CN104580830B - A kind of quasistatic image anti-jitter method of facing video monitoring - Google Patents
A kind of quasistatic image anti-jitter method of facing video monitoring Download PDFInfo
- Publication number
- CN104580830B CN104580830B CN201510012974.6A CN201510012974A CN104580830B CN 104580830 B CN104580830 B CN 104580830B CN 201510012974 A CN201510012974 A CN 201510012974A CN 104580830 B CN104580830 B CN 104580830B
- Authority
- CN
- China
- Prior art keywords
- mrow
- mtd
- mtr
- present frame
- frame
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012544 monitoring process Methods 0.000 title claims abstract description 14
- 238000013508 migration Methods 0.000 claims abstract description 15
- 230000005012 migration Effects 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000003139 buffering effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000000205 computational method Methods 0.000 description 4
- 238000013519 translation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Abstract
The present invention provides a kind of quasistatic image anti-jitter method of facing video monitoring, including：It is updated periodically reference frame；Calculate the vertically and horizontally projection properties vector per two field picture；Obtain optimized migration amount of every two field picture relative to reference frame；Present image is corrected according to optimized migration amount.The present invention have processing speed it is fast, for the quasistatic scene image anti-jitter effect in video surveillance applications it is good the characteristics of.
Description
Technical field
The present invention relates to technical field of image processing, the quasistatic image anti-jitter side of specifically a kind of facing video monitoring
Method.
Background technology
In video surveillance applications, it is to set up in the wild to have a large portion video camera, and installation environment is more severe, greatly
Wind weather or earth shock can cause video camera randomized jitter up and down.If the scene of monitoring is furthered by high power camera lens
When, the shake in entire surface face clearly will have a strong impact on monitoring effect.Video camera is fixed on more stable support
Shake can be reduced, but this measure is in many occasions and infeasible, it is therefore desirable to using the method for image procossing, eliminate picture
Shake, improve video effect.
Visually producing the essence of shake is：In two width adjacent images, identical target point, successively it is shown on screen
Different positions.In image processing field, it is believed that there is an affine transformation relationship between this two images.In theory, only
This affine transformation relationship is obtained, all pixels point calibration of latter is returned, it is possible to eliminate jitter phenomenon.At present
The method of conventional feature based Point matching asks for affine transformation relationship.Extract key point (such as the angle of two images respectively first
Point etc.), mapping relations then are determined by calculating the similarity between key point, it is (general so as to calculate geometric transform relation
It is affine transformation relationship), then according to the relation, then all pixels of the second width image are transformed into new position, so as to eliminate
Shake.
The above method has versatility in theory, therefore can handle asking for the various images match in practical application
Topic, but amount of calculation is bigger, and cost of implementation is higher.In video surveillance applications, because camera views can only produce upper bottom left
Right translational motion, this is a kind of affine transformation of simplification in fact, therefore we can be this kind of special by new algorithm solution
Problem, so as to reduce amount of calculation, reduce cost of implementation.Such trial has a kind of " anti-jitter of video image in video monitoring
Method " (Chinese invention patent application CN104079800A), this method carry out piecemeal to image, calculate the texture of each image block
Feature, matching area is searched in image, translation parameters is then obtained according to the matching result of multiple images block, image is carried out
Jitter correction.This method reduces amount of calculation relative to the method for Feature Points Matching.
In video surveillance applications, the monitoring scene most areas of video camera in the wild is set up generally all without hair
Changing, it is believed that be a kind of quasistatic image, therefore, projection properties vector vertically and horizontally is relative and stable
's.
The content of the invention
It is an object of the invention to provide a kind of quasistatic image anti-jitter method of facing video monitoring, this method according to
The vertically and horizontally projection properties vector of image asks for translation parameters, and relative to the method for image Block- matching, amount of calculation is more
It is few.
The technical scheme is that：
A kind of quasistatic image anti-jitter method of facing video monitoring, comprises the following steps：
(1) two field picture is inputted, judges whether reference frame, if so, step (5) is then performed, if it is not, then performing step
(2)；
(2) using present frame as reference frame；
(3) the vertically and horizontally projection properties vector of present frame is calculated, and result of calculation buffering is got up；
(4) present frame is exported；
(5) judge whether to need to update reference frame, if so, step (2) is then jumped to, if it is not, then performing step (6)；
(6) the vertically and horizontally projection properties vector of present frame is calculated；
(7) according to the vertically and horizontally projection properties of present frame and reference frame vector, the optimal inclined of present frame is calculated
Shifting amount；
(8) present frame is corrected according to optimized migration amount；
(9) result by current frame offset correction exports.
The quasistatic image anti-jitter method of described facing video monitoring, in the step (3) and step (6), calculate
The vertically and horizontally projection properties vector of present frame, is specifically included：
(21) value of each pixel in current frame image is designated as I (i, j), 0≤i ＜ M, 0≤j ＜ N, wherein, represent picture
The abscissa of element, j represent the ordinate of pixel, and M represents the width of current frame image, and N represents the height of current frame image；
(22) the vertical direction projection properties vector of present frame is calculated using below equation：
Wherein, V represents the vertical direction projection properties vector of present frame, is a M dimensional vector, and v (i) represents present frame
The i-th dimension coefficient of vertical direction projection properties vector；
(23) the horizontal direction projection properties vector of present frame is calculated using below equation：
Wherein, H represents the horizontal direction projection properties vector of present frame, is a N-dimensional vector, and h (j) represents present frame
The jth of horizontal direction projection properties vector maintains number.
The quasistatic image anti-jitter method of described facing video monitoring, in the step (7), according to present frame and base
The vertically and horizontally projection properties vector of quasi- frame, calculates the optimized migration amount of present frame, specifically includes：
(31) offset index of present frame relative to reference frame in the horizontal direction is calculated using below equation：
Wherein, Vdiff(m) represent that skew when present frame offsets m pixel relative to reference frame in the horizontal direction refers to
Number, vb(i-m) represent that the i-th-m of the vertical direction projection properties vector of reference frame maintains number；
(32) offset index of present frame relative to reference frame in vertical direction is calculated using below equation：
Wherein, Hdiff(n) represent that skew when present frame offsets n pixel relative to reference frame in vertical direction refers to
Number, hb(j-n) represent that the jth-n of the horizontal direction projection properties vector of reference frame maintains number；
(33) obtaining makes Vdiff(m) minimum m, that is, obtain the optimized migration of present frame relative datum frame in the horizontal direction
Measure mopt；
(34) obtaining makes Hdiff(n) minimum n, that is, obtain present frame relative to reference frame in vertical direction it is optimal partially
Shifting amount nopt。
The present invention, when image is shaken, can effectively suppress the shake of image for not firm enough the video camera of support
Amplitude, improve subjective effect, and calculate comparatively fast, practicality is good.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention.
Embodiment
Below, the present invention is further illustrated with reference to the drawings and specific embodiments.
As shown in figure 1, a kind of quasistatic image anti-jitter method of facing video monitoring, comprises the following steps：
Step S01, a two field picture is inputted, has judged whether reference frame buffered, if it is, performing step S05, such as
Fruit is no, then performs step S02；
Step S02, using present frame as reference frame；
Step S03, the vertically and horizontally projection properties vector of present frame is calculated, and result of calculation buffering is got up；
Projection properties vector acquiring method be：
The value of each pixel in image is designated as I (i, j), 0≤i ＜ M, 0≤j ＜ N, i are the abscissas of the pixel, and j is
The ordinate of the pixel, M are the width of image, and N is the height of image；Vertical direction projection properties vector is a M dimensional vector,
V is designated as, as shown in formula [1], v (i) represents the i-th dimension coefficient of the vertical direction projection properties vector of present frame, such as formula [2]
It is shown；Horizontal direction projection properties vector is a N-dimensional vector, is designated as H, and as shown in formula [3], h (j) represents the water of present frame
The of flat directional projection feature vector maintains number, as shown in formula [4]；After calculating, result of calculation buffering is got up；
Formula [1]：
Formula [2]：
Formula [3]：
Formula [4]：
Step S04, present frame is exported；
Step S05, judge whether to need to update reference frame, the foundation of renewal is：One incremental sequence number is compiled to each frame,
When sequence number divides exactly some normal integer T, it is judged as being otherwise to be judged as NO, T is bigger, and renewal is slower, and the smaller renewals of T are faster；
In general, it is proper between being adjusted to the update cycle 1~100 second；If the judgment is Yes, then step S02 is performed, if
It is judged as NO, then performs step S06；
Step S06, the vertically and horizontally projection properties vector of present frame is calculated, computational methods are referring to step S03；
Step S07, according to the vertically and horizontally projection properties of present frame and reference frame vector, present frame is calculated most
Good offset, computational methods are：
When present frame offsets m pixel relative to reference frame in the horizontal direction, offset index Vdiff(m) computational methods are such as
Shown in formula [5], wherein vb(i-m) represent that the i-th-m of the vertical direction projection properties vector of reference frame maintains number；
When present frame offsets n pixel relative to reference frame in vertical direction, offset index Hdiff(n) computational methods are such as
Shown in formula [6], wherein hb(j-n) represent that the jth-n of the horizontal direction projection properties vector of reference frame maintains number；
Formula [5]：
Formula [6]：
Remember that the possible maximum offset of horizontal direction is MaxM, then m intervals are [- MaxM, MaxM], and obtaining makes Vdiff
(m) minimum m, the optimized migration amount being just horizontally oriented；
Remember that the possible maximum offset of vertical direction is MaxN, then n intervals are [- MaxN, MaxN], and obtaining makes Hdiff
(n) minimum n, the optimized migration amount being just vertically oriented；
Step S08, present frame is corrected according to optimized migration amount；
If step S07 calculates horizontal direction, optimized migration amount is mopt, then present frame integral level direction is translated
moptIndividual pixel, if step S07 calculates vertical direction, optimized migration amount is nopt, then present frame entirety vertical direction is translated
noptIndividual pixel；
Step S09, the result by current frame offset correction exports.
Embodiment described above is only that the preferred embodiment of the present invention is described, not to the model of the present invention
Enclose and be defined, on the premise of design spirit of the present invention is not departed from, technical side of the those of ordinary skill in the art to the present invention
The various modifications and improvement that case is made, it all should fall into the protection domain of claims of the present invention determination.
Claims (1)
1. a kind of quasistatic image anti-jitter method of facing video monitoring, it is characterised in that comprise the following steps：
(1) two field picture is inputted, judges whether reference frame, if so, step (5) is then performed, if it is not, then performing step (2)；
(2) using present frame as reference frame；
(3) the vertically and horizontally projection properties vector of present frame is calculated, and result of calculation buffering is got up；
(4) present frame is exported；
(5) judge whether to need to update reference frame, if so, step (2) is then jumped to, if it is not, then performing step (6)；
(6) the vertically and horizontally projection properties vector of present frame is calculated；
(7) it is vectorial according to the vertically and horizontally projection properties of present frame and reference frame, calculate the optimized migration amount of present frame；
(8) present frame is corrected according to optimized migration amount；
(9) result by current frame offset correction exports；
In the step (3) and step (6), the vertically and horizontally projection properties vector of present frame is calculated, is specifically included：
(21) value of each pixel in current frame image is designated as I (i, j), 0≤i<M, 0≤j<N, wherein, i represents the horizontal stroke of pixel
Coordinate, j represent the ordinate of pixel, and M represents the width of current frame image, and N represents the height of current frame image；
(22) the vertical direction projection properties vector of present frame is calculated using below equation：
<mrow>
<mi>V</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mn>0</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>-</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo><</mo>
<mi>N</mi>
</mrow>
</munder>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<mi>i</mi>
<mo><</mo>
<mi>M</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, V represents the vertical direction projection properties vector of present frame, is a M dimensional vector, and v (i) represents the vertical of present frame
The i-th dimension coefficient of directional projection feature vector；
(23) the horizontal direction projection properties vector of present frame is calculated using below equation：
<mrow>
<mi>H</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mn>0</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>k</mi>
<mrow>
<mo>(</mo>
<mi>N</mi>
<mo>-</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>k</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<mi>i</mi>
<mo><</mo>
<mi>M</mi>
</mrow>
</munder>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo><</mo>
<mi>N</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, H represents the horizontal direction projection properties vector of present frame, is a N-dimensional vector, and h (j) represents the level of present frame
The jth of directional projection feature vector maintains number；
In the step (7), according to the vertically and horizontally projection properties of present frame and reference frame vector, present frame is calculated
Optimized migration amount, is specifically included：
(31) offset index of present frame relative to reference frame in the horizontal direction is calculated using below equation：
<mrow>
<msub>
<mi>V</mi>
<mrow>
<mi>d</mi>
<mi>i</mi>
<mi>f</mi>
<mi>f</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>M</mi>
<mo>-</mo>
<mi>m</mi>
</mrow>
</mfrac>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>&le;</mo>
<mi>i</mi>
<mo><</mo>
<mi>M</mi>
</mrow>
</munder>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<mi>v</mi>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
<mo>-</mo>
<msub>
<mi>v</mi>
<mi>b</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mi>m</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>|</mo>
</mrow>
Wherein, Vdiff(m) offset index when present frame offsets m pixel relative to reference frame in the horizontal direction, v are representedb
(i-m) represent that the i-th-m of the vertical direction projection properties vector of reference frame maintains number；
(32) offset index of present frame relative to reference frame in vertical direction is calculated using below equation：
<mrow>
<msub>
<mi>H</mi>
<mrow>
<mi>d</mi>
<mi>i</mi>
<mi>f</mi>
<mi>f</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mi>n</mi>
</mrow>
</mfrac>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>n</mi>
<mo>&le;</mo>
<mi>j</mi>
<mo><</mo>
<mi>N</mi>
</mrow>
</munder>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<mi>h</mi>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
<mo>-</mo>
<msub>
<mi>h</mi>
<mi>b</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>|</mo>
</mrow>
Wherein, Hdiff(n) offset index when present frame offsets n pixel relative to reference frame in vertical direction, h are representedb
(j-n) represent that the jth-n of the horizontal direction projection properties vector of reference frame maintains number；
(33) obtaining makes Vdiff(m) minimum m, that is, obtain the optimized migration amount of present frame relative to reference frame in the horizontal direction
mopt；
(34) obtaining makes Hdiff(n) minimum n, that is, obtain the optimized migration amount of present frame relative to reference frame in vertical direction
nopt。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510012974.6A CN104580830B (en) | 2015-01-09 | 2015-01-09 | A kind of quasistatic image anti-jitter method of facing video monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510012974.6A CN104580830B (en) | 2015-01-09 | 2015-01-09 | A kind of quasistatic image anti-jitter method of facing video monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104580830A CN104580830A (en) | 2015-04-29 |
| CN104580830B true CN104580830B (en) | 2017-12-19 |
Family
ID=53095939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510012974.6A Active CN104580830B (en) | 2015-01-09 | 2015-01-09 | A kind of quasistatic image anti-jitter method of facing video monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104580830B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120096A (en) * | 2019-05-14 | 2019-08-13 | 东北大学秦皇岛分校 | A kind of unicellular three-dimensional rebuilding method based on micro- monocular vision |
| CN113163120A (en) * | 2021-04-21 | 2021-07-23 | 安徽清新互联信息科技有限公司 | Transformer-based video anti-shake method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101316368A (en) * | 2008-07-18 | 2008-12-03 | 西安电子科技大学 | Full view stabilizing method based on global characteristic point iteration |
| CN102685371A (en) * | 2012-05-22 | 2012-09-19 | 大连理工大学 | Digital video image stabilization method based on multi-resolution block matching and PI (Portion Integration) control |
| CN103475802A (en) * | 2013-09-26 | 2013-12-25 | 中国矿业大学 | Electronic image stabilization method |
| CN104079800A (en) * | 2014-06-24 | 2014-10-01 | 上海波汇通信科技有限公司 | Shaking preventing method for video image in video surveillance |
| CN104144283A (en) * | 2014-08-10 | 2014-11-12 | 大连理工大学 | Real-time digital video image stabilization method based on improved Kalman filter |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2521091B1 (en) * | 2011-05-03 | 2016-04-20 | ST-Ericsson SA | Estimation of motion blur in a picture |
-
2015
- 2015-01-09 CN CN201510012974.6A patent/CN104580830B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101316368A (en) * | 2008-07-18 | 2008-12-03 | 西安电子科技大学 | Full view stabilizing method based on global characteristic point iteration |
| CN102685371A (en) * | 2012-05-22 | 2012-09-19 | 大连理工大学 | Digital video image stabilization method based on multi-resolution block matching and PI (Portion Integration) control |
| CN103475802A (en) * | 2013-09-26 | 2013-12-25 | 中国矿业大学 | Electronic image stabilization method |
| CN104079800A (en) * | 2014-06-24 | 2014-10-01 | 上海波汇通信科技有限公司 | Shaking preventing method for video image in video surveillance |
| CN104144283A (en) * | 2014-08-10 | 2014-11-12 | 大连理工大学 | Real-time digital video image stabilization method based on improved Kalman filter |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104580830A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3800878B1 (en) | Cascaded camera motion estimation, rolling shutter detection, and camera shake detection for video stabilization | |
| CN101742122B (en) | Method and system for removing video jitter | |
| CN104574347B (en) | Satellite in orbit image geometry positioning accuracy evaluation method based on multi- source Remote Sensing Data data | |
| CN109461174B (en) | Video target area tracking method and video plane advertisement implanting method and system | |
| KR101479387B1 (en) | Methods and apparatuses for face detection | |
| KR100985805B1 (en) | Apparatus and method for image stabilization using adaptive Kalman filter | |
| CN102801972B (en) | The estimation of motion vectors and transmission method of feature based | |
| CN109472267A (en) | Picture similarity alignment algorithm | |
| CN104079800A (en) | Shaking preventing method for video image in video surveillance | |
| CN106023230B (en) | A kind of dense matching method of suitable deformation pattern | |
| CN106204415A (en) | A kind of novel method for registering images | |
| CN105872345A (en) | Full-frame electronic image stabilization method based on feature matching | |
| US20100149421A1 (en) | Image processing method for determining motion vectors of interpolated picture and related apparatus | |
| Cho et al. | Affine motion based CMOS distortion analysis and CMOS digital image stabilization | |
| CN104517317A (en) | Three-dimensional reconstruction method of vehicle-borne infrared images | |
| CN104506775A (en) | Image collection jitter removing method and device based on stereoscopic visual matching | |
| CN106408596A (en) | Edge-based local stereo matching method | |
| CN104580830B (en) | A kind of quasistatic image anti-jitter method of facing video monitoring | |
| CN114979489A (en) | Gyroscope-based heavy equipment production scene video monitoring and image stabilizing method and system | |
| CN102637295B (en) | Rapid electronic image-stabilizing method and device | |
| CN103024247A (en) | Electronic image stabilization method based on improved block matching | |
| CN105957053B (en) | Two dimensional image depth of field generation method and device | |
| CN103914807B (en) | Non-locality image super-resolution method and system for zoom scale compensation | |
| CN104376544B (en) | Non-local super-resolution reconstruction method based on multi-region dimension zooming compensation | |
| JP4020093B2 (en) | Edge detection method and apparatus, program, storage medium, and frame detection method, apparatus, program, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Quasi static image anti-jitter method oriented to video monitoring Effective date of registration: 20190705 Granted publication date: 20171219 Pledgee: Hefei high tech Company limited by guarantee Pledgor: ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co.,Ltd. Registration number: 2019340000361 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20200713 Granted publication date: 20171219 Pledgee: Hefei high tech Company limited by guarantee Pledgor: ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co.,Ltd. Registration number: 2019340000361 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A quasi static image anti dithering method for video surveillance Effective date of registration: 20210611 Granted publication date: 20171219 Pledgee: Anhui Science and technology Financing Guarantee Co.,Ltd. Pledgor: ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co.,Ltd. Registration number: Y2021980004615 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20220718 Granted publication date: 20171219 Pledgee: Anhui Science and technology Financing Guarantee Co.,Ltd. Pledgor: ANHUI QINGXIN INTERNET INFORMATION TECHNOLOGY Co.,Ltd. Registration number: Y2021980004615 |