CN107633247A - The determination method and device of image-region - Google Patents
The determination method and device of image-region Download PDFInfo
- Publication number
- CN107633247A CN107633247A CN201710700996.0A CN201710700996A CN107633247A CN 107633247 A CN107633247 A CN 107633247A CN 201710700996 A CN201710700996 A CN 201710700996A CN 107633247 A CN107633247 A CN 107633247A
- Authority
- CN
- China
- Prior art keywords
- field picture
- image
- mtd
- positional information
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of determination method and device of image-region, this method includes:The first image-region for meeting user's request is determined from the first two field picture of acquisition, and determines positional information of first image-region in the first two field picture;At least two key points, and positional information of the key point in the first two field picture are determined from the first image-region;Using LK optical flow methods, it is determined that positional information of the key point determined from the first image-region in the second two field picture, wherein, the first two field picture and the second two field picture are two adjacent two field pictures;According to positional information of the key point in the first two field picture and the positional information in the second two field picture, rigid body change information of second two field picture relative to the first two field picture is calculated, wherein, rigid body change information includes translation information and rotation information;Using rigid body change information and the first image-region in the positional information of the first two field picture, the second image-region for meeting user's request is determined from the second two field picture.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of determination method and device of image-region.
Background technology
In image procossing, being sketched the contours of from processed image in a manner of square frame, circle, ellipse, irregular polygon etc. needs
Region to be processed, referred to as area-of-interest (Region Of Interest, abbreviation ROI).ROI is one selected from image
Individual image-region, this region are graphical analysis emphasis of interest.The region is drawn a circle to approve to be further processed.
In same spot for photography, camera is shot to moving object at different moments, the position of the ROI in obtained image
In the presence of change.In the related art, by image matching algorithm, ROI is found in the image shot at different moments from camera.On
The degree of accuracy for stating image matching algorithm is relatively low.
Accordingly, it is desirable to provide a kind of new technical method, is improved for above-mentioned technical problem of the prior art.
The content of the invention
It is an object of the present invention to provide the new solution of a kind of determination method of image-region.
According to the first aspect of the invention, there is provided a kind of determination method of image-region, including:
The first image-region for meeting user's request is determined from the first two field picture of acquisition, and determines first figure
As positional information of the region in first two field picture;
At least two key points are determined from described first image region, and determine at least two key point in institute
State the positional information in the first two field picture;
Using LK optical flow methods, at least two key points determined from described first image region are calculated in the second frame figure
Positional information as in, wherein, first two field picture and second two field picture are two adjacent two field pictures;
According to positional information of at least two key point in first two field picture and in second two field picture
In positional information, calculate the second image-region for meeting user's request in second two field picture relative to first figure
As the rigid body change information in region, wherein, the rigid body change information includes translation information and rotation information;
Using the rigid body change information and described first image region first two field picture positional information, from institute
State the positional information that second image-region is determined in the second two field picture.
Alternatively, methods described also includes:
Identical two-dimensional coordinate system is set up in each two field picture;
Using the two-dimensional coordinate system, the positional information in described first image region and at least two key point are determined
Positional information in first two field picture.
Optionally it is determined that positional information of the described first image region in first two field picture, including:
The characteristic point of the position for representing described first image region is selected from described first image region;
Determine positional information of the characteristic point in first two field picture;
Determine described first image region described according to positional information of the characteristic point in first two field picture
Positional information in first two field picture.
Alternatively, at least two key points are determined from described first image region, including:
Using Harris angle point algorithms, at least two key point is determined from described first image region.
Alternatively, using LK optical flow methods, at least two key points determined from described first image region is calculated and are existed
Positional information in second two field picture, including:
Using LK optical flow methods, the movement at least two key points determined from described first image region is calculated
Amount;
According to the amount of movement of at least two key point and at least two key point in first two field picture
Positional information, determine positional information of at least two key point in second two field picture.
Alternatively, according to positional information of at least two key point in first two field picture and described second
Positional information in two field picture, rigid body change information of second two field picture relative to first two field picture is calculated, wrapped
Include:
Based on following calculating formula, translation information and rotation of second two field picture relative to first two field picture are calculated
Transfering the letter breath,
Wherein, (x, y) is positional information of the key point in first two field picture, and (x', y') is key point described
Positional information in second two field picture, R are 2x2 spin matrixs, and t is two-dimension translational vector,For 3x3 matrix.
Alternatively, believed using the rigid body change information and described first image region in the position of first two field picture
Breath, the positional information of second image-region is determined from second two field picture, including:
Using the rigid body change information, positional information of the characteristic point in second two field picture is determined;
According to positional information of the characteristic point in second two field picture, determined from second two field picture described in
The positional information of second image-region.
According to the second aspect of the invention, there is provided a kind of determining device of image-region, including:
First determining module, for determining to meet the first image-region of user's request from the first two field picture of acquisition,
And determine positional information of the described first image region in first two field picture;
Second determining module, for determining at least two key points from described first image region, and described in determination
Positional information of at least two key points in first two field picture;
First computing module, for utilizing LK optical flow methods, calculate at least two determined from described first image region
Positional information of the individual key point in the second two field picture, wherein, first two field picture and second two field picture are two phases
Adjacent two field picture;
Second computing module, for according to positional information of at least two key point in first two field picture and
Positional information in second two field picture, calculate the second image-region for meeting user's request in second two field picture
Relative to the rigid body change information in described first image region, wherein, the rigid body change information includes translation information and rotation
Information;
3rd determining module, for utilizing the rigid body change information and described first image region in the first frame figure
The positional information of picture, the positional information of second image-region is determined from second two field picture.
Alternatively, second computing module is additionally operable to:
Based on following calculating formula, translation information and rotation of second two field picture relative to first two field picture are calculated
Transfering the letter breath,
Wherein, (x, y) is positional information of the key point in first two field picture, and (x', y') is key point described
Positional information in second two field picture, R are 2x2 spin matrixs, and t is two-dimension translational vector,For 3x3 matrix.
According to the third aspect of the invention we, there is provided a kind of determining device of image-region, including:Memory and processing
Device, wherein, the memory storage executable instruction, the executable instruction controls the processor to be operated with execution
State the determination method of the image-region described in any one.
The determination method and device of image-region provided by the invention, realizes image-region interested in user really
It is fixed.In addition, the determination method and device of image-region provided by the invention, improves the determination of user's image-region interested
The degree of accuracy.
By referring to the drawings to the present invention exemplary embodiment detailed description, further feature of the invention and its
Advantage will be made apparent from.
Brief description of the drawings
It is combined in the description and the accompanying drawing of a part for constitution instruction shows embodiments of the invention, and even
It is used for the principle for explaining the present invention together with its explanation.
Fig. 1 shows the process chart of the determination method of image-region according to an embodiment of the invention.
Fig. 2 shows the schematic diagram of the first two field picture according to an embodiment of the invention.
Fig. 3 shows the schematic diagram of the second two field picture according to an embodiment of the invention.
Fig. 4 shows the structural representation of the determining device of image-region according to an embodiment of the invention.
Fig. 5 shows another structural representation of the determining device of image-region according to an embodiment of the invention.
Embodiment
The various exemplary embodiments of the present invention are described in detail now with reference to accompanying drawing.It should be noted that:Unless have in addition
Body illustrates that the unlimited system of part and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The scope of invention.
The description only actually at least one exemplary embodiment is illustrative to be never used as to the present invention below
And its application or any restrictions that use.
It may be not discussed in detail for technology, method and apparatus known to person of ordinary skill in the relevant, but suitable
In the case of, the technology, method and apparatus should be considered as part for specification.
In shown here and discussion all examples, any occurrence should be construed as merely exemplary, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should be noted that:Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent accompanying drawing in individual accompanying drawing.
An embodiment provides a kind of determination method of image-region.Fig. 1 is shown according to the present invention one
The process chart of the determination method of the image-region of individual embodiment.Referring to Fig. 1, this method comprises at least following steps S101 extremely
Step S105.
Step S101, the first image-region for meeting user's request is determined from the first two field picture of acquisition, and determined
Positional information of first image-region in the first two field picture;
Step S102, at least two key points are determined from the first image-region, and determine that at least two key points exist
Positional information in first two field picture;
Step S103, using LK optical flow methods, it is determined that at least two key points determined from the first image-region are
Positional information in two two field pictures, wherein, the first two field picture and the second two field picture are two adjacent two field pictures;
Step S104, according to positional information of at least two key points in the first two field picture and in the second two field picture
Positional information, rigid body change information of second two field picture relative to the first two field picture is calculated, wherein, rigid body change information includes
Translation information and rotation information;
Step S105, using rigid body change information and the first image-region the first two field picture positional information, from second
The second image-region for meeting user's request is determined in two field picture.
In one embodiment of the present of invention, identical two-dimensional coordinate system is set up in each two field picture, i.e., each two field picture
In the two-dimensional coordinate system set up there is identical origin, X-axis and Y-axis.
Fig. 2 shows the schematic diagram of the first two field picture according to an embodiment of the invention.Fig. 3 is shown according to the present invention
The schematic diagram of second two field picture of one embodiment.Referring to Fig. 2 and Fig. 3, the two-dimensional coordinate system set up in the first two field picture and
The two-dimensional coordinate system set up in the second two field picture has identical origin, X-axis and Y-axis, i.e., two-dimensional coordinate system is with positioned at each
The point in the two field picture lower left corner is as origin, using the length direction parallel to each two field picture as X-direction, with parallel to each frame figure
The width of picture is as Y direction.
In one embodiment of the present of invention, using the two-dimensional coordinate system for being built up in the first two field picture, the first image district is determined
Positional information of the domain in the first two field picture.Specifically, first, selected from the first image-region for representing the first image district
The characteristic point of the position in domain, then, it is determined that positional information of the characteristic point in the first two field picture, finally, according to characteristic point
Positional information in one two field picture determines positional information of first image-region in the first two field picture.With first shown in Fig. 2
Exemplified by two field picture, using the region that square frame marks as the first image-region for meeting user's request, first, with positioned at the first image
The point A in the upper left corner in region, the point B in the lower left corner, the point C in the upper right corner and the point D in the lower right corner, which are used as, to be used to represent the first image district
The characteristic point of the position in domain, then, using the two-dimensional coordinate system set up in the first two field picture, determine that aforementioned four characteristic point exists
Positional information in first two field picture, finally, is determined according to positional information of the aforementioned four characteristic point in the first two field picture
Positional information of one image-region in the first two field picture.
It should be noted that the first image-region is square region, correspondingly, using the upper left corner for being located at square region
Point A, the lower left corner point B, the point C in the upper right corner and the point D in the lower right corner as represent the first image-region position characteristic point.
It is circular as expression using the central point of circle and any point in the circular length of side when the first image-region is circular
The characteristic point of the position in region.First border circular areas can also be other shapes, on the other hand, the present invention does not make any restriction.
In one embodiment of the present of invention, using Harris angle point algorithms, at least two are determined from the first image-region
Key point.Harris angle point algorithms are to be detected to obtain angle point based on image pixel gray level value changes gradient, herein are related to
Angle point is key point.Region around corner location is the very big region of pixel grey scale value changes, and its gradient is also very big.
Region around non-corner location is the of substantially equal region of grey scale pixel value, and its gradient is also smaller.The identification of angle steel joint is led to
It is often to be completed using a detection window.If go up the mobile detection window, the detection window in all directions in the picture
There occurs larger change for gray scale in corresponding image-region, then is considered as angle point in detection window being present.If
Upper mobile detection window, the gray scale corresponding to the detection window in image-region do not become substantially in all directions in image
Change, then be considered as that angle point is not present in detection window.By taking the first two field picture shown in Fig. 2 as an example, Fig. 2, which includes, to be shot
6 objects arrived, the background color of the first two field picture shown in Fig. 2 is black, and the color of 6 objects shown in Fig. 2 is white.
By Harris angle point algorithms, multiple key points, the i.e. point identified in Fig. 2 with circle are detected in the first image-region.
It should be noted that the point identified in Fig. 2 with circle is not all key points detected using Harris angle point algorithms,
It only represent a part of key point.
After at least two key points are determined from the first image-region, sat using the two dimension for being built up in the first two field picture
Mark system, determines positional information of above-mentioned at least two key point in the first two field picture.
In one embodiment of the present of invention, first, using LK optical flow methods, calculate what is determined from the first image-region
The amount of movement of at least two key points, then, according to the amount of movement of at least two key points and at least two key points first
Positional information in two field picture, determine positional information of at least two key points in the second two field picture.Light stream is spatial movement
The instantaneous velocity of pixel motion of the object on imaging plane.Sports ground is the real motion of three-dimensional world, because image is to take the photograph
Projection of the camera in its plane, sports ground can not be directly obtained from two dimensional image, but light can be obtained from image sequence
Flow field, optical flow field are projection of the sports ground in two dimensional image plane.By LK optical flow methods, the fortune in the second two field picture can obtain
Animal body relative to the moving object in the first two field picture motion vector.The general principle of LK optical flow methods is:Utilize consecutive frame
Brightness shape constancy between image, following image constraint equations are established,
Wherein, I (u, v, t) is certain
The brightness value of one pixel, (u+ Δs u, v+ Δ v, t+ Δ t) is the brightness value after pixel movement to I, and Δ u, Δ v are respectively light
Two motion vectors of stream, time intervals of the Δ t between consecutive frame.Assuming that time interval is sufficiently small, thenUsing image constraint equation, be calculated two of light stream corresponding to consecutive frame move to
Amount.Two motion vectors of light stream are the amount of movement for each key point determined.Then, according to the amount of movement of each key point,
In conjunction with positional information of the corresponding each key point in the first two field picture, position of each key point in the second two field picture is determined
Information.Specifically, using the two-dimensional coordinate system being built up in the second two field picture, represent each key point in the second two field picture
Positional information.
When the object of shooting is kept in motion, the image-region for meeting user's request in the second two field picture relative to
Change in location can occur for the image-region for meeting user's request in the first two field picture.It should be noted that in the first two field picture
The image-region for meeting user's request relative to the image-region for meeting user's request in the first two field picture only there occurs
Rigid body changes, i.e., is not only scaled there occurs rotation and translation change.In one embodiment of the present of invention, based on following
Calculating formula (1), the second image-region for meeting user's request in the second two field picture is calculated relative to the flat of the first image-region
Information and rotation information are moved,
Wherein, (x, y) is a certain key point in the first two field picture
Positional information, (x', y') is positional information of the key point in the second two field picture, and R is 2x2 spin matrixs, and t is flat for two dimension
The amount of shifting to,For 3x3 matrix.It should be noted that t represents the second image-region relative to the first image-region
Translation information, R represent rotation information of second image-region relative to the first image-region.
For above-mentioned calculating formula (1) to meeting the second image-region of user's request relative to the first figure in the second two field picture
As the translation information in region and the calculating process of rotation information are specifically described.If
Due to vector x ' and vectorial HEX is two parallel vectors, then both multiplication crosses are equal to 0, i.e.,
x′×HEX=0-calculating formula (3),
The multiplication cross computing of calculating formula (3) is converted into point multiplication operation, obtains following calculating formulas (4),
Wherein, i represents i-th of pass
Key point, [x 'i]xFor vector x 'iMultiplication cross matrix, above-mentioned calculating formula is deployed, obtains calculating formula (5), [x 'i]x HExi=
h11y′ixi-h21x′iyi+h12y′iyi-h22x′iyi+h13y′i-h23x′i=biA=0-calculating formula (5), wherein, bi=[y 'ixi -
x′iyi y′iyi -x′iyi y′i -x′i]T, a=[h11 h21 h12 h22 h13 h23]T, a finally is obtained using least square method,
And then obtain translation information and rotation information of second image-region relative to the first image-region.
Meet the second image-region of user's request relative to the firm of the first image-region in the second two field picture is determined
After body change information, first, using rigid body change information, positional information of the characteristic point in the second two field picture is determined, then,
According to positional information of the characteristic point in the second two field picture, the positional information of the second image-region is determined from the second two field picture.
Specifically, by taking the second two field picture shown in the first two field picture and Fig. 3 shown in Fig. 2 as an example, A points, B points, C points and D shown in Fig. 2
Characteristic point of the point as the position for representing the first image-region, positional information corresponding to A points, B points, C points and D points is distinguished
Above-mentioned calculating formula (1) is substituted into, obtains A' points, B' points, C' points and positional information corresponding to D' points, A', B', C' and D' point are expression
The characteristic point of the position of second image-region.Because D' points are beyond the scope of the second two field picture, so Fig. 3 illustrate only A'
Point, B' points and C' points, do not show D' points.
Based on same inventive concept, the invention provides a kind of determining device of image-region.Fig. 4 is shown according to this hair
The structural representation of the determining device of the image-region of bright one embodiment.Referring to Fig. 4, the device comprises at least:First determines
Module 410, for the first image-region for determining to meet user's request from the first two field picture of acquisition, and determine the first figure
As positional information of the region in the first two field picture;Second determining module 420, for determining at least two from the first image-region
Individual key point, and determine positional information of at least two key points in the first two field picture;First computing module 430, is used for
Using LK optical flow methods, position letter of at least two key points determined from the first image-region in the second two field picture is calculated
Breath, wherein, the first two field picture and the second two field picture are two adjacent two field pictures;Second computing module 440, for according at least two
Positional information of the individual key point in the first two field picture and the positional information in the second two field picture, calculate in the second two field picture
Meet the second image-region of user's request relative to the rigid body change information of the first image-region, wherein, rigid body change information
Including translation information and rotation information;3rd determining module 450, for using rigid body change information and the first image-region the
The positional information of one two field picture, the positional information of the second image-region is determined from the second two field picture.
In one embodiment of the present of invention, identical two-dimensional coordinate system is set up in each two field picture, i.e., each two field picture
In the two-dimensional coordinate system set up there is identical origin, X-axis and Y-axis.
In one embodiment of the present of invention, using the two-dimensional coordinate system for being built up in the first two field picture, the first image district is determined
Positional information of the domain in the first two field picture.Specifically, first, selected from the first image-region for representing the first image district
The characteristic point of the position in domain, then, it is determined that positional information of the characteristic point in the first two field picture, finally, according to characteristic point
Positional information in one two field picture determines positional information of first image-region in the first two field picture.
In one embodiment of the present of invention, the second determining module 420 is used to utilize Harris angle point algorithms, from the first image
At least two key points are determined in region.Harris angle point algorithms are based on image pixel gray level value changes gradient detect
To angle point, the angle point herein being related to is key point.
In one embodiment of the present of invention, the first computing module 430 is used to utilize LK optical flow methods, calculates from the first image
The amount of movement at least two key points determined in region, then, according to the amount of movement of at least two key points and at least two
Positional information of the individual key point in the first two field picture, determine positional information of at least two key points in the second two field picture.
In one embodiment of the present of invention, the second computing module 430 is additionally operable to:Based on following calculating formula (1), is calculated
Two two field pictures relative to the first two field picture translation information and rotation information,
Wherein, (x, y) is position of the key point in the first two field picture
Confidence ceases, and (x', y') be positional information of the key point in the second two field picture, and R is 2x2 spin matrixs, t for two-dimension translational to
Amount,For 3x3 matrix.
Fig. 5 shows another structural representation of the determining device of image-region according to an embodiment of the invention.
Referring to Fig. 5, the device comprises at least:Memory 520 and processor 510, wherein, memory 510 stores executable instruction, can hold
Row instruction control processor 520 operated with perform any of the above described one image-region determination method.
The present invention can be system, method and/or computer program product.Computer program product can include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer-readable recording medium can keep and store to perform the tangible of the instruction that uses of equipment by instruction
Equipment.Computer-readable recording medium for example can be-- but be not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electromagnetism storage device, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer-readable recording medium
More specifically example (non exhaustive list) includes:Portable computer diskette, hard disk, random access memory (RAM), read-only deposit
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), portable
Compact disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not construed as instantaneous signal in itself, the electromagnetic wave of such as radio wave or other Free propagations, leads to
Cross the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer-readable recording medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network can include copper transmission cable, optical fiber is transmitted, is wirelessly transferred, router, fire wall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment receive from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
For perform the computer program instructions that operate of the present invention can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, programming language-such as Smalltalk of the programming language including object-oriented,
C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer-readable program refers to
Order fully can on the user computer be performed, partly performed on the user computer, the software kit independent as one
Perform, part performs or completely on remote computer or server on the remote computer on the user computer for part
Perform.In the situation of remote computer is related to, remote computer can be by the network of any kind-include LAN
Or wide area network (WAN) (LAN)-subscriber computer is connected to, or, it may be connected to outer computer (such as utilize internet
Service provider passes through Internet connection).In certain embodiments, believe by using the state of computer-readable program instructions
Breath comes personalized customization electronic circuit, such as PLD, field programmable gate array (FPGA) or FPGA
Array (PLA), the electronic circuit can perform computer-readable program instructions, so as to realize various aspects of the invention.
Referring herein to method, apparatus (system) and computer program product according to embodiments of the present invention flow chart and/
Or block diagram describes various aspects of the invention.It should be appreciated that each square frame and flow chart of flow chart and/or block diagram and/
Or in block diagram each square frame combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special-purpose computer or other programmable datas
The processor of processing unit, so as to produce a kind of machine so that these instructions are passing through computer or other programmable datas
During the computing device of processing unit, work(specified in one or more of implementation process figure and/or block diagram square frame is generated
The device of energy/action.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
Order causes computer, programmable data processing unit and/or other equipment to work in a specific way, so as to be stored with instruction
Computer-readable medium then includes a manufacture, and it is included in one or more of implementation process figure and/or block diagram square frame
The instruction of the various aspects of defined function/action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment so that series of operation steps is performed on computer, other programmable data processing units or miscellaneous equipment, with production
Raw computer implemented process, so that performed on computer, other programmable data processing units or miscellaneous equipment
Instruct function/action specified in one or more of implementation process figure and/or block diagram square frame.
Flow chart and block diagram in accompanying drawing show system, method and the computer journey of multiple embodiments according to the present invention
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
One module of table, program segment or a part for instruction, module, program segment or a part for instruction include one or more be used in fact
The executable instruction of logic function as defined in existing.At some as in the realization replaced, the function of being marked in square frame can also
To occur different from the order marked in accompanying drawing.For example, two continuous square frames can essentially perform substantially in parallel, it
Can also perform in the opposite order sometimes, this is depending on involved function.It is also noted that block diagram and/or flow
The combination of each square frame and block diagram in figure and/or the square frame in flow chart, function or action as defined in performing can be used
Special hardware based system is realized, or can be realized with the combination of specialized hardware and computer instruction.For this
It is well known that, realized for art personnel by hardware mode, realized by software mode and pass through software and hardware
With reference to mode realize it is all of equal value.
It is described above various embodiments of the present invention, described above is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.In the case of without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
Best explaining the principle of each embodiment, practical application or to the technological improvement in market, or make the art its
Its those of ordinary skill is understood that each embodiment disclosed herein.The scope of the present invention is defined by the appended claims.
Claims (10)
1. a kind of determination method of image-region, it is characterised in that including:
The first image-region for meeting user's request is determined from the first two field picture of acquisition, and determines described first image area
Positional information of the domain in first two field picture;
Determine at least two key points from described first image region, and determine at least two key point described the
Positional information in one two field picture;
Using LK optical flow methods, at least two key points determined from described first image region are calculated in the second two field picture
Positional information, wherein, first two field picture and second two field picture are two adjacent two field pictures;
According to positional information of at least two key point in first two field picture and in second two field picture
Positional information, the second image-region for meeting user's request in second two field picture is calculated relative to described first image area
The rigid body change information in domain, wherein, the rigid body change information includes translation information and rotation information;
Using the rigid body change information and described first image region first two field picture positional information, from described
The positional information of second image-region is determined in two two field pictures.
2. according to the method for claim 1, it is characterised in that methods described also includes:
Identical two-dimensional coordinate system is set up in each two field picture;
Using the two-dimensional coordinate system, determine described first image region positional information and at least two key point in institute
State the positional information in the first two field picture.
3. according to the method for claim 1, it is characterised in that determine described first image region in first two field picture
In positional information, including:
The characteristic point of the position for representing described first image region is selected from described first image region;
Determine positional information of the characteristic point in first two field picture;
Determine described first image region described first according to positional information of the characteristic point in first two field picture
Positional information in two field picture.
4. according to the method for claim 1, it is characterised in that determine that at least two is crucial from described first image region
Point, including:
Using Harris angle point algorithms, at least two key point is determined from described first image region.
5. according to the method for claim 1, it is characterised in that using LK optical flow methods, calculate from described first image region
In the positional information of at least two key points determined in the second two field picture, including:
Using LK optical flow methods, the amount of movement at least two key points determined from described first image region is calculated;
According to the position of the amount of movement of at least two key point and at least two key point in first two field picture
Confidence ceases, and determines positional information of at least two key point in second two field picture.
6. according to the method for claim 1, it is characterised in that according at least two key point in the first frame figure
Positional information as in and the positional information in second two field picture, second two field picture is calculated relative to described the
The rigid body change information of one two field picture, including:
Based on following calculating formula, calculate second two field picture and believe relative to the translation information of first two field picture and rotation
Breath,
<mrow>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msup>
<mi>x</mi>
<mo>&prime;</mo>
</msup>
</mtd>
</mtr>
<mtr>
<mtd>
<msup>
<mi>y</mi>
<mo>&prime;</mo>
</msup>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>R</mi>
</mtd>
<mtd>
<mi>t</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<msup>
<mn>0</mn>
<mi>T</mi>
</msup>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>x</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>y</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>,</mo>
</mrow>
Wherein, (x, y) is positional information of the key point in first two field picture, and (x', y') is key point described second
Positional information in two field picture, R are 2x2 spin matrixs, and t is two-dimension translational vector,For 3x3 matrix.
7. according to the method for claim 3, it is characterised in that utilize the rigid body change information and described first image area
Domain determines the position letter of second image-region in the positional information of first two field picture from second two field picture
Breath, including:
Using the rigid body change information, positional information of the characteristic point in second two field picture is determined;
According to positional information of the characteristic point in second two field picture, described second is determined from second two field picture
The positional information of image-region.
A kind of 8. determining device of image-region, it is characterised in that including:
First determining module, for the first image-region for determining to meet user's request from the first two field picture of acquisition, and
Determine positional information of the described first image region in first two field picture;
Second determining module, for determining at least two key points from described first image region, and described in determination at least
Positional information of two key points in first two field picture;
First computing module, for utilizing LK optical flow methods, calculate at least two passes determined from described first image region
Positional information of the key o'clock in the second two field picture, wherein, first two field picture and second two field picture are two consecutive frames
Image;
Second computing module, for according to positional information of at least two key point in first two field picture and in institute
The positional information in the second two field picture is stated, calculates and meets that the second image-region of user's request is relative in second two field picture
Rigid body change information in described first image region, wherein, the rigid body change information includes translation information and rotation information;
3rd determining module, for utilizing the rigid body change information and described first image region in first two field picture
Positional information, the positional information of second image-region is determined from second two field picture.
9. device according to claim 8, it is characterised in that second computing module is additionally operable to:
Based on following calculating formula, calculate second two field picture and believe relative to the translation information of first two field picture and rotation
Breath,
<mrow>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msup>
<mi>x</mi>
<mo>&prime;</mo>
</msup>
</mtd>
</mtr>
<mtr>
<mtd>
<msup>
<mi>y</mi>
<mo>&prime;</mo>
</msup>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>R</mi>
</mtd>
<mtd>
<mi>t</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<msup>
<mn>0</mn>
<mi>T</mi>
</msup>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>x</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>y</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>,</mo>
</mrow>
Wherein, (x, y) is positional information of the key point in first two field picture, and (x', y') is key point described second
Positional information in two field picture, R are 2x2 spin matrixs, and t is two-dimension translational vector,For 3x3 matrix.
A kind of 10. determining device of image-region, it is characterised in that including:Memory and processor, wherein, the memory
Executable instruction is stored, the executable instruction controls the processor to be operated to perform according in claim 1-7
The determination method of image-region described in any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710700996.0A CN107633247A (en) | 2017-08-16 | 2017-08-16 | The determination method and device of image-region |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710700996.0A CN107633247A (en) | 2017-08-16 | 2017-08-16 | The determination method and device of image-region |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107633247A true CN107633247A (en) | 2018-01-26 |
Family
ID=61099718
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710700996.0A Pending CN107633247A (en) | 2017-08-16 | 2017-08-16 | The determination method and device of image-region |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107633247A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598744A (en) * | 2018-11-29 | 2019-04-09 | 广州市百果园信息技术有限公司 | A kind of method, apparatus of video tracking, equipment and storage medium |
CN110310299A (en) * | 2019-07-03 | 2019-10-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for training light stream network and handling image |
WO2020024483A1 (en) * | 2018-08-03 | 2020-02-06 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing image |
CN111028283A (en) * | 2019-12-11 | 2020-04-17 | 北京迈格威科技有限公司 | Image detection method, device, equipment and readable storage medium |
CN111815754A (en) * | 2019-04-12 | 2020-10-23 | Oppo广东移动通信有限公司 | Three-dimensional information determination method, three-dimensional information determination device and terminal equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101901481A (en) * | 2010-08-11 | 2010-12-01 | 深圳市蓝韵实业有限公司 | Image mosaic method |
US20100328532A1 (en) * | 2009-06-30 | 2010-12-30 | Hung Wei Wu | Image generating device, static text detecting device and method thereof |
CN102456226A (en) * | 2010-10-22 | 2012-05-16 | 财团法人工业技术研究院 | Region-of-interest tracking system, method and computer program product |
CN102609708A (en) * | 2012-01-15 | 2012-07-25 | 北京工业大学 | Method for calculating translation vector and rotary parameters of central point of barbell |
CN103985136A (en) * | 2014-03-21 | 2014-08-13 | 南京大学 | Target tracking method based on local feature point feature flow pattern |
CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电(苏州)有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
-
2017
- 2017-08-16 CN CN201710700996.0A patent/CN107633247A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100328532A1 (en) * | 2009-06-30 | 2010-12-30 | Hung Wei Wu | Image generating device, static text detecting device and method thereof |
CN101901481A (en) * | 2010-08-11 | 2010-12-01 | 深圳市蓝韵实业有限公司 | Image mosaic method |
CN102456226A (en) * | 2010-10-22 | 2012-05-16 | 财团法人工业技术研究院 | Region-of-interest tracking system, method and computer program product |
CN102609708A (en) * | 2012-01-15 | 2012-07-25 | 北京工业大学 | Method for calculating translation vector and rotary parameters of central point of barbell |
CN103985136A (en) * | 2014-03-21 | 2014-08-13 | 南京大学 | Target tracking method based on local feature point feature flow pattern |
CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电(苏州)有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020024483A1 (en) * | 2018-08-03 | 2020-02-06 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing image |
US11403730B2 (en) | 2018-08-03 | 2022-08-02 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for processing image |
CN109598744A (en) * | 2018-11-29 | 2019-04-09 | 广州市百果园信息技术有限公司 | A kind of method, apparatus of video tracking, equipment and storage medium |
CN111815754A (en) * | 2019-04-12 | 2020-10-23 | Oppo广东移动通信有限公司 | Three-dimensional information determination method, three-dimensional information determination device and terminal equipment |
CN110310299A (en) * | 2019-07-03 | 2019-10-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for training light stream network and handling image |
CN110310299B (en) * | 2019-07-03 | 2021-11-19 | 北京字节跳动网络技术有限公司 | Method and apparatus for training optical flow network, and method and apparatus for processing image |
CN111028283A (en) * | 2019-12-11 | 2020-04-17 | 北京迈格威科技有限公司 | Image detection method, device, equipment and readable storage medium |
CN111028283B (en) * | 2019-12-11 | 2024-01-12 | 北京迈格威科技有限公司 | Image detection method, device, equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11238644B2 (en) | Image processing method and apparatus, storage medium, and computer device | |
CN107633247A (en) | The determination method and device of image-region | |
US20180012411A1 (en) | Augmented Reality Methods and Devices | |
CN109215080A (en) | 6D Attitude estimation network training method and device based on deep learning Iterative matching | |
US20200126289A1 (en) | Method and system for creating a virtual 3d model | |
US10334168B2 (en) | Threshold determination in a RANSAC algorithm | |
CN103582893B (en) | The two dimensional image represented for augmented reality is obtained | |
CN103703758B (en) | mobile augmented reality system | |
CN105453559B (en) | Handhold portable optical scanner and its application method | |
CN109407547A (en) | Multi-cam assemblage on-orbit test method and system towards panoramic vision perception | |
CN109003325A (en) | A kind of method of three-dimensional reconstruction, medium, device and calculate equipment | |
JP2018163654A (en) | System and method for telecom inventory management | |
KR20180069786A (en) | Method and system for generating an image file of a 3D garment model for a 3D body model | |
EP3987443A1 (en) | Recurrent multi-task convolutional neural network architecture | |
CN110148177A (en) | For determining the method, apparatus of the attitude angle of camera, calculating equipment, computer readable storage medium and acquisition entity | |
US20240070972A1 (en) | Rendering new images of scenes using geometry-aware neural networks conditioned on latent variables | |
Zhu et al. | Spatially-varying outdoor lighting estimation from intrinsics | |
Fieraru et al. | REMIPS: Physically consistent 3D reconstruction of multiple interacting people under weak supervision | |
Park et al. | Neural object learning for 6d pose estimation using a few cluttered images | |
He et al. | Volumeter: 3D human body parameters measurement with a single Kinect | |
Sun et al. | Three-dimensional structural displacement measurement using monocular vision and deep learning based pose estimation | |
Concha et al. | Performance evaluation of a 3D multi-view-based particle filter for visual object tracking using GPUs and multicore CPUs | |
US11595568B2 (en) | System for generating a three-dimensional scene of a physical environment | |
WO2021173489A1 (en) | Apparatus, method, and system for providing a three-dimensional texture using uv representation | |
CN110689609A (en) | Image processing method, image processing device, electronic equipment and 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180126 |
|
RJ01 | Rejection of invention patent application after publication |