to the characteristic point for falling into the image subblock in set M2
Matching is to quantity；
Retain the Nm in each image subblock to Feature Points Matching pair, and delete remaining Feature Points Matching pair, obtains third feature
Point matching is to set M3.
4. method for registering images according to claim 3, which is characterized in that Nm pairs retained in each image subblock
Feature Points Matching pair, comprising:
According to the detection ordering in characteristic point detection process, retain the preceding Nm in each image subblock to Feature Points Matching pair.
5. method for registering images according to claim 2, which is characterized in that it is described to the reference picture and it is described to
Registration image is slightly matched, comprising:
The reference picture and the image subject to registration are carried out than secondary neighbour's mode using the arest neighbors based on first threshold
Thick matching；
It is described that smart matching, packet are carried out to the reference picture and the image subject to registration according to the first homography matrix H1
It includes:
According to the first homography matrix H1, using the arest neighbors based on second threshold than secondary neighbour's mode to the reference picture
And the image subject to registration carries out smart matching, wherein the second threshold is less than the first threshold.
6. method for registering images according to claim 2, which is characterized in that described according to fisrt feature point matching pair
Set M1 calculates the first homography matrix H1, comprising:
To fisrt feature point matching to set M1, first is calculated using the consistent RANSAC algorithm of the first stochastical sampling and singly answers square
Battle array H1, wherein the first RANSAC algorithm uses first error threshold value；
It is described that the second homography matrix H2 is calculated to set M3 according to third feature point matching, comprising:
To third feature point matching to set M3, the second homography matrix is calculated using the 2nd RANSAC algorithm, wherein described
2nd RANSAC algorithm uses the second error threshold, and second error threshold is less than the first error threshold value.
7. method for registering images according to any one of claims 1 to 6, which is characterized in that described single according to described first
It answers matrix H 1 to carry out smart matching to the reference picture and the image subject to registration, obtains between set of characteristic points P1 and P2
Second feature point is matched to set M2, comprising:
For each characteristic point of the set of characteristic points P1 of the reference pictureIt is calculated in the image subject to registration
Initial mapping point
Calculate characteristic pointWith it in the set of characteristic points P2 of the image subject to registration corresponding characteristic pointIt is corresponding
The first Euclidean distance d between description1；
According to the first Euclidean distance d between description1And the Euclidean distance weight between descriptionCalculate the second Euclidean distance d between description2=wd1, wherein range pointsCloser feature
PointCorresponding weight w is smaller, and range pointsRemoter characteristic pointCorresponding weight w is bigger；
According to the second Euclidean distance between description, using the arest neighbors based on second threshold than secondary neighbour's mode to described
Reference picture and the image subject to registration carry out smart matching, obtain the second feature point matching between set of characteristic points P1 and P2
To set M2.
8. method for registering images according to any one of claims 1 to 6, which is characterized in that it is described to reference picture and
Image subject to registration carries out characteristic point detection and description respectively, comprising:
Characteristic point detection and description are carried out respectively to reference picture and image subject to registration using acceleration robust feature SURF algorithm.
9. a kind of mobile terminal, which is characterized in that the mobile terminal includes memory, at least one processor and is stored in institute
At least one program stated on memory and can executed at least one described processor, at least one described program by it is described extremely
A few processor realizes the step in the described in any item methods of the claims 1~8 when executing.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer executable at least
One program, which is characterized in that at least one described program makes the computer execute above-mentioned power when being executed by the computer
Benefit requires the step in 1~8 described in any item methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910472038.1A CN110189368B (en) | 2019-05-31 | 2019-05-31 | Image registration method, mobile terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910472038.1A CN110189368B (en) | 2019-05-31 | 2019-05-31 | Image registration method, mobile terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110189368A true CN110189368A (en) | 2019-08-30 |
| CN110189368B CN110189368B (en) | 2023-09-19 |
Family
ID=67719623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910472038.1A Active CN110189368B (en) | 2019-05-31 | 2019-05-31 | Image registration method, mobile terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110189368B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091590A (en) * | 2019-12-18 | 2020-05-01 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN111932593A (en) * | 2020-07-21 | 2020-11-13 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
| CN112017218A (en) * | 2020-09-09 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Image registration method and device, electronic equipment and storage medium |
| CN113362380A (en) * | 2021-06-09 | 2021-09-07 | 北京世纪好未来教育科技有限公司 | Image feature point detection model training method and device and electronic equipment thereof |
| CN113362380B (en) * | 2021-06-09 | 2024-07-02 | 北京世纪好未来教育科技有限公司 | Image feature point detection model training method and device and electronic equipment thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140072231A1 (en) * | 2012-09-10 | 2014-03-13 | Nokia Corporation | Method, apparatus and computer program product for processing of images |
| CN106023187A (en) * | 2016-05-17 | 2016-10-12 | 西北工业大学 | Image registration method based on SIFT feature and angle relative distance |
| CN106296570A (en) * | 2016-07-28 | 2017-01-04 | 北京小米移动软件有限公司 | Image processing method and device |
| CN106558074A (en) * | 2015-09-18 | 2017-04-05 | 河北工业大学 | Coarse-fine combination matching algorithm in assemble of the satellite based on rotational transformation matrix |
| WO2017107700A1 (en) * | 2015-12-21 | 2017-06-29 | 努比亚技术有限公司 | Image registration method and terminal |
| CN106919944A (en) * | 2017-01-20 | 2017-07-04 | 南京航空航天大学 | A kind of wide-angle image method for quickly identifying based on ORB algorithms |
| CN108447084A (en) * | 2018-03-17 | 2018-08-24 | 北京工业大学 | Stereo matching compensation method based on ORB features |
| CN108550165A (en) * | 2018-03-18 | 2018-09-18 | 哈尔滨工程大学 | A kind of image matching method based on local invariant feature |
| WO2018184255A1 (en) * | 2017-04-06 | 2018-10-11 | 华为技术有限公司 | Image correction method and device |
-
2019
- 2019-05-31 CN CN201910472038.1A patent/CN110189368B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140072231A1 (en) * | 2012-09-10 | 2014-03-13 | Nokia Corporation | Method, apparatus and computer program product for processing of images |
| CN106558074A (en) * | 2015-09-18 | 2017-04-05 | 河北工业大学 | Coarse-fine combination matching algorithm in assemble of the satellite based on rotational transformation matrix |
| WO2017107700A1 (en) * | 2015-12-21 | 2017-06-29 | 努比亚技术有限公司 | Image registration method and terminal |
| CN106023187A (en) * | 2016-05-17 | 2016-10-12 | 西北工业大学 | Image registration method based on SIFT feature and angle relative distance |
| CN106296570A (en) * | 2016-07-28 | 2017-01-04 | 北京小米移动软件有限公司 | Image processing method and device |
| CN106919944A (en) * | 2017-01-20 | 2017-07-04 | 南京航空航天大学 | A kind of wide-angle image method for quickly identifying based on ORB algorithms |
| WO2018184255A1 (en) * | 2017-04-06 | 2018-10-11 | 华为技术有限公司 | Image correction method and device |
| CN108447084A (en) * | 2018-03-17 | 2018-08-24 | 北京工业大学 | Stereo matching compensation method based on ORB features |
| CN108550165A (en) * | 2018-03-18 | 2018-09-18 | 哈尔滨工程大学 | A kind of image matching method based on local invariant feature |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091590A (en) * | 2019-12-18 | 2020-05-01 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN111091590B (en) * | 2019-12-18 | 2024-04-23 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN111932593A (en) * | 2020-07-21 | 2020-11-13 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
| CN111932593B (en) * | 2020-07-21 | 2024-04-09 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
| CN112017218A (en) * | 2020-09-09 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Image registration method and device, electronic equipment and storage medium |
| CN113362380A (en) * | 2021-06-09 | 2021-09-07 | 北京世纪好未来教育科技有限公司 | Image feature point detection model training method and device and electronic equipment thereof |
| CN113362380B (en) * | 2021-06-09 | 2024-07-02 | 北京世纪好未来教育科技有限公司 | Image feature point detection model training method and device and electronic equipment thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110189368B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214810A (en) | A kind of two-dimensional code display method, mobile terminal and computer readable storage medium | |
| CN108900778A (en) | A kind of image pickup method, mobile terminal and computer readable storage medium | |
| CN108289174A (en) | A kind of image pickup method, mobile terminal and computer readable storage medium | |
| CN108156374A (en) | A kind of image processing method, terminal and readable storage medium storing program for executing | |
| CN107770443A (en) | A kind of image processing method, mobile terminal and computer-readable recording medium | |
| CN107483804A (en) | A kind of image pickup method, mobile terminal and computer-readable recording medium | |
| CN110189368A (en) | Method for registering images, mobile terminal and computer readable storage medium | |
| CN109034317A (en) | A kind of two-dimensional code scanning method, terminal and computer readable storage medium | |
| CN107682630A (en) | Dual camera anti-fluttering method, mobile terminal and computer-readable recording medium | |
| CN110180181A (en) | Screenshot method, device and the computer readable storage medium of Wonderful time video | |
| CN109462700A (en) | A kind of call method, mobile terminal and computer readable storage medium | |
| CN109710159A (en) | A kind of flexible screen response method, equipment and computer readable storage medium | |
| CN110064196A (en) | Method for controlling mobile terminal, mobile terminal and computer readable storage medium | |
| CN109445660A (en) | A kind of wearable device control method, mobile terminal and wearable device | |
| CN109101301A (en) | A kind of display control method, mobile terminal and computer readable storage medium | |
| CN108121762A (en) | A kind of image processing method, mobile terminal and computer storage media | |
| CN110167004A (en) | A kind of network registering method, mobile terminal and computer readable storage medium | |
| CN110177206A (en) | Image pickup method, mobile terminal and computer readable storage medium | |
| CN109471569A (en) | A kind of screen adjustment method of mobile terminal, mobile terminal and storage medium | |
| CN108965695A (en) | A kind of image pickup method, mobile terminal and computer readable storage medium | |
| CN108879117A (en) | Mobile terminal and its antenna structure | |
| CN108228070A (en) | Input display method, device and computer readable storage medium | |
| CN109739676A (en) | A kind of operational monitoring method, mobile terminal and computer readable storage medium | |
| CN108965514A (en) | A kind of the display screen FPC structure and its mobile terminal of double screen terminal | |
| CN110381249A (en) | One kind is taken pictures processing method, terminal and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |