CN104135597A - Automatic detection method of jitter of video - Google Patents
Automatic detection method of jitter of video Download PDFInfo
- Publication number
- CN104135597A CN104135597A CN201410318324.XA CN201410318324A CN104135597A CN 104135597 A CN104135597 A CN 104135597A CN 201410318324 A CN201410318324 A CN 201410318324A CN 104135597 A CN104135597 A CN 104135597A
- Authority
- CN
- China
- Prior art keywords
- video
- jitter
- light stream
- stream vector
- video jitter
- 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
- 238000001514 detection method Methods 0.000 title abstract description 10
- 239000013598 vector Substances 0.000 claims abstract description 65
- 230000002159 abnormal effect Effects 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 230000006641 stabilisation Effects 0.000 description 13
- 238000011105 stabilization Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses an automatic detection method of jitter of a video. The automatic detection method comprises the following steps of: a first step, selecting feature points from a video picture; a second step, tracing and matching the feature points in an adjacent frame; a third step, removing abnormal points of the feature points to obtain an inter-frame motion vector; a fourth step, extracting a video jitter frequency and video jitter amplitude features; a fifth step, extracting histogram features of an inter-frame light stream vector; and a sixth step, judging the video jitter degree through a classifier. According to the automatic detection method, any prior knowledge is not needed while judging whether the video has jitter and the automatic detection method has the advantage of a higher accuracy rate.
Description
Technical field
Whether the present invention can be used for mobile phone, Digital Video, the first-class movement of monitoring camera or the captured digital video of permanent plant, exist shake automatically to detect, specifically a kind of video jitter automatic testing method to digital video picture.
Background technology
The digital video that mobile terminal is taken is often with video jitter, and the existence of video jitter affects the visual quality of video and such as subsequent treatment effects such as target identifications, therefore, exists at present various video digital image stabilization method for reducing video jitter degree.But, for a digital video arbitrarily, need to first judge its video jitter degree, could correct Video Stabilization method and the method parameter of selecting properly.
On the one hand, video jitter detection method can be used as the pretreatment module of Video Stabilization method, for any video, first detects video jitter degree, according to degree of jitter, selects corresponding digital image stabilization method and parameter; On the other hand, video jitter detection method can be used as the subsequent treatment module of Video Stabilization method, and the video after digital image stabilization method is processed carries out shaking detection, and the effect of digital image stabilization method is evaluated.
At present, shaking detection and the evaluation for digital video also do not have complete detection method and standard, the present invention to be intended to propose a kind of effective video shake automatic testing method.
Summary of the invention
The present invention proposes a kind of video jitter automatic testing method, and without any input video priori in the situation that, it can be used for choosing digital image stabilization method kind and regulates digital image stabilization method parameter, and can be used for evaluating the steady picture effect of digital image stabilization method.
For achieving the above object, the technical solution used in the present invention is: first the present invention finds equally distributed characteristic point in video pictures, and tracking characteristics point obtains sparse optical flow vector, then through abnormal light stream vector, gets rid of and obtains interframe light stream vector.Interframe light stream vector is averaged and obtained the estimation of inter frame motion model, from motion model, count video jitter frequency, video jitter amplitude two class jitter features, obtain light stream vector histogram as a class jitter feature according to interframe light stream vector.Finally above-mentioned three class video jitter features are input to the degree of jitter that the video jitter degree grader training obtains input video.
A kind of video jitter automatic testing method of the present invention, comprises the steps:
The first step, chooses characteristic point in present frame picture;
Second step, tracking and matching characteristic point in consecutive frame, obtains interframe light stream vector;
The 3rd step, the interframe light stream vector that second step is obtained carries out abnormity point eliminating;
The 4th step, the interframe light stream vector obtaining according to the 3rd step is estimated inter frame motion model, then according to this model extraction, goes out video jitter frequency, two features of video jitter amplitude;
The 5th step, the interframe light stream vector obtaining according to the 3rd step counts light stream vector histogram as video jitter another feature;
The 6th step, video jitter frequency, video jitter amplitude and light stream vector histogram three class jitter features that the 4th step and the 5th step are extracted are input to the grader training and obtain this video jitter degree.
