CN110458776A - A kind of the real-time video antidote and its electronic equipment of customizable - Google Patents
A kind of the real-time video antidote and its electronic equipment of customizable Download PDFInfo
- Publication number
- CN110458776A CN110458776A CN201910714963.0A CN201910714963A CN110458776A CN 110458776 A CN110458776 A CN 110458776A CN 201910714963 A CN201910714963 A CN 201910714963A CN 110458776 A CN110458776 A CN 110458776A
- Authority
- CN
- China
- Prior art keywords
- correction
- image
- real
- video
- corrected
- 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
- 239000000729 antidote Substances 0.000 title claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 150
- 238000004088 simulation Methods 0.000 claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000003384 imaging method Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 abstract description 14
- 230000003287 optical effect Effects 0.000 abstract description 4
- 230000009466 transformation Effects 0.000 abstract description 4
- 229940075522 antidotes Drugs 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 241001292396 Cirrhitidae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
This application involves a kind of real-time video antidote of customizable, applied to can carry out in the electronic equipment of video processing;The method is on the basis of the original image of holding effective content, single-frame images corrected zone is handled, and correcting image is generated, the consistency for being influenced to guarantee the time is not blocked in the subregion part and global correction in real time, the method for carrying out image/video by movement;It in the case where joining variation outside camera lens, reads in camera lens and joins outside, by amendment corrected zone, correct parameters of formula, carry out subregion part and the overall situation correction in real time of image/video;Using the spatial character according to corrected zone, nonlinear transformation is introduced, optimizes longitude and latitude correction model, isolate longitude correction and dimension correction, subregion part and the overall situation correction in real time of image/video are carried out in conjunction with the optical center radius of simulation correction model by the various combination of two kinds of antidotes.
Description
Technical field
This application involves image technique field, in particular to the real-time video antidote and its electronics of a kind of customizable
Equipment.
Background technique
With the promotion of network speed, the visualization file such as image, video is more and more to be appeared in our lives.It is regarding
In terms of frequency acquisition video, generally require to correct image acquired in camera, to provide more preferable visual effect;Existing
In technology, often through important area in identification image, several regions is divided the image into, multiple seamless partial projection areas are formed
The such width figure in domain completes the projection correction of full figure by multiple seamless interval combinations projections.The above method is dependent in image
Hold, it is undesirable in the unconspicuous scene of image texture characteristic or the scene effect that is blocked of movement, while operation complicated difficult with
It realizes real-time, is not suitable with video flowing.
Summary of the invention
In order to solve the above-mentioned technical problem the application, provides a kind of real-time video antidote of customizable, application
In the electronic equipment that can carry out video processing, comprising:
Obtain the resolution ratio H*W of video flowing to be corrected;
Obtain simulation correction center and the simulation correction radius of single-frame images corrected zone;
According to the simulation correction center and simulation correction radius, single-frame images corrected zone is handled, and generates
Correcting image.
Optionally, the simulation correction central information and simulation correction radius information are obtained or are passed through by external input
Imaging space characteristic obtains.
It is optionally, described that single-frame images corrected zone is handled, comprising:
By longitude correction and/or latitude correction, single-frame images corrected zone is corrected.
It is optionally, described that single-frame images corrected zone is handled, comprising:
Corrected zone is treated by the correction of secondary longitude to be corrected, correcting image is generated, and corrects formula are as follows:
Wherein, (f (u, v), v) is any point on former single-frame images, and coordinate is (u, v), (x in corresponding correction figure0.y0)
Center origin is simulated for correction model, R is simulation correction radius, aiFor variable element relevant to R, biFor linear variable constant.
It is optionally, described that single-frame images corrected zone is handled, comprising:
The left and right sides any region of image is corrected by a longitude respectively, corrects formula are as follows:
Wherein, (f (u, v), v) is any point on former single-frame images, and coordinate is (u, V), (x in corresponding correction figure0, y0)
For correction model origin, R is simulation correction radius.
Optionally, execution is described is respectively corrected the left and right sides any region of image by a longitude
Afterwards, further includes:
To the single-frame images for carrying out the correction of a longitude, first part and second part are separated by cut-off rule up and down;
The first part is subjected to nonuniform stretching processing;
The second part is subjected to one or many latitude corrections, correction formula is
By carrying out ROI region cutting, generating to the first part and the second part single-frame images that carries out that treated
Correcting image.
Optionally, the cut-off rule is obtained by external input or is obtained by imaging space characteristic.
Optionally, the external input is that electronic equipment is keyed in or touch-control inputs.
Optionally, after the generation correcting image, further includes:
According to the mapping relations of former single-frame images and correcting image, mapped file is generated;
According to the mapped file, each frame image of video flowing is corrected in real time.
In addition, present invention also provides a kind of electronic equipments of real-time video correction, including a kind of above-mentioned customizable
Real-time video antidote.
The real-time video antidote and its electronic equipment of a kind of customizable of the application, the beneficial effect is that, this
Application causes to obtain image/video imaging spy using different camera lens installation parameters on the basis of the original image of holding effective content
Property, the consistency for being influenced to guarantee the time is not blocked by movement, according to the spatial character of corrected zone, optimizes longitude and latitude and corrects mould
Type carries out subregion part and the overall situation correction in real time of image/video.On the basis of the original image of holding effective content, to list
Frame image flame detection region is handled, and generates correcting image, carries out subregion part and the overall situation correction in real time of image/video,
The method is not blocked the consistency for being influenced to guarantee the time by movement;In the case where joining variation outside camera lens, reads in and joins outside camera lens,
By amendment corrected zone, correction parameters of formula, subregion part and the overall situation correction in real time of image/video are carried out;Utilize basis
The spatial character of corrected zone introduces nonlinear transformation, optimizes longitude and latitude correction model, isolates longitude correction and dimension correction,
The subregion office of image/video is carried out in conjunction with the optical center radius of simulation correction model by the various combination of two kinds of antidotes
Portion and global correction in real time.
Detailed description of the invention
Fig. 1 is the image correction method flow chart of the embodiment of the present application;
Fig. 2 is the video flowing antidote flow chart of the embodiment of the present application;
Fig. 3 is a kind of schematic diagram of method of image flame detection of the embodiment of the present application;
Fig. 4 is the schematic diagram of the image flame detection another kind method of the embodiment of the present application.
Specific embodiment
The preferred embodiment of the application is described in detail with reference to the accompanying drawing so that the advantages of the application and feature more
It is easily readily appreciated by one skilled in the art, to make apparent define to the protection scope of the application.
In a kind of embodiment as shown in Figure 1, this application provides a kind of real-time video antidote of customizable,
Applied to can carry out in the electronic equipment of video processing, comprising:
100, obtain the resolution ratio H*W of video flowing to be corrected;
In step 100, in the electronic device, the electronic equipment that can carry out video processing passes through for video flowing storage to be corrected
The real-time video antidote for running customizable carries out video correction, and process includes 100, obtains point of video flowing to be corrected
Resolution H*W can obtain resolution information therein by parsing video stream file, can also be arranged in electronic equipment by reading
Video acquisition device resolution parameter obtain it is to be measured correction video flowing resolution information, this step obtain resolution ratio H*W
Afterwards, and according to resolution ratio H*W video is corrected.
200, obtain simulation correction center and the simulation correction radius of single-frame images corrected zone;
In step 200, simulation correction central information and simulation correction radius information are obtained by external input;If electronics
Equipment is the computer with mouse-keyboard, simulation correction center can be chosen by mouse-keyboard, and simulate by a keyboard entry
Correct radius information;If electronic equipment be can touch-control computer or mobile terminal device, can pass through touch-control choose simulation correction
Center, and key in simulation correction radius information.It chooses simulation correction central information and simulation correction radius information according to user
The setting of being customized of demand;In addition, can be also customized by presetting according to the video acquisition device that electronic equipment is arranged in
Change configuration, to reach optimal display result.
300, according to simulation correction center and simulation correction radius, single-frame images corrected zone is handled, and generates
Correcting image.
In step 300, it is corrected by longitude correction and/or latitude, single-frame images corrected zone is corrected,
In, longitude correction can be the parameter correction carried out any point on the single-frame images of video flowing to be corrected in X-axis, and latitude is rectified
Just can be the parameter correction any point on the single-frame images of video flowing to be corrected carried out in Y-axis;In the present embodiment, lead to
It crosses longitude correction or latitude correction or longitude correction and latitude correction combines, single-frame images is corrected, after the completion of correction
Generate correcting image.
In the present embodiment, in the electronic device, the electronic equipment that can carry out video processing is logical for video flowing storage to be corrected
The real-time video antidote for crossing operation customizable carries out video correction, and the video acquisition device that electronic equipment is arranged in can
To be fish eye lens, wide-angle lens or other kinds of camera lens.The application is on the basis of the original image of holding effective content, benefit
Image/video imaging characteristic is caused to obtain with different camera lens installation parameters, the consistency for being influenced to guarantee the time is not blocked by movement,
According to the spatial character of corrected zone, optimize longitude and latitude correction model, the subregion part and the overall situation for carrying out image/video are rectified in real time
Just.
In some embodiments, simulation correction central information and simulation correction radius information by external input acquisition or at
Image space characteristic obtains.If electronic equipment is the computer with mouse-keyboard, can be chosen by mouse-keyboard in simulation correction
The heart, and simulation correction radius information by a keyboard entry;If electronic equipment be can touch-control computer or mobile terminal device, can
Simulation correction center is chosen by touch-control, and keys in simulation correction radius information.It chooses simulation correction central information and simulation
Radius information is corrected to be arranged according to being customized of user demand.In the present embodiment, imaging space characteristic, which can be, defaults in
The correction parameter of video correction system, video correction system are chosen corresponding according to the camera lens posture of current video flowing to be corrected
Default correction parameter, video flowing is handled.In addition, imaging space characteristic is also possible to rectifying for video correction generation
The camera lens posture of the image of positive parameter, such as output for generating correction parameter and the camera lens posture phase for exporting video flowing to be corrected
Together, then directly by reading the correction parameter that is previously generated, that video flowing is rapidly completed on the basis of keeping original picture material is more
Correction that region is seamless;As exported the camera lens posture of the image for generating correction parameter and exporting the camera lens appearance of video flowing to be corrected
State is mutually different, then needs to pass through imaging space characteristic, i.e. the relative translation matrix Q of camera lens according to camera lens3×3With related spin matrix
R3×3Obtain formula: H3×3=R3×3Q3×3…(4)。
In some embodiments, single-frame images corrected zone is handled, comprising: pass through longitude correction and/or latitude
Correction, corrects single-frame images corrected zone;Longitude correction can be appointing on the single-frame images of video flowing to be corrected
The parameter correction in X-axis is a little carried out, latitude correction, which can be, carries out Y for any point on the single-frame images of video flowing to be corrected
Parameter correction on axis;In the present embodiment, it is combined by longitude correction or latitude correction or longitude correction and latitude correction,
Single-frame images is corrected, correcting image is generated after the completion of correction.
In some embodiments, single-frame images corrected zone is handled, comprising:
Corrected zone is treated by the correction of secondary longitude to be corrected, correcting image is generated, and corrects formula are as follows:
Wherein, (f (u, v), v) is any point on former single-frame images, and coordinate is (u, V), (x in corresponding correction figure0, y0)
Center origin is simulated for correction model, R is simulation correction radius, aiFor the relevant variable element of R, biFor linear variable constant.
In this embodiment, secondary longitude correction, ginseng are carried out by above-mentioned correction formula by each point to single-frame images
See that Fig. 3, left hand view are former single-frame images, right part of flg is correcting image.If the simulation center origin of left area model is (W0,
H0), right side modeling center origin is (W1, H1);Generate correcting image.
In some embodiments, single-frame images corrected zone is handled, comprising:
Any region at left and right sides of former single-frame images is corrected by a longitude respectively, corrects formula are as follows:
Wherein, (f (u, v), v) is any point on former single-frame images, and coordinate is (u, v), (x in corresponding correction figure0.y0)
For correction model origin, R is simulation correction radius, aiFor the relevant variable element of R, biFor linear variable constant.
Any region at left and right sides of former single-frame images is passed through into correction formula (2) by each pixel of a longitude
Carry out longitude correction.
It executes after being corrected respectively to the left and right sides any region of image by a longitude, further includes:
To the single-frame images for carrying out the correction of a longitude, first part and second part are separated by cut-off rule up and down;
First part is subjected to nonuniform stretching processing;Image stretch is also referred to as contrast enhancing or contrast enhancing, is to pass through
Change the brightness value of image primitive to improve the whole or local contrast of image, a kind of method of improving image quality.Its geometry
Correction is exactly the geometry deformation for eliminating image, realizes the process of the geometry integration of original image and standard picture or map.Geometry
It mutually corrects: referring to earth station according to the various correction parameters related with sensor of measurement to made by the logical sense data received
Correction process, this correction are very effective to sensor internal distortion is eliminated;In the present embodiment, the stretch processing of first part
It is heterogeneous to reach optimal display result;In the present embodiment, a kind of embodiment of nonuniform stretching is, by into
The transformation of row class hyperbola formula carries out nonuniform stretching: its formula are as follows:Wherein a=H0, b is mould
Quasi- radius R0, nonuniform stretching is then carried out, wherein (6) u=x ...;By formula (6), formula (7) substitution can
Acquire formula (5).
Second part is subjected to one or many latitude corrections, correction formula is
In the present embodiment, single-frame images can carry out one or many latitude corrections according to imaging demand, to meet user
It is required that imaging effect.In the present embodiment, each reference point of the second part of single-frame images is subjected to the every of a latitude
One pixel carries out latitude correction by correction formula (3), carries out correction process by each pixel to single-frame images
To obtain required image.
By carrying out ROI region cutting, generating correction to first part and the second part single-frame images that carries out that treated
Image, in the present embodiment, ROI region can be chosen according to user demand, can also be chosen according to systemic presupposition value.
Referring to fig. 4, in the present embodiment, first to former single-frame images, that is, upper left corner Fig. 4 figure, respectively to image or so
One corrected zone is corrected, and the correction that region carries out following formula is once corrected, wherein corrected zone by being an externally input or
Person is chosen by imaging space characteristic;Secondly the image after a longitude being corrected separate up and down and is separated into first
Part and second part;First part, second part are handled respectively respectively again, generate the figure in the upper right corner Fig. 4;Finally
By carrying out ROI region and cutting such as to first part and second part single-frame images, that is, upper right corner Fig. 4 figure that carries out that treated
The figure in the lower left corner Fig. 4 generates correcting image.Wherein, ROI is area-of-interest.In machine vision, image procossing, from processed
Image region to be treated, referred to as area-of-interest are sketched the contours of in a manner of box, circle, ellipse, irregular polygon etc..In
Various operators and function are commonly used on the machine vision softwares such as Halcon, OpenCV, Matlab to acquire region of interest ROI,
And carry out the next step processing of image.
After embodiment as shown in Figure 2, after generating correcting image, further includes:
According to the mapping relations of former single-frame images and correcting image, mapped file is generated;
In the present embodiment, according to each pixel of former single-frame images each pixel corresponding with its correcting image
Mapping relations, generate mapped file, i.e. mapping table, in the present embodiment, mapped file are map file.
According to mapped file, each frame image of video flowing is corrected in real time.
In the present embodiment, according to mapped file, i.e. mapping table, by each frame image of video flowing according to mapping relations into
Row correction in real time;The seamless correction of video flowing ROI region multizone is rapidly completed by reading file map;The application is being kept
On the basis of original effective content of image, image/video imaging characteristic is caused to obtain using different camera lens installation parameters, is not moved
The influence blocked guarantees the consistency of time, according to the spatial character of corrected zone, optimizes longitude and latitude correction model, carries out image view
The subregion part of frequency and global correction in real time.
In some embodiments, the cut-off rule is obtained by external input;The external input is electronic equipment key entry
Or touch-control input.Electronic equipment can be operation have the PC machine of real-time video antidote of above-mentioned customizable a kind of, mobile phone,
The mobile terminals such as plate can carry out checking picture, and lead to when the single-frame images to video is corrected by the screen of PC machine
The input that the external input devices such as mouse-keyboard carry out the data of customizables such as simulation center, simulation radius, cut-off rule is crossed, it is whole
Image under each frame of a video carries out analogy adjusting according to the current single-frame images adjusted is customized.When the single frames to video
When image is corrected, can check picture by showing screen, and be simulated by external input devices such as touch-controls
The input of the heart, simulation radius, the data of customizables such as cut-off rule, image under each frame of entire video are adjusted according to customizing
The current single-frame images of section carries out analogy adjusting.
In some embodiments, video flowing to be corrected is obtained, the image of a certain frame of video flowing to be corrected is chosen, is named as
Current single-frame images goes the dark seamless correction of angle subregion domain video stream to realize;Current single-frame images is carried out by following steps
Processing:
Obtain the resolution ratio H*W of video flowing to be corrected;
Current single-frame images is divided into two to corrected zone by cut-off rule;
Single-frame images two simulations to corrected zone are obtained respectively corrects center;
Single-frame images two simulations to corrected zone are obtained respectively corrects radius;
Using secondary longitude correction treat corrected zone carry out correction formula it is as follows
If (x, y) is any point in original graph, coordinate is (u, v) in corresponding correction figure, and point (x0, y0) is correction model
Center origin is simulated, R is simulation correction radius.
Wherein, if the simulation center origin of left area model is (W0, H0), right side modeling center origin is (W1,
H1);(W0, H0)、(W1, H1) known parameters that are an externally input or are obtained by imaging space characteristic, aiFor R is relevant can
Variable element, biFor linear variable constant.
Mapping relations are stored in a file map according to formula (2);
It is as identical with the camera lens posture of video flowing to be corrected is exported for calculating the camera lens posture of the image of map in exported, then
The seamless correction of video flowing multizone is directly rapidly completed on the basis of keeping original picture material by reading file map;Such as
Output is mutually different with the camera lens posture for exporting video flowing to be corrected for calculating the camera lens posture of the image of map, then needs basis
Camera lens passes through imaging space characteristic, i.e. the relative translation matrix Q of camera lens3×3With related spin matrix R3×3Obtain formula:
H3×3=R3×3Q3×3…(4)
For repairing simulation optical center and simulation radius, repeats the above steps and complete the mapping of map.
In some embodiments, video flowing to be corrected is obtained, the image of a certain frame of video flowing to be corrected is chosen, is named as
Current single-frame images, to realize the ROI region correction for keeping greatest content, including following implementation steps:
Obtain the resolution ratio H*W of video flowing to be corrected;
Current single-frame images is divided into two to corrected zone by cut-off rule;
Single-frame images two simulations to corrected zone are obtained respectively corrects center;
Single-frame images two simulations to corrected zone are obtained respectively corrects radius;
A corrected zone of image or so is corrected respectively, the correction that region carries out following formula is once corrected,
In, corrected zone is by being an externally input or being chosen by imaging space characteristic;
If (x, v) is any point in original graph, coordinate is (u, v) in corresponding correction figure, and point (f (u, v), y0) is correction
Model origin, R are simulation correction radius:
If the simulation center origin of left area model is (W0, H0), right side modeling center origin is (W1, H1), In
In the present embodiment, (W0, H0)、(W1, H1) known parameters that are an externally input or are obtained by imaging space characteristic;
Based on above-mentioned steps, top and the bottom segmentation is carried out using cut-off rule to image, lower half portion carries out following formula
Second of correction:
If lower half portion modeling center origin O is (W2, H2), radius R is R0, the correction of the different piece of image, mould
Quasi- center origin O, cut-off rule, R are different.
Top half carries out nonuniform stretching, in the present embodiment, by carrying out to the transformation for carrying out class hyperbola formula
Nonuniform stretching:
Wherein a=H0, b is simulation radius R0, nonuniform stretching is then carried out, wherein
U=x ... (6)
ROI region cutting is carried out according to demand to the image after correction.
Mapping relations are stored in a file map according to above formula.
It is as identical with the camera lens posture of video flowing to be corrected is exported for calculating the camera lens posture of the image of map in exported, then
The seamless correction of video flowing multizone is directly rapidly completed on the basis of keeping original picture material by reading file map;Such as
Output is mutually different with the camera lens posture for exporting video flowing to be corrected for calculating the camera lens posture of the image of map, then needs basis
Camera lens passes through imaging space characteristic, i.e. the relative translation matrix Q of camera lens3×3With related spin matrix R3×3Obtain formula:
H3×3=R3×3Q3×3…(4)
For repairing simulation optical center and simulation radius, repeats the above steps and complete the mapping of map.
In some embodiments, present invention also provides a kind of electronic equipments of real-time video correction, including above-mentioned one
The real-time video antidote of kind customizable.The electronic equipment of the application can be installed using different video acquisition device, that is, camera lens
Parameter causes to obtain image/video imaging characteristic, realizes the seamless correction of subregion.Customized correction formula according to demand carries out image
The subregion part of video and global correction in real time.Video acquisition device, that is, camera lens to be corrected can be demarcated and can not be demarcated.This Shen
Please on the basis of the original image of holding effective content, image/video imaging characteristic is caused to obtain using different camera lens installation parameters,
The consistency for being influenced to guarantee the time is not blocked by movement, according to the spatial character of corrected zone, optimizes longitude and latitude correction model, into
The subregion part of row image/video and global correction in real time.
Wherein, the numerical value a occurred in any of the above-described embodimenti、bi、(W0, H0)、(W1, H1)、(W2, H2)、R0It is external defeated
The known parameters for entering or being obtained by imaging space characteristic, and realize that relevant art effect more preferably regards for Fig. 3 or Fig. 4
Frequency correction parameter, specific value can be adjusted according to actual scene and imaging effect.The present invention is not limited to any of the above-described realities
Numerical value cited by example is applied, the technical solution of video correction can be implemented in combination with by said one embodiment or multiple embodiments
It each falls in the protection scope of the application.
Presently filed embodiment is explained in detail above in conjunction with attached drawing, but the application is not limited to above-mentioned implementation
Mode within the knowledge of a person skilled in the art can also be under the premise of not departing from the application objective
Various changes can be made.
Claims (10)
1. a kind of real-time video antidote of customizable, applied to can carry out in the electronic equipment of video processing, feature
It is, comprising:
Obtain the resolution ratio H*W of video flowing to be corrected;
Obtain simulation correction center and the simulation correction radius of single-frame images corrected zone;
According to the simulation correction center and simulation correction radius, single-frame images corrected zone is handled, and generate correction
Image.
2. a kind of real-time video antidote of customizable according to claim 1, which is characterized in that the simulation is rectified
Center information and simulation correction radius information are obtained by external input or are obtained by imaging space characteristic.
3. a kind of real-time video antidote of customizable according to claim 1, which is characterized in that described to single frames
Image flame detection region is handled, comprising:
By longitude correction and/or latitude correction, single-frame images corrected zone is corrected.
4. a kind of real-time video antidote of customizable according to claim 3, which is characterized in that described to single frames
Image flame detection region is handled, comprising:
Corrected zone is treated to correction by the correction of secondary longitude to correct, generates correcting image, corrects formula are as follows:
Wherein (f (u, v), v) is any point on former single-frame images, and coordinate is (u, v), (x in corresponding correction figure0,y0) it is correction
Modeling center origin, R are simulation correction radius, aiFor the relevant variable element of R, biFor linear variable constant.
5. a kind of real-time video antidote of customizable according to claim 3, which is characterized in that described to single frames
Image flame detection region is handled, comprising:
The left and right sides any region of image is corrected by a longitude respectively, corrects formula are as follows:
Wherein (f (u, v), v) is any point on former single-frame images, and coordinate is (u, v), (x in corresponding correction figure0,y0) it is correction
Model origin, R are simulation correction radius, aiFor the relevant variable element of R, biFor linear variable constant.
6. a kind of real-time video antidote of customizable according to claim 5, which is characterized in that execute described point
After the other left and right sides any region to image is corrected by a longitude, further includes:
To the single-frame images for carrying out the correction of a longitude, first part and second part are separated by cut-off rule up and down;
The first part is subjected to nonuniform stretching processing;
The second part is subjected to one or many latitude corrections, corrects formula are as follows:
By carrying out ROI region cutting, generating correction to the first part and the second part single-frame images that carries out that treated
Image.
7. a kind of real-time video antidote of customizable according to claim 6, which is characterized in that the cut-off rule
It is obtained by external input or is obtained by imaging space characteristic.
8. a kind of real-time video antidote of customizable according to claim 2 or 7, which is characterized in that described outer
Portion's input is that electronic equipment is keyed in or touch-control inputs.
9. a kind of real-time video antidote of customizable according to claim 1, which is characterized in that described generate is rectified
After positive image, further includes:
According to the mapping relations of former single-frame images and correcting image, mapped file is generated;
According to the mapped file, each frame image of video flowing is corrected in real time.
10. a kind of electronic equipment of real-time video correction, which is characterized in that customizable including one kind described in claim 1-9
The real-time video antidote of change.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910714963.0A CN110458776B (en) | 2019-07-31 | 2019-07-31 | Customizable real-time video correction method and electronic equipment thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910714963.0A CN110458776B (en) | 2019-07-31 | 2019-07-31 | Customizable real-time video correction method and electronic equipment thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110458776A true CN110458776A (en) | 2019-11-15 |
CN110458776B CN110458776B (en) | 2023-05-19 |
Family
ID=68484823
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910714963.0A Active CN110458776B (en) | 2019-07-31 | 2019-07-31 | Customizable real-time video correction method and electronic equipment thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110458776B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105354796A (en) * | 2015-10-12 | 2016-02-24 | 北京鑫洋泉电子科技有限公司 | Image processing method and system used for driving assistance |
CN106600549A (en) * | 2016-11-16 | 2017-04-26 | 深圳六滴科技有限公司 | Method and device for correcting fisheye image |
US20180150944A1 (en) * | 2016-01-18 | 2018-05-31 | Shenzhen Arashi Vision Company Limited | Method and Device For Rectifying Image Photographed by Fish-Eye Lens |
CN108830810A (en) * | 2018-06-07 | 2018-11-16 | 辽宁工业大学 | A kind of fisheye image distortion correction method based on rectangular projection |
CN109308686A (en) * | 2018-08-16 | 2019-02-05 | 北京市商汤科技开发有限公司 | A kind of fish eye images processing method and processing device, equipment and storage medium |
-
2019
- 2019-07-31 CN CN201910714963.0A patent/CN110458776B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105354796A (en) * | 2015-10-12 | 2016-02-24 | 北京鑫洋泉电子科技有限公司 | Image processing method and system used for driving assistance |
US20180150944A1 (en) * | 2016-01-18 | 2018-05-31 | Shenzhen Arashi Vision Company Limited | Method and Device For Rectifying Image Photographed by Fish-Eye Lens |
CN106600549A (en) * | 2016-11-16 | 2017-04-26 | 深圳六滴科技有限公司 | Method and device for correcting fisheye image |
CN108830810A (en) * | 2018-06-07 | 2018-11-16 | 辽宁工业大学 | A kind of fisheye image distortion correction method based on rectangular projection |
CN109308686A (en) * | 2018-08-16 | 2019-02-05 | 北京市商汤科技开发有限公司 | A kind of fish eye images processing method and processing device, equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
杨玲等: "应用经纬映射的鱼眼图像校正设计方法", 《工程图学学报》 * |
贺晓冬等: "鱼眼图像在城市气象研究中的应用", 《S8 大气探测与仪器新技术、新方法》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110458776B (en) | 2023-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4452497B2 (en) | Method and system for modifying a digital image in consideration of noise | |
CN105825544A (en) | Image processing method and mobile terminal | |
CN112272292B (en) | Projection correction method, apparatus and storage medium | |
CN103843329B (en) | Methods and apparatus for conditional display of a stereoscopic image pair | |
CN110335330B (en) | Image simulation generation method and system, deep learning algorithm training method and electronic equipment | |
WO2016197469A1 (en) | Method and apparatus for generating unlocking interface, and electronic device | |
CN113126862B (en) | Screen capture method and device, electronic equipment and readable storage medium | |
WO2023093291A1 (en) | Image processing method and apparatus, computer device, and computer program product | |
US20190340726A1 (en) | Projection image construction method and device | |
CN108551552A (en) | Image processing method, device, storage medium and mobile terminal | |
CN110458790A (en) | A kind of image detecting method, device and computer storage medium | |
CN106919246A (en) | The display methods and device of a kind of application interface | |
CN111540060B (en) | Display calibration method and device of augmented reality equipment and electronic equipment | |
CN111968605A (en) | Exposure adjusting method and device | |
CN110458776A (en) | A kind of the real-time video antidote and its electronic equipment of customizable | |
US20190252431A1 (en) | Image processing apparatus and image processing method | |
CN103674274A (en) | Thermal image recording control device and thermal image recording control method | |
CN116053549A (en) | Battery cell positioning method, device and system | |
CN103674269A (en) | Thermal image measuring device and thermal image measuring method | |
CN111428707A (en) | Method and device for identifying pattern identification code, storage medium and electronic equipment | |
CN116880723B (en) | 3D scene display method and system | |
CN117689782B (en) | Method, device, equipment and storage medium for generating poster image | |
TWI813181B (en) | Image processing circuit and image processing method | |
CN117389451A (en) | Image processing method and device | |
CN113538655B (en) | Virtual face generation method and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20191115 Assignee: Shenzhen Dechi micro vision technology Co.,Ltd. Assignor: SHENZHEN DESAY MICROELECTRONIC TECHNOLOGY Co.,Ltd. Contract record no.: X2020980002081 Denomination of invention: Customizable real-time video correction method and electronic device thereof License type: Exclusive License Record date: 20200509 |
|
EE01 | Entry into force of recordation of patent licensing contract | ||
GR01 | Patent grant | ||
GR01 | Patent grant |