CN106296568A - Determination method, device and the client of a kind of lens type - Google Patents
Determination method, device and the client of a kind of lens type Download PDFInfo
- Publication number
- CN106296568A CN106296568A CN201510300276.6A CN201510300276A CN106296568A CN 106296568 A CN106296568 A CN 106296568A CN 201510300276 A CN201510300276 A CN 201510300276A CN 106296568 A CN106296568 A CN 106296568A
- Authority
- CN
- China
- Prior art keywords
- characteristic point
- pictures
- point
- frame
- transformation relation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000009466 transformation Effects 0.000 claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 15
- 230000008878 coupling Effects 0.000 claims abstract description 13
- 238000010168 coupling process Methods 0.000 claims abstract description 13
- 238000005859 coupling reaction Methods 0.000 claims abstract description 13
- 238000000746 purification Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 4
- 230000013011 mating Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses determination method, device and the client of a kind of lens type.The method includes: two frame pictures before and after adjacent under camera lens are carried out feature point detection respectively, extracts characteristic point;The characteristic point of two frame pictures is mated, purifies described characteristic point;Use the characteristic point after purifying, determine the transformation relation of before and after two frame picture;According to this transformation relation, a later frame image in two frame pictures is carried out image conversion;According to a later frame image after previous frame image and conversion, determine the type of affiliated camera lens.The present invention is by the way of mating adjacent two pictures under same camera lens, determine the type of affiliated camera lens, achieve the automatization of lens type identification, and, the transformation relation of two pictures is determined after characteristic point is purified, according to transformation relation, a later frame image is carried out the mode of image conversion, it is possible to increase the accuracy of the coupling of characteristic point.
Description
Technical field
The present invention relates to Internet technical field, particularly to a kind of determination method of lens type, device and
Client.
Background technology
Along with developing rapidly of network and multimedia technology, emerged substantial amounts of digital video, as news,
Advertisement, monitor video, home videos etc..Emerging in multitude of digital video has caused many new technology, bag
Include video archive, catalogue, index and valid memory access etc., and these are required for non-structured video counts
According to being converted into structurized video data.
Video data can be divided into frame, camera lens, scene, story unit etc. by level, and wherein camera lens is video
The ultimate unit of structure, therefore the detection to video lens becomes the basic work of video frequency searching and browser technology
Make.
Automatically identifying of lens shooting mode in video is belonged to the description category that viewdata is catalogued, camera lens
Style of shooting includes: fixed lens, translate, advance and stretch, camera lens conversion.Traditional way, camera lens
The determination of style of shooting be to be judged by artificial viewing video.But, there is effect in the mode of artificial cognition
Rate is relatively low, identifies the problem that accuracy is poor.And shot segmentation can be substantially reduced video editing system accurately
Storage and the data of system upload burden.
Summary of the invention
In view of the above problems, it is proposed that the present invention is to provide one to overcome the problems referred to above or at least in part
Solve determination method, device and the client of the lens type of the problems referred to above.
The determination method of a kind of lens type that the embodiment of the present invention provides, including:
Two frame pictures before and after adjacent under camera lens are carried out feature point detection respectively, extracts characteristic point;
The characteristic point of described two frame pictures is mated, purifies described characteristic point;
Use the characteristic point after purifying, determine the transformation relation of described two frame pictures front and back;
According to described transformation relation, a later frame image in described two frame pictures is carried out image conversion;
According to a later frame image after previous frame image and conversion, determine the type of affiliated camera lens.
Further, after the step of described extraction characteristic point, also include:
Use RANSAC that the feature point pairs of coupling is screened;
Correspondingly, the characteristic point of described two frame pictures is mated, purifies described characteristic point, specifically include:
Characteristic point after RANSAC screens is mated, purifies described characteristic point.
Further, the characteristic point of described two frame pictures is mated, purifies described characteristic point, including:
Reject matching degree in two two field pictures and be less than the feature point pairs of the threshold value set;And/or
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than setting threshold value
Characteristic point.
The described characteristic point used after purifying, determines the transformation relation of described two frame pictures front and back, specifically includes:
Use the characteristic point after purification processes to calculate, obtain the transformation matrix between picture.
The determination device of a kind of lens type that the embodiment of the present invention provides, including:
Feature point detection module, for carrying out feature spot check respectively by two frame pictures before and after adjacent under camera lens
Survey, extract characteristic point;
Purify module, for the characteristic point of described two frame pictures is mated, purify described characteristic point;
Transformation relation determines module, the characteristic point after using purification, determines described two frame pictures front and back
Transformation relation;
Image transform module, for according to described transformation relation, to a later frame image in described two frame pictures
Carry out image conversion;
Lens type determines module, for according to a later frame image after previous frame image and conversion, determining institute
Belong to the type of camera lens.
Further, described purification module, it is additionally operable to, after feature point detection module extracts characteristic point, make
With RANSAC, the feature point pairs of coupling is screened;
Correspondingly, described purification module, for the characteristic point after RANSAC screens is mated,
Purify described characteristic point.
Further, above-mentioned purification module, it is less than, specifically for rejecting matching degree in two two field pictures, the threshold set
The feature point pairs of value;And/or
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than setting threshold value
Characteristic point.
Further, transformation relation determines module, counts specifically for the characteristic point after using purification processes
Calculate, obtain the transformation matrix between picture.
The embodiment of the present invention additionally provides a kind of video editing client, and described client includes above-mentioned shot cluster
The determination device of type.
The beneficial effect comprise that
In determination method, device and the client of the real above-mentioned lens type provided of the present invention, by phase under camera lens
Before and after neighbour, two frame pictures carry out feature point detection respectively, extract characteristic point;Then the feature to two frame pictures
Point mates, and purifies the characteristic point of two frame pictures before and after this;Use the characteristic point after purifying, before and after determining
The transformation relation of two frame pictures;According to transformation relation, a later frame image in two frame pictures is carried out image
Conversion;According to a later frame image after previous frame image and conversion, determine the type of affiliated camera lens.The present invention
By the way of adjacent two pictures under same camera lens are mated, determine the type of affiliated camera lens,
Achieve the automatization of lens type identification, and, determine the change of two pictures after characteristic point is purified
Change relation, according to transformation relation, a later frame image is carried out the mode of image conversion, it is possible to increase characteristic point
The accuracy of coupling.
Further, in determination method, device and the client of the above-mentioned lens type that the present invention provides, use
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than the spy setting threshold value
Characteristic point is purified by mode a little of levying, and mode is simply effective, further increases the speed of picture match
And accuracy.
Other features and advantages of the present invention will illustrate in the following description, and, partly from explanation
Book becomes apparent, or understands by implementing the present invention.The purpose of the present invention and other advantages can
Realize by structure specifically noted in the description write, claims and accompanying drawing and obtain
?.
Below by drawings and Examples, technical scheme is described in further detail.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit for ability
Territory those of ordinary skill will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and also
It is not considered as limitation of the present invention.And in whole accompanying drawing, it is denoted by the same reference numerals identical
Parts.In the accompanying drawings:
Fig. 1 is the flow chart of the determination method of lens type in the embodiment of the present invention;
The connecting line mating accurate and inaccurate characteristic point in the picture that Fig. 2 provides for the embodiment of the present invention shows
It is intended to;
Fig. 3 is the structural representation of the coalignment of picture in the embodiment of the present invention.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows
The exemplary embodiment of the disclosure, it being understood, however, that may be realized in various forms the disclosure and should be by
Embodiments set forth here is limited.On the contrary, it is provided that these embodiments are able to be best understood from this
Open, and complete for the scope of the present disclosure can be conveyed to those skilled in the art.
First the detailed description of the invention of the determination method of the lens type that the embodiment of the present invention provides is said
Bright.
The determination method of the lens type that the embodiment of the present invention provides, as it is shown in figure 1, include:
S11, two frame pictures before and after adjacent under camera lens are carried out feature point detection respectively, extract characteristic point;
S12, characteristic point to described two frame pictures are mated, and purify described characteristic point;
Characteristic point after S13, use purification, determines the transformation relation of before and after two frame picture;
S14, according to transformation relation, a later frame image in two frame pictures is carried out image conversion;
S15, according to previous frame image with conversion after a later frame image, determine the type of affiliated camera lens.
Separately below above steps is described in detail.
Above-mentioned steps S11-S15 for the adjacent picture of two frames, its image overlapping region can not be the least, one
For as, it is impossible to less than the 15% of picture size, such guarantee has enough Feature Points Matching.Typically
Seriality camera lens need not consider the problem that overlapping region is how many;Only the when of cutaway, it is impossible to according still further to
This method is carried out, because the picture under different camera lens is difficult to match point be detected, in other words, detects
Match point is the most all gross error.
Further, in above-mentioned S11, two frame pictures before and after adjacent under camera lens are carried out feature spot check respectively
Surveying, extract characteristic point, the method being referred to existing feature point detection, for example with simple Harris angle
Point detection etc., or extract or extract scale invariant feature conversion (Scale-invariant according to prior art
Feature transform, SIFT) feature etc..Concrete method no longer describes in detail.
Characteristic point is carried out after Detection and Extraction go out characteristic point, between above-mentioned steps S11 and S12, it is also possible to
Including using consistent (RANdom SAmple Consensus, the RANSAC) algorithm of stochastic sampling to feature
Clicking on the step of row filter, this step can also use method of least square to carry out, and the purpose of this step is to remove
Some noises, obtain effective sample, the most preliminary purification.
Following is a brief introduction of RANSAC algorithm.
RANSAC can be estimated by iterative manner from one group of observation data set comprising " point not in the know "
The parameter of mathematical model.It is a kind of uncertain algorithm it have certain probability to draw one reasonably
Result;Iterations must be improved to improve probability.The input of RANSAC algorithm is one group of observation data,
One parameterized model that can explain or be adapted to observe data, some believable parameters.RANSAC
Target is reached by the one group of random subset being chosen in data.The subset being selected is assumed to be intra-office
Point, and verify by following method:
Having a model to be adapted to the intra-office point assumed, the most all of unknown parameter can be from the intra-office point assumed
Calculate, go to test other data all of with model obtained above, if certain point is applicable to estimate
Model, it is believed that it is also intra-office point.If there being abundant point to be classified as the intra-office point assumed, then
The model estimated is sufficient for rationally.Then, go to reappraise model with the intra-office point of all hypothesis, because it
Only by initial hypothesis intra-office point estimation.
Specifically, the embodiment of the present invention uses RANSAC to screen the feature point pairs of coupling, can
To comprise the steps:
From the feature point pairs of all couplings, one RANSAC sample of random selection, described RANSAC
Sample comprises multiple matching double points;
According to the matching double points in RANSAC sample, calculate transformation matrix;
According to RANSAC sample, described transformation matrix and error metrics function, calculate and meet Current Transform
The consistent collection of matrix;
According to the consistent element number concentrated, it is judged that whether consistent collection is the optimum consistent collection set;
When judged result is for being, calculate current erroneous probability, when error probability is less than the minimal error set
During probability, transformation matrix is exported as final result, otherwise, random selection RANSAC sample again,
Repeat above-mentioned calculating, until error probability is less than the minimum error probability set.
Lift a simply example and illustrate to use the flow process of RANSAC, first random selection from sample set
One RANSAC sample, such as 4 matching double points, then calculate conversion according to these 4 matching double points
Matrix M;Calculate according to sample set, transformation matrix M, and error metrics function and meet current transform matrix
Unanimously collect consensus, and element number is unanimously concentrated in return;Judge according to current consistent concentration element number
The most optimum consistent collection, if then updating current optimum consistent collection;Update current erroneous Probability p simultaneously, if
P then repeats step above more than the minimum error probability allowed and continues iteration, until current erroneous Probability p
Less than minimum error probability.
In performing S12, can be by following manner purification characteristic point after RANSAC screens:
First kind of way is: rejects matching degree in two two field pictures and is less than the feature point pairs of the threshold value set.
That is: the threshold value (presetting) of the matching degree of the characteristic point in reference two frame pictures, by characteristic point
Matching degree screens out further less than the characteristic point setting threshold value.
The second way is: the connecting line between matching double points after editor's purification, rejects connecting line slope big
In the characteristic point setting threshold value.
The third mode is: has both rejected matching degree in two two field pictures and has been less than the feature point pairs of the threshold value set, again
The connecting line between matching double points after editor's purification, rejects connecting line slope more than the feature setting threshold value
Point, and the execution sequence of the two step can exchange front and back.
Inventor finds, between every two pictures, the slope of connecting line between feature point pairs exceedes certain journey
The matching double points of degree is all wrong.Thus, if delete the feature point pairs of mistake according to the slope of connecting line,
Then finally obtain is all the most parallel matching double points, namely the feature point pairs of correct coupling.
For the example of Fig. 2, when picture 1 and picture 2 mate, the connecting line between feature point pairs
Slope less than such as 0.1 time (almost horizontal), then be the feature point pairs of accurate match, as shown in Figure 2
Dotted line connect feature point pairs, otherwise, the slope of the connecting line between feature point pairs higher than this threshold value time,
The feature point pairs that solid line as shown in Figure 2 connects, then be the feature point pairs of erroneous matching.
The method that image is mated by prior art, usually uses and is changed by all match points, obtain
The transformational relation of one adjacent image carries out the mode changed the most again, and the premise of this mode is characteristic point
Choosing is all correct and the coupling of characteristic point is also correct, exists for a balance contradiction in the middle of this
Problem: the accuracy the most excellent (such as sift characteristic point) that characteristic point selects, then extract the speed of characteristic point more
Slowly, if the dimension of characteristic point is the highest, the speed of coupling also can be very slow (even if first passing through the feature of previous step
Point screening).So how select in characteristic point and be balanced in images match speed, being to need to consider.
Based on this, in the S12 step of the embodiment of the present invention, have employed between the matching double points after using editor to purify
Connecting line, reject connecting line slope more than the mode of the characteristic point setting threshold value and/or reject in two two field pictures
Characteristic point, less than the mode of the feature point pairs of the threshold value set, is purified by matching degree, and mode is simply effective,
Further increase speed and the accuracy of picture match.
Correspondingly, above-mentioned S13 uses the characteristic point after purifying, determines the transformation relation of before and after two frame picture,
In the specific implementation, effective close quarters of two frame pictures can be used the spy after characteristic point purification processes
Levy and a little calculate, obtain the transformation matrix between picture and (such as select in opencv
The perspective transformation matrix of FindHomography function output).
Based on same inventive concept, the embodiment of the present invention additionally provide a kind of lens type determination device and
Video editing client, due to principle and the determination method of aforementioned lens type of the solved problem of these devices
Similar, therefore the enforcement of this device and client may refer to the enforcement of preceding method, the most superfluous in place of repetition
State.
Further, in above-mentioned S15, according to a later frame image after previous frame image and conversion, determine institute
Belong to the type of camera lens, specifically, i.e. according to the similar journey of a later frame image after conversion to previous frame image
Degree, determines whether camera lens is fixed, if the translation that there occurs, advance and stretching etc..
The determination device of a kind of lens type that the embodiment of the present invention provides, as it is shown on figure 3, include:
Feature point detection module 301, for carrying out characteristic point respectively by two frame pictures before and after adjacent under camera lens
Detection, extracts characteristic point;
Purify module 302, for the characteristic point of described two frame pictures is mated, purify described characteristic point;
Transformation relation determines module 303, the characteristic point after using purification, determines described two frame figures front and back
The transformation relation of sheet;
Image transform module 304, for according to described transformation relation, to a later frame in described two frame pictures
Image carries out image conversion;
Lens type determines module 305, a later frame image after being used for according to previous frame image and conversion, really
The type of camera lens belonging to fixed.
Further, above-mentioned purification module 302, it is additionally operable to after feature point detection module extracts characteristic point,
Use RANSAC that the feature point pairs of coupling is screened;
Correspondingly, purify module 302, for the characteristic point after RANSAC screens is mated,
Purify described characteristic point.
Further, above-mentioned purification module 302, specifically for purifying module, specifically for rejecting two frame figures
In Xiang, matching degree is less than the feature point pairs of the threshold value set;And/or
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than setting threshold value
Characteristic point.
Further, above-mentioned transformation relation determines module 303, specifically for the feature after use purification processes
Point calculates, and obtains the transformation matrix between picture.
The embodiment of the present invention additionally provides a kind of video editing client, and this video editing client includes this
The determination device of the above-mentioned lens type that bright embodiment provides.
In determination method, device and the client of the real above-mentioned lens type provided of the present invention, by phase under camera lens
Before and after neighbour, two frame pictures carry out feature point detection respectively, extract characteristic point;Then the feature to two frame pictures
Point mates, and purifies the characteristic point of two frame pictures before and after this;Use the characteristic point after purifying, before and after determining
The transformation relation of two frame pictures;According to transformation relation, a later frame image in two frame pictures is carried out image
Conversion;According to a later frame image after previous frame image and conversion, determine the type of affiliated camera lens.The present invention
By the way of adjacent two pictures under same camera lens are mated, determine the type of affiliated camera lens,
Achieve the automatization of lens type identification, and, determine the change of two pictures after characteristic point is purified
Change relation, according to transformation relation, a later frame image is carried out the mode of image conversion, it is possible to increase characteristic point
The accuracy of coupling.
Further, in determination method, device and the client of the above-mentioned lens type that the present invention provides, make
The connecting line between matching double points after purifying with editor, rejects connecting line slope more than the feature setting threshold value
Characteristic point is purified by the mode of point, and mode is simply effective, further increase picture match speed and
Accuracy.
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated, it will be appreciated that described herein
Preferred embodiment is merely to illustrate and explains the present invention, is not intended to limit the present invention.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can use complete hardware embodiment, complete software implementation or knot
The form of the embodiment in terms of conjunction software and hardware.And, the present invention can use and wherein wrap one or more
Computer-usable storage medium containing computer usable program code (include but not limited to disk memory and
Optical memory etc.) form of the upper computer program implemented.
The present invention is with reference to method, equipment (system) and computer program product according to embodiments of the present invention
The flow chart of product and/or block diagram describe.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or flow process in square frame and flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embedding
The processor of formula datatron or other programmable data processing device is to produce a machine so that by calculating
The instruction that the processor of machine or other programmable data processing device performs produces for realizing at flow chart one
The device of the function specified in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and computer or the process of other programmable datas can be guided to set
In the standby computer-readable memory worked in a specific way so that be stored in this computer-readable memory
Instruction produce and include the manufacture of command device, this command device realizes in one flow process or multiple of flow chart
The function specified in flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices
Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one
The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification without deviating from this to the present invention
The spirit and scope of invention.So, if these amendments of the present invention and modification belong to the claims in the present invention
And within the scope of equivalent technologies, then the present invention is also intended to comprise these change and modification.
Claims (9)
1. the determination method of a lens type, it is characterised in that including:
Two frame pictures before and after adjacent under camera lens are carried out feature point detection respectively, extracts characteristic point;
The characteristic point of described two frame pictures is mated, purifies described characteristic point;
Use the characteristic point after purifying, determine the transformation relation of described two frame pictures front and back;
According to described transformation relation, a later frame image in described two frame pictures is carried out image conversion;
According to a later frame image after previous frame image and conversion, determine the type of affiliated camera lens.
2. the method for claim 1, it is characterised in that after the step of described extraction characteristic point,
Also include:
Use RANSAC that the feature point pairs of coupling is screened;
Correspondingly, the characteristic point of described two frame pictures is mated, purifies described characteristic point, specifically include:
Characteristic point after RANSAC screens is mated, purifies described characteristic point.
3. method as claimed in claim 1 or 2, it is characterised in that the feature to described two frame pictures
Point mates, and purifies described characteristic point, including:
Reject matching degree in two two field pictures and be less than the feature point pairs of the threshold value set;And/or
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than setting threshold value
Characteristic point.
4. require the method as described in 1 or 2 such as claim, it is characterised in that after described use purifies
Characteristic point, determines the transformation relation of described two frame pictures front and back, specifically includes:
Use the characteristic point after purification processes to calculate, obtain the transformation matrix between picture.
5. the determination device of a lens type, it is characterised in that including:
Feature point detection module, for carrying out feature spot check respectively by two frame pictures before and after adjacent under camera lens
Survey, extract characteristic point;
Purify module, for the characteristic point of described two frame pictures is mated, purify described characteristic point;
Transformation relation determines module, the characteristic point after using purification, determines described two frame pictures front and back
Transformation relation;
Image transform module, for according to described transformation relation, to a later frame image in described two frame pictures
Carry out image conversion;
Lens type determines module, for according to a later frame image after previous frame image and conversion, determining institute
Belong to the type of camera lens.
6. device as claimed in claim 5, it is characterised in that described purification module, is additionally operable to spy
After levying a detection module extraction characteristic point, use RANSAC that the feature point pairs of coupling is screened;
Correspondingly, described purification module, for the characteristic point after RANSAC screens is mated,
Purify described characteristic point.
7. the device as described in claim 5 or 6, it is characterised in that purify module, specifically for picking
Except in two two field pictures, matching degree is less than the feature point pairs of the threshold value set;And/or
The connecting line between matching double points after editor's purification, rejects described connecting line slope more than setting threshold value
Characteristic point.
8. require the method as described in 5 or 6 such as claim, it is characterised in that transformation relation determines module,
Calculate specifically for the characteristic point after using purification processes, obtain the transformation matrix between picture.
9. a video editing client, it is characterised in that include as described in any one of claim 5-8
The determination device of lens type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510300276.6A CN106296568A (en) | 2015-06-03 | 2015-06-03 | Determination method, device and the client of a kind of lens type |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510300276.6A CN106296568A (en) | 2015-06-03 | 2015-06-03 | Determination method, device and the client of a kind of lens type |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106296568A true CN106296568A (en) | 2017-01-04 |
Family
ID=57656325
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510300276.6A Pending CN106296568A (en) | 2015-06-03 | 2015-06-03 | Determination method, device and the client of a kind of lens type |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106296568A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107588768A (en) * | 2017-08-21 | 2018-01-16 | 中国科学院长春光学精密机械与物理研究所 | Interframe angular speed computational methods based on star chart |
CN111639658A (en) * | 2020-06-03 | 2020-09-08 | 北京维盛泰科科技有限公司 | Method and device for detecting and eliminating dynamic characteristic points in image matching |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110122A (en) * | 2007-08-31 | 2008-01-23 | 北京工业大学 | Large cultural heritage picture pattern split-joint method based on characteristic |
US20120162224A1 (en) * | 2008-06-05 | 2012-06-28 | Kiu Sha Management Limited Liability Company | Free view generation in ray-space |
CN102663015A (en) * | 2012-03-21 | 2012-09-12 | 上海大学 | Video semantic labeling method based on characteristics bag models and supervised learning |
CN103886569A (en) * | 2014-04-03 | 2014-06-25 | 北京航空航天大学 | Parallel and matching precision constrained splicing method for consecutive frames of multi-feature-point unmanned aerial vehicle reconnaissance images |
-
2015
- 2015-06-03 CN CN201510300276.6A patent/CN106296568A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110122A (en) * | 2007-08-31 | 2008-01-23 | 北京工业大学 | Large cultural heritage picture pattern split-joint method based on characteristic |
US20120162224A1 (en) * | 2008-06-05 | 2012-06-28 | Kiu Sha Management Limited Liability Company | Free view generation in ray-space |
CN102663015A (en) * | 2012-03-21 | 2012-09-12 | 上海大学 | Video semantic labeling method based on characteristics bag models and supervised learning |
CN103886569A (en) * | 2014-04-03 | 2014-06-25 | 北京航空航天大学 | Parallel and matching precision constrained splicing method for consecutive frames of multi-feature-point unmanned aerial vehicle reconnaissance images |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107588768A (en) * | 2017-08-21 | 2018-01-16 | 中国科学院长春光学精密机械与物理研究所 | Interframe angular speed computational methods based on star chart |
CN107588768B (en) * | 2017-08-21 | 2020-07-07 | 中国科学院长春光学精密机械与物理研究所 | Star map-based inter-frame angular velocity calculation method |
CN111639658A (en) * | 2020-06-03 | 2020-09-08 | 北京维盛泰科科技有限公司 | Method and device for detecting and eliminating dynamic characteristic points in image matching |
CN111639658B (en) * | 2020-06-03 | 2023-07-21 | 北京维盛泰科科技有限公司 | Method and device for detecting and eliminating dynamic feature points in image matching |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fan et al. | Dual refinement underwater object detection network | |
Zhang et al. | Robust metric reconstruction from challenging video sequences | |
CN109035304B (en) | Target tracking method, medium, computing device and apparatus | |
Ma et al. | Stage-wise salient object detection in 360 omnidirectional image via object-level semantical saliency ranking | |
CN109389555B (en) | Panoramic image splicing method and device | |
CN104318517A (en) | Image splicing method and device and client terminal | |
CN109903282B (en) | Cell counting method, system, device and storage medium | |
JP6703314B2 (en) | Focus detection | |
US10096114B1 (en) | Determining multiple camera positions from multiple videos | |
CN110674886B (en) | Video target detection method fusing multi-level features | |
CN110276777B (en) | Image segmentation method and device based on depth map learning | |
US11361534B2 (en) | Method for glass detection in real scenes | |
CN113255685B (en) | Image processing method and device, computer equipment and storage medium | |
CN113407773A (en) | Short video intelligent recommendation method and system, electronic device and storage medium | |
CN114140623A (en) | Image feature point extraction method and system | |
CN115860091A (en) | Depth feature descriptor learning method based on orthogonal constraint | |
CN110544202A (en) | parallax image splicing method and system based on template matching and feature clustering | |
CN106327531A (en) | Panorama video identification method and device, and video playing method and device | |
CN112149545A (en) | Sample generation method and device, electronic equipment and storage medium | |
CN106331848A (en) | Panoramic video identification method and device, and video playing method and device | |
CN109785357B (en) | Robot intelligent panoramic photoelectric reconnaissance method suitable for battlefield environment | |
CN112270748B (en) | Three-dimensional reconstruction method and device based on image | |
CN106296568A (en) | Determination method, device and the client of a kind of lens type | |
CN106296580A (en) | A kind of method and device of image mosaic | |
CN106203244A (en) | A kind of determination method and device of lens type |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |