CN107135331A - The UAV Video antihunt means and device of low-latitude flying scene - Google Patents
The UAV Video antihunt means and device of low-latitude flying scene Download PDFInfo
- Publication number
- CN107135331A CN107135331A CN201710198431.7A CN201710198431A CN107135331A CN 107135331 A CN107135331 A CN 107135331A CN 201710198431 A CN201710198431 A CN 201710198431A CN 107135331 A CN107135331 A CN 107135331A
- Authority
- CN
- China
- Prior art keywords
- characteristic point
- mrow
- track
- msub
- coordinate
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/144—Movement detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/682—Vibration or motion blur correction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides the UAV Video antihunt means and device of a kind of low-latitude flying scene, and wherein method includes:Obtain UAV Video to be stablized, feature point extraction is carried out to each frame in video, connection obtains the track of each characteristic point, track is divided into long track and short track by threshold value, it can be calculated based on long track and smooth long track and obtain the corresponding global change's matrix of every frame picture, with reference to the corresponding global change's matrix of every frame picture, short track and low pass filter, smooth short track can be obtained, finally calculated using many plane optimizing methods with reference to long track with short track, the UAV Video stablized.The present invention is classified to feature point trajectory, while characteristic point abundance regional stability effect is ensured, stablizing effect is served to the insufficient region of characteristic point, the unstable influence in many plane optimizing method edges in low-latitude flying scene can be solved to a certain extent, so as to improve the stablizing effect of UAV Video.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of UAV Video antihunt means of low-latitude flying scene and
Device.
Background technology
UAV Video stabilization technique, is mainly caused to solve the reasons such as atmospheric turbulance, the vibrations of rotation oar and posture changing
UAV Video float problem.The technology can shoot the image information in video according only to unmanned plane, pass through computer
Graph transformation, restores stable field of view, and shooting video usability to enhancing unmanned plane is significant.
, will be a certain mainly based on estimating the transformation matrix between image sequence in current unmanned plane video stabilizing method
Frame is compensated as benchmark to all frames, makes the visual angle of all frames close to selected frame, transformation matrix can also be carried out smoothly,
So as to obtain a series of metastable images.Due to this kind of method to every frame only with linear transformation, thus algorithm robustness
Good, processing speed is fast, is adapted to use when high aerial and video content is stable.However, in the photographed scene of low latitude, currently without
Man-machine video stabilizing method still has deficiency, on the one hand can not solve the problem of parallax experienced of low latitude Scene, on the other hand also be vulnerable to
The influence of roller shutter effect.
The content of the invention
The present invention provides the UAV Video antihunt means and device of a kind of low-latitude flying scene, for solve it is existing nobody
The problem of machine video stabilization technology low-to-medium altitude flying scene poor availability,.
The first aspect of the invention is to provide a kind of UAV Video antihunt means of low-latitude flying scene, including:
Video to be stablized is extracted per the characteristic point in frame picture, the track and track that connection obtains each characteristic point are long
Degree;
The path length of characteristic point is compared with feature point trajectory length threshold, respectively obtain the long track of characteristic point and
The short track of characteristic point;
The coordinate value of the long track of characteristic point is smoothed using LPF, the long rail of characteristic point after obtaining smoothly
Mark;
To the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizing calculating, obtain every frame picture
Corresponding global change's matrix;
Line translation and smooth place are entered to the coordinate of corresponding characteristic point in the short track of characteristic point using global change's matrix
Reason, the short track of characteristic point after obtaining smoothly;
To it is described it is smooth after the long track of characteristic point with it is smooth after the short track of characteristic point merge and obtain characteristic point and put down
Slide rail mark, is calculated each feature point trajectory and characteristic point smooth track using many plane optimizing methods, obtains every frame figure
The corresponding object transformation matrix of piece;
Stable video is treated successively, and coordinate change is carried out using corresponding object transformation matrix per each pixel in frame picture
Change, the UAV Video stablized.
Further, it is described to the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizing meters
Calculate, obtain the corresponding global change's matrix of every frame picture, including:
For every frame picture, the coordinate of each corresponding characteristic point of picture described in the long track of each characteristic point is obtained;
The coordinate of each corresponding characteristic point of picture described in the long track of characteristic point after obtaining smoothly;
Using coordinate of many plane optimizing methods to each corresponding characteristic point of picture described in the long track of each characteristic point,
And it is smooth after the long track of characteristic point described in the coordinate of each corresponding characteristic point of picture calculated, obtain the picture
Corresponding global change's matrix.
Further, use global change matrix becomes to the coordinate of corresponding characteristic point in the short track of characteristic point
Change and smoothing processing, the short track of characteristic point after obtaining smoothly, including:
The coordinate of corresponding characteristic point in the short track of characteristic point is carried out using each frame picture corresponding global change's matrix
Conversion, obtains the coordinate after each feature point transformation in the short track of characteristic point;
Coordinate after each feature point transformation in the short track of characteristic point is combined, the short rail of characteristic point of precondition is obtained
Mark;
B-spline curves fitting is carried out to the short track of characteristic point of the precondition, the short track of characteristic point after obtaining smoothly.
Further, the B-spline curves fitting function is
Wherein PiFor control point, Ni,p(u) it is p B-spline basic function.
Further, B-spline basic function is
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.
In the present invention, by extracting video to be stablized per the characteristic point in frame picture, connection obtains the rail of each characteristic point
Mark and path length, and binding characteristic locus of points length threshold classified, and obtains the long track of characteristic point and the short rail of characteristic point
Mark, the long track of distinguished point based and low-pass filtered processing obtain it is smooth after the long track of characteristic point, calculating obtain every frame figure
The corresponding global change's matrix of piece, with reference to the corresponding global change's matrix of every frame picture, the short track of characteristic point and smoothing processing
Means, the short track after obtaining smoothly, using many plane optimizing methods to each feature point trajectory and characteristic point smooth track
Calculated, obtain the corresponding object transformation matrix of every frame picture, stable video is treated successively per each pixel in frame picture
Coordinate transform, the UAV Video stablized, track of the present invention to characteristic point are carried out using corresponding object transformation matrix
Classification, the calculating of global change's matrix corresponding to every frame picture so that different transformation rules can be used per frame picture
Its motion is described, the motion of different zones can be accurately described, the present invention combines the use of many plane optimizing methods, Neng Gouyi
Determine degree and solve unmanned plane low-latitude flying scene roller shutter effect, and influence of the CMOS camera dither scenes to video, from
And the stablizing effect of UAV Video is improved, improve the availability of UAV Video.
The second aspect of the invention is to provide a kind of UAV Video stabilising arrangement of low-latitude flying scene, including:
Extraction module, for extracting video to be stablized per the characteristic point in frame picture, connection obtains the rail of each characteristic point
Mark and path length;
Comparison module, for the path length of characteristic point to be compared with feature point trajectory length threshold, is obtained respectively
The long track of characteristic point and the short track of characteristic point;
Filtering process module, is smoothed using LPF for the coordinate value to the long track of characteristic point, obtained
The long track of characteristic point after smooth;
First computing module, for the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizings
Calculate, obtain the corresponding global change's matrix of every frame picture;
Conversion module, for being become using global change's matrix to the coordinate of corresponding characteristic point in the short track of characteristic point
Change and smoothing processing, the short track of characteristic point after obtaining smoothly;
Second computing module, for it is described it is smooth after the long track of characteristic point with it is smooth after the short track of characteristic point carry out
Merging obtains characteristic point smooth track, and each feature point trajectory and characteristic point smooth track are carried out using many plane optimizing methods
Calculate, obtain the corresponding object transformation matrix of every frame picture;
Displacement compensation module, is become for treating stable video successively per each pixel in frame picture using corresponding target
Change matrix and carry out coordinate transform, the UAV Video stablized.
Further, first computing module includes:
First acquisition unit, it is corresponding each for for every frame picture, obtaining picture described in the long track of each characteristic point
The coordinate of individual characteristic point;
Second acquisition unit, for obtain it is smooth after the long track of characteristic point described in each corresponding characteristic point of picture
Coordinate;
Computing unit, using many plane optimizing methods to each corresponding feature of picture described in the long track of each characteristic point
The coordinate of point, and it is smooth after the long track of characteristic point described in the coordinate of each corresponding characteristic point of picture calculated, obtain
To the corresponding global change's matrix of the picture.
Further, the conversion module includes:
Converter unit, for using the corresponding global change's matrix of each frame picture to corresponding feature in the short track of characteristic point
The coordinate of point enters line translation, obtains the coordinate after each feature point transformation in the short track of characteristic point;
Assembled unit, for being combined to the coordinate after each feature point transformation in the short track of characteristic point, obtains pre- steady
The short track of fixed characteristic point;
Curve matching unit, carries out B-spline curves fitting for the short track of characteristic point to the precondition, obtains smooth
The short track of characteristic point afterwards.
Further, the B-spline curves fitting function is
Wherein PiFor control point, Ni,p(u) it is p B-spline basic function.
Further, B-spline basic function is
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.
In the present invention, by extracting video to be stablized per the characteristic point in frame picture, connection obtains the rail of each characteristic point
Mark, and binding characteristic locus of points length threshold classified, and obtains the long track of characteristic point and the short track of characteristic point, distinguished point based
Long track and low-pass filtered processing obtain it is smooth after the long track of characteristic point, calculating obtains that every frame picture is corresponding global to be become
Matrix is changed, with reference to the corresponding global change's matrix of every frame picture, the short track of characteristic point and smoothing processing means, after obtaining smoothly
Short track, each feature point trajectory and characteristic point smooth track are calculated using many plane optimizing methods, obtain every
The corresponding object transformation matrix of frame picture, is treated stable video and is become per each pixel in frame picture using corresponding target successively
Change matrix and carry out coordinate transform, the UAV Video stablized, classification of the present invention to the track of characteristic point, to every frame picture
The calculating of corresponding global change's matrix so that its motion, Neng Goujing can be described using different transformation rules per frame picture
The motion of different zones really is described, the present invention combines the use of many plane optimizing methods, unmanned plane can be solved to a certain degree
Low-latitude flying scene roller shutter effect, and influence of the CMOS camera dither scenes to video, so as to improve UAV Video
Stablizing effect, improve UAV Video availability.
Brief description of the drawings
The flow chart of the UAV Video antihunt means one embodiment for the low-latitude flying scene that Fig. 1 provides for the present invention;
The flow for the UAV Video antihunt means of low-latitude flying scene another embodiment that Fig. 2 provides for the present invention
Figure;
The flow for the UAV Video antihunt means of low-latitude flying scene another embodiment that Fig. 3 provides for the present invention
Figure;
The structural representation of the UAV Video stabilising arrangement one embodiment for the low-latitude flying scene that Fig. 4 provides for the present invention
Figure;
The structure for the UAV Video stabilising arrangement of low-latitude flying scene another embodiment that Fig. 5 provides for the present invention is shown
It is intended to;
The structure for the UAV Video stabilising arrangement of low-latitude flying scene another embodiment that Fig. 6 provides for the present invention is shown
It is intended to.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
The flow chart of the UAV Video antihunt means one embodiment for the low-latitude flying scene that Fig. 1 provides for the present invention,
As shown in figure 1, including:
101st, video to be stablized is extracted per the characteristic point in frame picture, and connection obtains the track and track of each characteristic point
Length.
Specifically, angle point tracking can be used, using interframe gray scale difference quadratic sum as measurement, is obtained in video to be stablized
Characteristic point and its coordinate information, and the same characteristic features point in each frame picture is associated, obtains the track of each characteristic point
And path length.
102nd, the path length of characteristic point and feature point trajectory length threshold are compared, the long rail of characteristic point is obtained respectively
Mark and the short track of characteristic point.
Specifically, by after the trajectory map of characteristic point to X-Y coordinate, path length can be more than feature point trajectory long
The feature point trajectory of degree threshold tau is defined as the long track T of characteristic pointL, path length is less than to feature point trajectory length threshold τ spy
Levy the locus of points and be defined as the short track T of characteristic pointS。
103rd, the coordinate value of the long track of characteristic point is smoothed using LPF, the characteristic point after obtaining smoothly
Long track.
Specifically, can be using one-dimensional Gaussian filter or track wave filter etc. to characteristic point in the long track of characteristic point
Abscissa track and ordinate track carry out one-dimensional LPF respectively, by the position for estimating characteristic point abscissa smooth track
And the position of ordinate smooth track, the long track of characteristic point stablized, the stable long track of characteristic point is defined as putting down
The long track T of characteristic point after cunningL'。
104th, to the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizing calculating, obtain every frame
The corresponding global change's matrix of picture.
Wherein, the UAV Video stabilising arrangement of low-latitude flying scene can use many plane optimizing methods will be per frame picture
Be divided into multiple planes, and combine the feature point coordinates in each plane and it is corresponding it is smooth after feature point coordinates calculate every
The transformation matrix of one plane, the transformation relation between picture to be stablized and Target Photo is defined as by transformation matrix set.
105th, line translation is entered to the coordinate of corresponding characteristic point in the short track of characteristic point and flat using global change's matrix
Sliding processing, the short track of characteristic point after obtaining smoothly.
Specifically, the UAV Video stabilising arrangement of low-latitude flying scene can use the corresponding global change of each frame picture
The coordinate for the characteristic point that matrix is included to each frame picture in the short track of characteristic point enters line translation, and the characteristic point for obtaining precondition is short
Track, is the short track of characteristic point after smooth by the short track fitting of the characteristic point of precondition then using the method for curve matching
TS'。
106th, to the long track of characteristic point after smooth with it is smooth after the short track of characteristic point merge and obtain characteristic point and put down
Slide rail mark, is calculated the track of each characteristic point and characteristic point smooth track using many plane optimizing methods, obtains every frame
The corresponding object transformation matrix of picture.
Specifically, the UAV Video stabilising arrangement of low-latitude flying scene obtains the long track T of characteristic pointL, it is smooth after spy
Levy a little long track TL', the short track T of characteristic pointS, it is smooth after the short track T of characteristic pointS' afterwards, can be by the long track T of characteristic pointL
With the short track T of characteristic pointSIt is combined as the track T of characteristic pointC, will it is smooth after the long track T of characteristic pointL' and it is smooth after characteristic point
Short track TS' be combined as it is smooth after feature point trajectory TC', obtain the corresponding target of every frame picture using many plane optimizing methods
Transformation matrix M'={ H1',H2'...Hk-1',Hk', wherein Hk' be each plane transformation matrix.
107th, stable video is treated successively to be sat using corresponding object transformation matrix per each pixel in frame picture
Mark conversion, the UAV Video stablized.
Wherein, if the coordinate of all pixels point is matrix in per frame picture
The coordinate of all pixels point is P'=M'P after then converting, and each pixel is mapped to new coordinate by coordinate P'
System, obtains the picture after frame stabilization.Above-mentioned conversion will be carried out successively by each frame picture in video to be stablized, you can after being stablized
Sequence of pictures;Sequence of pictures after stabilization is spliced by sequence number, you can obtain stablizing video.
In the present embodiment, by extracting video to be stablized per the characteristic point in frame picture, connection obtains each characteristic point
Track and path length, and binding characteristic locus of points length threshold classified, and obtains the long track of characteristic point and characteristic point is short
The long track of characteristic point after track, the filtering that the long track of distinguished point based and low-pass filtered processing are obtained, calculating is obtained
Per the corresponding global change's matrix of frame picture, with reference to the corresponding global change's matrix of every frame picture, the short track of characteristic point and song
Line fitting means, obtain it is smooth after short track, using many plane optimizing methods to the track of each characteristic point and it is smooth after
Feature point trajectory calculated, obtain the corresponding object transformation matrix of every frame picture, become using the corresponding target of every frame picture
The coordinate progress conversion process that matrix treats each pixel in the corresponding picture of stable video is changed, obtains stablizing video, the present invention
Classification to the track of characteristic point, the calculating of global change's matrix corresponding to every frame picture so that can be used per frame picture
Different transformation rules describes its motion, can accurately describe its motion, and the present invention combines the use of many plane optimizing methods,
Unmanned plane low-latitude flying scene roller shutter effect can be solved to a certain degree, and CMOS camera dither scenes are to the shadow of video
Ring, so as to improve the stablizing effect of low-latitude flying scene UAV Video, improve the availability of UAV Video.
The flow chart for UAV Video antihunt means another embodiment that Fig. 2 provides for the present invention, as shown in Fig. 2
On the basis of embodiment illustrated in fig. 1, step 104 can specifically include:
1041st, for every frame picture, the coordinate of each corresponding characteristic point of picture in the long track of each characteristic point is obtained.
1042nd, the coordinate of each corresponding characteristic point of picture described in the long track of characteristic point after obtaining smoothly.
1043rd, using many plane optimizing methods to each corresponding characteristic point of picture described in the long track of each characteristic point
Coordinate, and it is smooth after the long track of characteristic point described in the coordinate of each corresponding characteristic point of picture calculated, obtain institute
State the corresponding global change's matrix of picture.
Specifically, the UAV Video stabilising arrangement of low-latitude flying scene specifically can be first by all spies in every frame picture
Levy point Pk,i, with each four angle point V of gridkLinear interpolation represent that the linear interpolation coefficient of four angle points is expressed as
ωk, wherein k is grid sequence number, and i is characteristic point sequence number in the grid, is passed throughCan be by four angle points and characteristic point
PkTry to achieve linear interpolation coefficientNowAnd PkFor, it is known that optimization after four angle point Vk" it is unknown.Energy term can be with table
It is shown as:
Wherein k is grid sequence number, and i is the grid characteristic point sequence number, Vk" for the angular coordinate after stable in k-th grid.
Make this energy term minimum, all interpolation feature points V minimum with smooth features point Euclidean distance sum can be obtainedk" result.
In addition, each grid can be divided into two triangles, each triangle again can be with similitude come table
Up to its deformation.If weBe set to right angled triangle right angle electrical and two summits, then haveWhereinThe ratio between right-angle side length of side is represented, R represents rotating vector.Now all triangles are combined and counted
Calculate, energy term can be obtained:
WhereinFor three angle points after stabilization in k-th of grid, s is all triangles after segmentation
Shape, two energy term optimizations of joint:
E=Ed+γEt,
Wherein γ is the weight of energy term.By minimizing energy type, then it can show that four angle points of each grid are sat
Mark Vk'。
Now according to the original angular coordinate V of each gridkWith stablize angular coordinate Vk', according to identity transformation matrix rule
P'=HP, can calculate the transformation matrix set M={ H of each grid of correspondence1,H2...Hk-1,Hk, the set is global change
Change matrix.
The flow for the UAV Video antihunt means of low-latitude flying scene another embodiment that Fig. 3 provides for the present invention
Figure, as shown in figure 3, on the basis of embodiment illustrated in fig. 1, due to there was only TLAnd TL' global change's matrix computations are participated in, this is complete
Office's transformation matrix is still undesirable for processing image periphery and the sparse position of characteristic point, can be carried out using the short track of characteristic point
Supplement.Therefore, step 105 can specifically include:
1051st, using coordinate of the corresponding global change's matrix of each frame picture to corresponding characteristic point in the short track of characteristic point
Enter line translation, obtain the coordinate after each feature point transformation in the short track of characteristic point.
Specifically, obtain after the corresponding global change's matrix of each frame picture, can be by the short track T of characteristic pointSIn each frame picture
Including the coordinate of characteristic point substitute into the corresponding global change's matrix of each frame picture.Feature point coordinates is represented with P, then can obtain spy
Levy coordinate P "=M*P after each characteristic point is stable in a little short track.
1052nd, the coordinate after each feature point transformation in the short track of characteristic point is combined, obtains the feature of precondition
The short track of point.
Wherein, the coordinate P " after the same characteristic features point stabilization in each frame picture is connected as feature point trajectory with the time, then
The short track of characteristic point of precondition can be obtained, T is expressed asS”。
1053rd, B-spline curves fitting is carried out to the short track of characteristic point of precondition, the short rail of characteristic point after obtaining smoothly
Mark.
Wherein, to the short track T of characteristic point of each preconditionS" carry out B-spline curves fitting, B-spline curves fitting function
ForWherein PiFor control point, Ni,p(u) it is p B-spline basic function.
Wherein, B-spline basic function is
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.To the B-spline curves after smooth in integer
Frame is sampled, and the point obtained in each frame is linked as smooth track, the as smooth short track T of characteristic pointS'。
In the present embodiment, by extracting video to be stablized per the characteristic point in frame picture, connection obtains each characteristic point
Track, and binding characteristic locus of points length threshold classified, and the long track of characteristic point and the short track of characteristic point is obtained, for every frame
Picture, obtains the coordinate of each corresponding characteristic point of picture in the long track of each characteristic point, the long rail of characteristic point after obtaining smoothly
The coordinate of each corresponding characteristic point of picture described in mark, using many plane optimizing methods to described in the long track of each characteristic point
The coordinate of each corresponding characteristic point of picture, and it is smooth after the long track of characteristic point described in each corresponding characteristic point of picture
Coordinate calculated, the corresponding global change's matrix of the picture is obtained, using the corresponding global change's matrix of each frame picture
Line translation is entered to the coordinate of corresponding characteristic point in the short track of characteristic point, obtained in the short track of characteristic point after each feature point transformation
Coordinate, the coordinate after each feature point transformation in the short track of characteristic point is combined, the short rail of characteristic point of precondition is obtained
Mark, B-spline curves fitting is carried out to the short track of characteristic point of precondition, the short track of characteristic point after obtaining smoothly, using more flat
Face optimization method is calculated each feature point trajectory and characteristic point smooth track, is obtained the corresponding target of every frame picture and is become
Matrix is changed, stable video is treated successively coordinate change is carried out using corresponding object transformation matrix per each pixel in frame picture
Change, the UAV Video stablized, classification of the present invention to the track of characteristic point, global change's square corresponding to every frame picture
The calculating of battle array so that its motion can be described using different transformation rules per frame picture, different zones can be accurately described
Motion, the present invention combine many plane optimizing methods use, unmanned plane low-latitude flying scene roller shutter can be solved to a certain degree
Effect, and influence of the CMOS camera dither scenes to video, so as to improve the stablizing effect of UAV Video, improve nothing
The availability of man-machine video.
One of ordinary skill in the art will appreciate that:Realizing all or part of step of above-mentioned each method embodiment can lead to
The related hardware of programmed instruction is crossed to complete.Foregoing program can be stored in a computer read/write memory medium.The journey
Sequence upon execution, performs the step of including above-mentioned each method embodiment;And foregoing storage medium includes:ROM, RAM, magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
The structural representation of the UAV Video stabilising arrangement one embodiment for the low-latitude flying scene that Fig. 4 provides for the present invention
Figure, as shown in figure 4, including:
Extraction module 41, for extracting video to be stablized per the characteristic point in frame picture, connection obtains each characteristic point
Track and path length;
Comparison module 42, for the path length of characteristic point to be compared with feature point trajectory length threshold, is obtained respectively
Take the long track of characteristic point and the short track of characteristic point;
Filtering process module 43, is smoothed using LPF for the coordinate value to the long track of characteristic point, obtained
To the long track of characteristic point after smooth;
First computing module 44, for the long track of characteristic point and it is smooth after to carry out many planes excellent the long track of characteristic point
Change and calculate, obtain the corresponding global change's matrix of every frame picture;
Conversion module 45, for being carried out using global change's matrix to the coordinate of corresponding characteristic point in the short track of characteristic point
Conversion and smoothing processing, the short track of characteristic point after obtaining smoothly;
Second computing module 46, for the long track of characteristic point after smooth with smoothly after the short track of characteristic point close
And characteristic point smooth track is obtained, each feature point trajectory and characteristic point smooth track are counted using many plane optimizing methods
Calculate, obtain the corresponding object transformation matrix of every frame picture;
Displacement compensation module 47, for treating stable video successively per each pixel in frame picture using corresponding target
Transformation matrix carries out coordinate transform, the UAV Video stablized.
The UAV Video stabilising arrangement for the low-latitude flying scene that the present invention is provided can be regarding on unmanned plane
Frequency stabilizer either video stabilization software or can be video stabilization software on background server.
Specifically, extraction module 41 can use angle point tracking, using interframe gray scale difference quadratic sum as measurement, be treated
Characteristic point and its coordinate information in stable video, and the same characteristic features point in each frame picture is associated, obtain each special
Levy track a little.
Path length can be more than characteristic point rail by comparison module 42 by after the trajectory map of characteristic point to X-Y coordinate
Mark length threshold τ feature point trajectory is defined as the long track T of characteristic pointL, path length is less than feature point trajectory length threshold τ
Feature point trajectory be defined as the short track T of characteristic pointS。
Filtering process module 43 specifically can be long to characteristic point using one-dimensional Gaussian filter or long track wave filter etc.
The abscissa track and ordinate track of characteristic point carry out one-dimensional LPF respectively in track, by estimating characteristic point abscissa
The position of smooth track and the position of ordinate smooth track, the long track of characteristic point stablized, by stable characteristic point
Long track be defined as it is smooth after the long track T of characteristic pointL'。
Second computing module 46 can specifically obtain the long track T of characteristic pointL, it is smooth after the long track T of characteristic pointL', feature
The short track T of pointS, it is smooth after the short track T of characteristic pointS' afterwards, can be by the long track T of characteristic pointLWith the short track T of characteristic pointSGroup
It is combined into the track T of characteristic pointC, will it is smooth after the long track T of characteristic pointL' and it is smooth after the short track T of characteristic pointS' be combined as putting down
Feature point trajectory T after cunningC', obtain the corresponding object transformation matrix M'={ H of every frame picture using many plane optimizing methods1',
H2'...Hk-1',Hk'}。
Need to illustrate, the coordinate of all pixels point in every frame picture can be set as matrix
The coordinate of all pixels point is P'=M'P after then converting, and each pixel is mapped to new coordinate by coordinate P'
System, obtains the picture after frame stabilization.Above-mentioned conversion will be carried out successively by each frame picture in video to be stablized, you can after being stablized
Sequence of pictures;Sequence of pictures after stabilization is spliced by sequence number, you can obtain stablizing video.
In the present embodiment, by extracting video to be stablized per the characteristic point in frame picture, connection obtains each characteristic point
Track and path length, and binding characteristic locus of points length threshold classified, and obtains the long track of characteristic point and characteristic point is short
The long track of characteristic point after track, the filtering that the long track of distinguished point based and low-pass filtered processing are obtained, calculating is obtained
Per the corresponding global change's matrix of frame picture, with reference to the corresponding global change's matrix of every frame picture, the short track of characteristic point and song
Line fitting means, obtain it is smooth after short track, using many plane optimizing methods to the track of each characteristic point and it is smooth after
Feature point trajectory calculated, obtain the corresponding object transformation matrix of every frame picture, become using the corresponding target of every frame picture
The coordinate progress conversion process that matrix treats each pixel in the corresponding picture of stable video is changed, obtains stablizing video, the present invention
Classification to the track of characteristic point, the calculating of global change's matrix corresponding to every frame picture so that can be used per frame picture
Different transformation rules describes its motion, can accurately describe its motion, and the present invention combines the use of many plane optimizing methods,
Unmanned plane low-latitude flying scene roller shutter effect can be solved to a certain degree, and CMOS camera dither scenes are to the shadow of video
Ring, so as to improve the stablizing effect of the UAV Video of low-latitude flying scene, improve the availability of UAV Video.
Further, on the basis of embodiment illustrated in fig. 4, with reference to referring to Fig. 5, first computing module 44 can be with
Including:
First acquisition unit 441, it is corresponding for for every frame picture, obtaining picture described in the long track of each characteristic point
The coordinate of each characteristic point;
Second acquisition unit 442, for obtain it is smooth after the long track of characteristic point described in each corresponding feature of picture
The coordinate of point;
Computing unit 443, for corresponding to picture described in the long track of each characteristic point using many plane optimizing methods
The coordinate of each characteristic point, and it is smooth after the long track of characteristic point described in the coordinate of each corresponding characteristic point of picture carry out
Calculate, obtain the corresponding global change's matrix of the picture.
Specifically, the UAV Video stabilising arrangement of low-latitude flying scene specifically can be first by all spies in every frame picture
Levy point Pk,i, with each four angle point V of gridkLinear interpolation represent that the linear interpolation coefficient of four angle points is expressed as
ωk, wherein k is grid sequence number, and i is characteristic point sequence number in the grid, is passed throughCan be by four angle points and characteristic point
PkTry to achieve linear interpolation coefficientNowAnd PkFor, it is known that optimization after four angle point Vk" it is unknown.Energy term can be with table
It is shown as:
Wherein k is grid sequence number, and i is the grid characteristic point sequence number, Vk" for the angular coordinate after stable in k-th grid.
Make this energy term minimum, all interpolation feature points V minimum with smooth features point Euclidean distance sum can be obtainedk" result.
In addition, each grid can be divided into two triangles, each triangle again can be with similitude come table
Up to its deformation.If weBe set to right angled triangle right angle electrical and two summits, then haveWhereinThe ratio between right-angle side length of side is represented, R represents rotating vector.Now all triangles are combined and counted
Calculate, energy term can be obtained:
Wherein s is all triangles after segmentation, two energy term optimizations of joint:
E=Ed+γEt,
Wherein γ is the weight of two energy terms.By minimizing energy type, then four angle points of each grid can be drawn
Coordinate Vk'。
Now according to the original angular coordinate V of each gridkWith stablize angular coordinate Vk', according to identity transformation matrix rule
P'=HP, can calculate the transformation matrix set M={ H of each grid of correspondence1,H2...Hk-1,Hk, the set is global change
Change matrix.
Further, on the basis of embodiment illustrated in fig. 4, with reference to Fig. 6 is referred to, the conversion module 45 can also be wrapped
Include:
Converter unit 451, for using the corresponding global change's matrix of each frame picture to corresponding in the short track of characteristic point
The coordinate of characteristic point enters line translation, obtains the coordinate after each feature point transformation in the short track of characteristic point;
Assembled unit 452, for being combined to the coordinate after each feature point transformation in the short track of characteristic point, obtains pre-
The stable short track of characteristic point;
Curve matching unit 453, carries out B-spline curves fitting for the short track of characteristic point to the precondition, obtains
The short track of characteristic point after smooth.
Wherein, obtain after the corresponding global change's matrix of each frame picture, converter unit 451 can be by the short track T of characteristic pointSIn
The coordinate for the characteristic point that each frame picture includes substitutes into the corresponding global change's matrix of each frame picture.Feature point coordinates is represented with P, then
It can obtain coordinate P "=M*P after each characteristic point is stable in the short track of characteristic point.Assembled unit 452 is by the phase in each frame picture
Feature point trajectory is connected as with the time with coordinate P " of the characteristic point after stable, then can obtain the short track of characteristic point of precondition,
It is expressed as TS”。
Wherein, to the short track T of characteristic point of each preconditionS" carry out B-spline curves fitting, B-spline curves fitting function
MeetWherein PiFor control point, Ni,p(u) it is p B-spline basic function.
Wherein, B-spline basic function is
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.To the B-spline curves after smooth in integer
Frame is sampled, and the point obtained in each frame is linked as smooth track, the as smooth short track T of characteristic pointS'。
In the present embodiment, by extracting video to be stablized per the characteristic point in frame picture, connection obtains each characteristic point
Track, and binding characteristic locus of points length threshold classified, and the long track of characteristic point and the short track of characteristic point is obtained, for every frame
Picture, obtains the coordinate of each corresponding characteristic point of picture in the long track of each characteristic point, the long rail of characteristic point after obtaining smoothly
The coordinate of each corresponding characteristic point of picture described in mark, using many plane optimizing methods to described in the long track of each characteristic point
The coordinate of each corresponding characteristic point of picture, and it is smooth after the long track of characteristic point described in each corresponding characteristic point of picture
Coordinate calculated, the corresponding global change's matrix of the picture is obtained, using the corresponding global change's matrix of each frame picture
Line translation is entered to the coordinate of corresponding characteristic point in the short track of characteristic point, obtained in the short track of characteristic point after each feature point transformation
Coordinate, the coordinate after each feature point transformation in the short track of characteristic point is combined, the short rail of characteristic point of precondition is obtained
Mark, B-spline curves fitting is carried out to the short track of characteristic point of precondition, the short track of characteristic point after obtaining smoothly, using more flat
Face optimization method is calculated each feature point trajectory and characteristic point smooth track, is obtained the corresponding target of every frame picture and is become
Matrix is changed, stable video is treated successively coordinate change is carried out using corresponding object transformation matrix per each pixel in frame picture
Change, the UAV Video stablized, classification of the present invention to the track of characteristic point, global change's square corresponding to every frame picture
The calculating of battle array so that its motion can be described using different transformation rules per frame picture, different zones can be accurately described
Motion, the present invention combine many plane optimizing methods use, unmanned plane low-latitude flying scene roller shutter can be solved to a certain degree
Effect, and influence of the CMOS camera dither scenes to video, so as to improve the stablizing effect of UAV Video, improve nothing
The availability of man-machine video.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations;To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that:Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent substitution;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme.
Claims (10)
1. a kind of UAV Video antihunt means of low-latitude flying scene, it is characterised in that including:
Video to be stablized is extracted per the characteristic point in frame picture, connection obtains track and the path length of each characteristic point;
The path length of characteristic point is compared with feature point trajectory length threshold, the long track of characteristic point and feature are obtained respectively
The short track of point;
The coordinate value of the long track of characteristic point is smoothed using LPF, the long track of characteristic point after obtaining smoothly;
To the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizing calculating, obtain every frame picture correspondence
Global change's matrix;
Line translation and smoothing processing are entered to the coordinate of corresponding characteristic point in the short track of characteristic point using global change's matrix, obtained
To the short track of characteristic point after smooth;
To it is described it is smooth after the long track of characteristic point with it is smooth after the short track of characteristic point merge and obtain the smooth rail of characteristic point
Mark, is calculated each feature point trajectory and characteristic point smooth track using many plane optimizing methods, obtains every frame picture pair
The object transformation matrix answered;
Stable video is treated successively coordinate transform is carried out using corresponding object transformation matrix per each pixel in frame picture, obtain
To stable UAV Video.
2. the UAV Video antihunt means of low-latitude flying scene according to claim 1, it is characterised in that described to spy
The long track of characteristic point after levying a little long track and being smooth carries out many plane optimizing calculating, obtains the corresponding global change of every frame picture
Matrix is changed, including:
For every frame picture, the coordinate of each corresponding characteristic point of picture described in the long track of each characteristic point is obtained;
The coordinate of each corresponding characteristic point of picture described in the long track of characteristic point after obtaining smoothly;
Using coordinate of many plane optimizing methods to each corresponding characteristic point of picture described in the long track of each characteristic point, and
The coordinate of each corresponding characteristic point of picture is calculated described in the long track of characteristic point after smooth, obtains the picture correspondence
Global change's matrix.
3. the UAV Video antihunt means of low-latitude flying scene according to claim 1, it is characterised in that the use
Global change's matrix enters line translation and smoothing processing to the coordinate of corresponding characteristic point in the short track of characteristic point, after obtaining smoothly
The short track of characteristic point, including:
Line translation is entered to the coordinate of corresponding characteristic point in the short track of characteristic point using the corresponding global change's matrix of each frame picture,
Obtain the coordinate after each feature point transformation in the short track of characteristic point;
Coordinate after each feature point transformation in the short track of characteristic point is combined, the short track of characteristic point of precondition is obtained;
B-spline curves fitting is carried out to the short track of characteristic point of the precondition, the short track of characteristic point after obtaining smoothly.
4. the UAV Video antihunt means of low-latitude flying scene according to claim 3, it is characterised in that the B samples
Bar iunction for curve is
Wherein PiFor control point, Ni,p(u) it is p B-spline basic function.
5. the UAV Video antihunt means of the low-latitude flying scene described in the claim 3 of track, it is characterised in that B-spline base
Function is
<mrow>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mn>0</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
<mo>&le;</mo>
<mi>u</mi>
<mo><</mo>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mrow>
<mi>e</mi>
<mi>l</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
1
<mrow>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>p</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>u</mi>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>p</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
</mrow>
</mfrac>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mfrac>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<mi>u</mi>
</mrow>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mfrac>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
<mo>,</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.
6. a kind of UAV Video stabilising arrangement of low-latitude flying scene, it is characterised in that including:
Extraction module, for extracting video to be stablized per frame picture in characteristic point, connection obtain the track of each characteristic point with
And path length;
Comparison module, for the path length of characteristic point to be compared with feature point trajectory length threshold, obtains feature respectively
The long track of point and the short track of characteristic point;
Filtering process module, is smoothed for the coordinate value to the long track of characteristic point using LPF, obtains smooth
The long track of characteristic point afterwards;
First computing module, by the long track of characteristic point and it is smooth after the long track of characteristic point carry out many plane optimizings based on
Calculate, obtain the corresponding global change's matrix of every frame picture;
Conversion module, for use global change's matrix the coordinate of corresponding characteristic point in the short track of characteristic point is entered line translation with
And smoothing processing, the short track of characteristic point after obtaining smoothly;
Second computing module, for it is described it is smooth after the long track of characteristic point with smoothly after the short track of characteristic point merge
Characteristic point smooth track is obtained, each feature point trajectory and characteristic point smooth track are counted using many plane optimizing methods
Calculate, obtain the corresponding object transformation matrix of every frame picture;
Displacement compensation module, for treating stable video successively per each pixel in frame picture using corresponding object transformation square
Battle array carries out coordinate transform, the UAV Video stablized.
7. the UAV Video stabilising arrangement of low-latitude flying scene according to claim 6, it is characterised in that described first
Computing module includes:
First acquisition unit, for for every frame picture, obtaining each corresponding spy of picture described in the long track of each characteristic point
Levy coordinate a little;
Second acquisition unit, for obtain it is smooth after the long track of characteristic point described in each corresponding characteristic point of picture seat
Mark;
Computing unit, using many plane optimizing methods to each corresponding characteristic point of picture described in the long track of each characteristic point
Coordinate, and it is smooth after the long track of characteristic point described in the coordinate of each corresponding characteristic point of picture calculated, obtain institute
State the corresponding global change's matrix of picture.
8. the UAV Video stabilising arrangement of low-latitude flying scene according to claim 6, it is characterised in that the conversion
Module includes:
Converter unit, for using the corresponding global change's matrix of each frame picture to corresponding characteristic point in the short track of characteristic point
Coordinate enters line translation, obtains the coordinate after each feature point transformation in the short track of characteristic point;
Assembled unit, for being combined to the coordinate after each feature point transformation in the short track of characteristic point, obtains precondition
The short track of characteristic point;
Curve matching unit, carries out B-spline curves fitting, after obtaining smoothly for the short track of characteristic point to the precondition
The short track of characteristic point.
9. the UAV Video stabilising arrangement of low-latitude flying scene according to claim 8, it is characterised in that the B samples
Bar iunction for curve is
Wherein PiFor control point, Ni,p(u) it is p B-spline basic function.
10. the UAV Video stabilising arrangement of low-latitude flying scene according to claim 8, it is characterised in that B-spline base
Function is
<mrow>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mn>0</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
<mo>&le;</mo>
<mi>u</mi>
<mo><</mo>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mrow>
<mi>e</mi>
<mi>l</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mrow>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>p</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>u</mi>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>p</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
</mrow>
</mfrac>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mfrac>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<mi>u</mi>
</mrow>
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mfrac>
<msub>
<mi>N</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
<mo>,</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
Wherein k is B-spline power, and u is node, and i is the sequence frame number of B-spline.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710198431.7A CN107135331B (en) | 2017-03-29 | 2017-03-29 | The UAV Video antihunt means and device of low-latitude flying scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710198431.7A CN107135331B (en) | 2017-03-29 | 2017-03-29 | The UAV Video antihunt means and device of low-latitude flying scene |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107135331A true CN107135331A (en) | 2017-09-05 |
CN107135331B CN107135331B (en) | 2019-12-03 |
Family
ID=59715994
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710198431.7A Active CN107135331B (en) | 2017-03-29 | 2017-03-29 | The UAV Video antihunt means and device of low-latitude flying scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107135331B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112804444A (en) * | 2020-12-30 | 2021-05-14 | 影石创新科技股份有限公司 | Video processing method and device, computing equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102780846A (en) * | 2012-07-11 | 2012-11-14 | 清华大学 | Electronic image stabilization method based on inertial navigation information |
US20130100303A1 (en) * | 2011-10-24 | 2013-04-25 | National Central University | Video Stabilization System and Method |
CN103093481A (en) * | 2013-01-28 | 2013-05-08 | 中国科学院上海微系统与信息技术研究所 | Moving object detection method under static background based on watershed segmentation |
CN103414853A (en) * | 2013-07-26 | 2013-11-27 | 东华大学 | Device and method for stabilizing video image sequence capable of doing multi-degree of freedom movement in real time |
US20140362240A1 (en) * | 2013-06-07 | 2014-12-11 | Apple Inc. | Robust Image Feature Based Video Stabilization and Smoothing |
KR101638628B1 (en) * | 2015-03-06 | 2016-07-12 | 서울과학기술대학교 산학협력단 | a Image stabilization device of a camera |
CN105761233A (en) * | 2014-12-15 | 2016-07-13 | 南京理工大学 | FPGA-based real-time panoramic image mosaic method |
JP2017021430A (en) * | 2015-07-07 | 2017-01-26 | Kddi株式会社 | Panoramic video data processing device, processing method, and program |
-
2017
- 2017-03-29 CN CN201710198431.7A patent/CN107135331B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130100303A1 (en) * | 2011-10-24 | 2013-04-25 | National Central University | Video Stabilization System and Method |
CN102780846A (en) * | 2012-07-11 | 2012-11-14 | 清华大学 | Electronic image stabilization method based on inertial navigation information |
CN103093481A (en) * | 2013-01-28 | 2013-05-08 | 中国科学院上海微系统与信息技术研究所 | Moving object detection method under static background based on watershed segmentation |
US20140362240A1 (en) * | 2013-06-07 | 2014-12-11 | Apple Inc. | Robust Image Feature Based Video Stabilization and Smoothing |
CN103414853A (en) * | 2013-07-26 | 2013-11-27 | 东华大学 | Device and method for stabilizing video image sequence capable of doing multi-degree of freedom movement in real time |
CN105761233A (en) * | 2014-12-15 | 2016-07-13 | 南京理工大学 | FPGA-based real-time panoramic image mosaic method |
KR101638628B1 (en) * | 2015-03-06 | 2016-07-12 | 서울과학기술대학교 산학협력단 | a Image stabilization device of a camera |
JP2017021430A (en) * | 2015-07-07 | 2017-01-26 | Kddi株式会社 | Panoramic video data processing device, processing method, and program |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112804444A (en) * | 2020-12-30 | 2021-05-14 | 影石创新科技股份有限公司 | Video processing method and device, computing equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107135331B (en) | 2019-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Content-aware unsupervised deep homography estimation | |
CN107862704B (en) | Target tracking method and system and holder camera used by same | |
Zhang et al. | Multi-viewpoint panorama construction with wide-baseline images | |
Li et al. | SPM-BP: Sped-up PatchMatch belief propagation for continuous MRFs | |
Lei et al. | Depth map super-resolution considering view synthesis quality | |
Yu et al. | Robust video stabilization by optimization in cnn weight space | |
Zhou et al. | Plane-based content preserving warps for video stabilization | |
CN101540046B (en) | Panoramagram montage method and device based on image characteristics | |
CN105791705B (en) | Video anti-fluttering method, system and camera terminal suitable for mobile time-lapse photography | |
CN103139568B (en) | Based on the Video Stabilization method of degree of rarefication and fidelity constraint | |
CN110766024B (en) | Deep learning-based visual odometer feature point extraction method and visual odometer | |
CN104982027A (en) | Systems and methods for digital video stabilization via constraint-based rotation smoothing | |
CN106878612B (en) | A kind of video stabilizing method based on the optimization of online total variation | |
CN110580720B (en) | Panorama-based camera pose estimation method | |
Koh et al. | Video stabilization based on feature trajectory augmentation and selection and robust mesh grid warping | |
CN110175011B (en) | Panoramic image seamless splicing method | |
CN111798373A (en) | Rapid unmanned aerial vehicle image stitching method based on local plane hypothesis and six-degree-of-freedom pose optimization | |
CN106851102A (en) | A kind of video image stabilization method based on binding geodesic curve path optimization | |
CN106952247A (en) | A kind of dual camera terminal and its image processing method and system | |
CN111951325A (en) | Pose tracking method, pose tracking device and electronic equipment | |
Liu et al. | Depth-guided sparse structure-from-motion for movies and tv shows | |
CN101945299B (en) | Camera-equipment-array based dynamic scene depth restoring method | |
Huang et al. | Stablenet: semi-online, multi-scale deep video stabilization | |
Zhu et al. | PairCon-SLAM: Distributed, online, and real-time RGBD-SLAM in large scenarios | |
CN107135331B (en) | The UAV Video antihunt means and device of low-latitude flying scene |
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 |