Compared with prior art, the present invention has following beneficial effect:
The thought that the present invention adopts sparse optical flow to calculate is estimated video inter frame motion model, without any need for video priori, all applicable to most of video scene, and has higher accuracy rate.According to the degree of jitter of the video parameter of selecting video digital image stabilization method and digital image stabilization method better, improve efficiency and the effect of steady picture step.
Accompanying drawing explanation
By reading the detailed description of non-limiting example being done with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 is a kind of video jitter automatic testing method overview flow chart that the present invention proposes.
Fig. 2 is the design sketch of feature point extraction in the present invention, and wherein in figure, dot is selected characteristic point position.
Fig. 3 is characteristic pattern when light stream vector histogram divides X and Y both direction statistics in the present invention, wherein figure (a) is stable video directions X light stream vector histogram, figure (b) is stable video Y-direction light stream vector histogram, figure (c) is slight jitter video directions X light stream vector histogram, figure (d) is slight jitter video Y-direction light stream vector histogram, figure (e) is violent shake video directions X light stream vector histogram, and figure (f) is violent shake video Y-direction light stream vector histogram.
Fig. 4 is that in the present invention, video jitter detects grader recall ratio--precision ratio curve.
Fig. 5 is that application case of the present invention lists intention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.Following examples will contribute to those skilled in the art further to understand the present invention, but not limit in any form the present invention.It should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, can also make some distortion and improvement.These all belong to protection scope of the present invention.
As shown in Figure 1, the overview flow chart for one embodiment of the invention, specifically comprises:
The first step, chooses characteristic point in current video frame;
Second step, tracking and matching characteristic point in consecutive frame, obtains interframe light stream vector;
The 3rd step, the interframe light stream vector that second step is obtained carries out abnormity point removal; During abnormal light stream vector is removed, the light stream vector that phase place and amplitude and most of light stream vector are differed greatly is considered as abnormal light stream vector, has to be removed.
The 4th step, the interframe light stream vector obtaining according to the 3rd step is estimated inter frame motion model, then according to this model extraction, goes out video jitter frequency, two features of video jitter amplitude; In the estimation of inter frame motion model, inter frame motion model is translation model, uses the mean value of interframe light stream vector as the estimation of motion model.
The 5th step, the interframe light stream vector obtaining according to the 3rd step counts light stream vector histogram as video jitter feature; The histogrammic statistics of light stream vector, statistics be the light stream vector after abnormity point is got rid of, light stream vector histogram is added up all normal interframe light stream vectors in parallel.
The 6th step, video jitter frequency, video jitter amplitude and light stream vector histogram three class jitter features that the 4th step and the 5th step are extracted are input to the grader training, and obtain this video jitter degree.In this step: stable video and the artificial shake video that synthesize different jitter level of jitter level grader training set for taking.The selected standard of label of jitter level grader test set video is video jitter subjective assessment.Adopt SVMs as video jitter grade separation device.
Step based on above-mentioned, a kind of concrete implementation detail of video jitter automatic testing method is as follows:
Fig. 2 is feature point extraction schematic diagram in the present invention, and the chosen position of characteristic point should be evenly distributed in whole video pictures as far as possible, and characteristic point position is marked by dot.
When feature point tracking, the match is successful obtains after interframe light stream vector, if formula (1) is set up, thinks that video pictures exists once shake on directions X, if formula (2) is set up, thinks that video pictures exists once in the Y direction to shake.
[P(x)|
k+1-P(x)|
k]·[P(x)|
k-P(x)|
k-1]<0 (1)
[P(y)|
k+1-P(y)|
k]·[P(y)|
k-P(y)|
k-1]<0 (2)
In its Chinese style (1), first, the left side represents that on directions X, k frame is estimated to the interframe translational motion model of k+1 frame, second represents that on directions X, k-1 frame is estimated to the interframe translational motion model of k frame, in formula (2), first, the left side represents that in Y-direction, k frame is estimated to the interframe translational motion model of k+1 frame, and second represents that in Y-direction, k-1 frame is estimated to the interframe translational motion model of k frame.After having traveled through video sequence, just can obtain the frequency of video jitter.
Video jitter amplitude represents that inter frame motion model is towards the ultimate range of a direction (X positive direction, X opposite direction, Y positive direction or Y are in the other direction) cumulative movement.Video jitter amplitude will be done normalization operation, to adapt to the video pictures of different sizes.
Fig. 3 is light stream vector histogram feature figure in the embodiment of the present invention, when statistics light stream vector histogram, each light stream vector is projected to X and Y both direction takes statistics again, first take directions X histogrammic foundation as example illustrates.While adding up the histogram of directions X, be subdivided into both direction, one is the positive direction (value for just) of X, one is the opposite direction (value is for negative) of X, histogrammic step-length is 1% of video width, because the displacement of interframe light stream vector is seldom a part of, can be greater than 20% of video width, so histogram is divided into 40 grades, the both forward and reverse directions of X respectively has 20 grades.When light stream vector is when the displacement of directions X is greater than 20%, counted in the middle of last rank, from length, be 1% to 19% each own rank that step-length is 1% of video width, be greater than 19% unified calculation in a rank, the histogrammic transverse axis scope of light stream vector is from left to right followed successively by: (∞ ,-19%], (and 19% ,-18%],, (1%, 0], (0,1%], (1%, 2%] ..., (18%, 19%], (19% ,+∞) totally 40 grades.In like manner, for the statistics with histogram of Y-direction, be also same step-length and statistical method, unique different be that its step-length is 1% of video height, rather than video width 1%.Finally light stream vector histogram is done to normalization operation, the light stream vector that histogrammic height represents to be positioned at this interval accounts for the ratio of total light stream vector number.
Fig. 3 has drawn the light stream vector histogram of three videos, wherein, figure (a) is stable video directions X light stream vector histogram, figure (b) is stable video Y-direction light stream vector histogram, figure (c) is slight jitter video directions X light stream vector histogram, figure (d) is slight jitter video Y-direction light stream vector histogram, and figure (e) is violent shake video directions X light stream vector histogram, and figure (f) is violent shake video Y-direction light stream vector histogram.
Fig. 4 is that in the present invention, video jitter detects grader recall ratio--precision ratio curve.
Fig. 5 is that application case of the present invention lists intention, embodied the contribution of the present invention in steady picture process, the more perfect step of whole Video Stabilization.
From above-described embodiment, can find out, the present invention is judging whether video exists when shake without any need for priori, and has higher accuracy rate.
Above specific embodiments of the invention are described.It will be appreciated that, the present invention is not limited to above-mentioned specific implementations, and those skilled in the art can make various distortion or modification within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (7)
1. a video jitter automatic testing method, is characterized in that described method comprises the steps:
The first step, chooses characteristic point in current video frame;
Second step, tracking and matching characteristic point in consecutive frame, obtains interframe light stream vector;
The 3rd step, the interframe light stream vector that second step is obtained carries out abnormity point removal;
The 4th step, the interframe light stream vector obtaining according to the 3rd step is estimated inter frame motion model, then according to this model extraction, goes out video jitter frequency, two features of video jitter amplitude;
The 5th step, the interframe light stream vector obtaining according to the 3rd step counts light stream vector histogram as video jitter feature;
The 6th step, video jitter frequency, video jitter amplitude and light stream vector histogram three class jitter features that the 4th step and the 5th step are extracted are input to the grader training, and obtain this video jitter degree.
2. a kind of video jitter automatic testing method according to claim 1, is characterized in that, in described the 3rd step: the light stream vector that phase place and amplitude and most of light stream vector are differed larger is considered as abnormal light stream vector, has to be removed.
3. a kind of video jitter automatic testing method according to claim 1, is characterized in that, in described the 4th step: inter frame motion model is translation model, using the mean value of interframe light stream vector as estimation.
4. a kind of video jitter automatic testing method according to claim 1, is characterized in that, in described the 5th step: light stream vector histogram is added up all normal interframe light stream vectors in parallel.
5. according to a kind of video jitter automatic testing method described in claim 1-4 any one, it is characterized in that, in described the 6th step: adopt the stable video of taking and the shake video that manually synthesizes different jitter level as grader training set.
6. a kind of video jitter automatic testing method according to claim 5, is characterized in that, the selected standard of label of the test set video of described grader is video jitter subjective assessment.
7. a kind of video jitter automatic testing method according to claim 6, is characterized in that, described the 6th step adopts SVMs as grader.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410318324.XA CN104135597B (en) | 2014-07-04 | 2014-07-04 | A kind of video jitter automatic testing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410318324.XA CN104135597B (en) | 2014-07-04 | 2014-07-04 | A kind of video jitter automatic testing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104135597A true CN104135597A (en) | 2014-11-05 |
CN104135597B CN104135597B (en) | 2017-12-15 |
Family
ID=51808112
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410318324.XA Expired - Fee Related CN104135597B (en) | 2014-07-04 | 2014-07-04 | A kind of video jitter automatic testing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104135597B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105681663A (en) * | 2016-02-26 | 2016-06-15 | 北京理工大学 | Video jitter detection method based on inter-frame motion geometric smoothness |
CN105812788A (en) * | 2016-03-24 | 2016-07-27 | 北京理工大学 | Video stability quality assessment method based on interframe motion amplitude statistics |
CN106210448A (en) * | 2016-07-22 | 2016-12-07 | 恒业智能信息技术(深圳)有限公司 | A kind of video image dithering Processing for removing method |
CN106713702A (en) * | 2017-01-19 | 2017-05-24 | 博康智能信息技术有限公司 | Method and apparatus of determining video image jitter and camera device jitter |
CN108040225A (en) * | 2017-12-11 | 2018-05-15 | 梁金凤 | A kind of intelligent monitoring machine people |
CN109194878A (en) * | 2018-11-08 | 2019-01-11 | 深圳市闻耀电子科技有限公司 | Video image anti-fluttering method, device, equipment and storage medium |
CN110062222A (en) * | 2019-03-15 | 2019-07-26 | 华为技术有限公司 | A kind of evaluation method of video, terminal, server and Related product |
CN110248048A (en) * | 2019-06-21 | 2019-09-17 | 苏宁云计算有限公司 | A kind of detection method and device of video jitter |
CN110349177A (en) * | 2019-07-03 | 2019-10-18 | 广州多益网络股份有限公司 | A kind of the face key point-tracking method and system of successive frame video flowing |
CN110401796A (en) * | 2019-07-05 | 2019-11-01 | 浙江大华技术股份有限公司 | A kind of jitter compensation method and device of image collecting device |
CN110602487A (en) * | 2019-09-06 | 2019-12-20 | 高新兴科技集团股份有限公司 | Video image jitter detection method based on TSN (time delay network) |
CN111372000A (en) * | 2020-03-17 | 2020-07-03 | Oppo广东移动通信有限公司 | Video anti-shake method and apparatus, electronic device, and computer-readable storage medium |
CN113691733A (en) * | 2021-09-18 | 2021-11-23 | 北京百度网讯科技有限公司 | Video jitter detection method and device, electronic equipment and storage medium |
CN113887547A (en) * | 2021-12-08 | 2022-01-04 | 北京世纪好未来教育科技有限公司 | Key point detection method and device and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070171981A1 (en) * | 2006-01-25 | 2007-07-26 | Yingyong Qi | Projection based techniques and apparatus that generate motion vectors used for video stabilization and encoding |
CN101009021A (en) * | 2007-01-25 | 2007-08-01 | 复旦大学 | Video stabilizing method based on matching and tracking of characteristic |
CN102202164A (en) * | 2011-05-20 | 2011-09-28 | 长安大学 | Motion-estimation-based road video stabilization method |
CN102222349A (en) * | 2011-07-04 | 2011-10-19 | 江苏大学 | Prospect frame detecting method based on edge model |
US20120008051A1 (en) * | 2010-07-08 | 2012-01-12 | Gaddy William L | System and method for shot change detection in a video sequence |
CN103546726A (en) * | 2013-10-28 | 2014-01-29 | 东南大学 | Method for automatically discovering illegal land use |
CN103763461A (en) * | 2013-12-31 | 2014-04-30 | 合一网络技术(北京)有限公司 | Video jitter detection method and device |
-
2014
- 2014-07-04 CN CN201410318324.XA patent/CN104135597B/en not_active Expired - Fee Related
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070171981A1 (en) * | 2006-01-25 | 2007-07-26 | Yingyong Qi | Projection based techniques and apparatus that generate motion vectors used for video stabilization and encoding |
CN101009021A (en) * | 2007-01-25 | 2007-08-01 | 复旦大学 | Video stabilizing method based on matching and tracking of characteristic |
US20120008051A1 (en) * | 2010-07-08 | 2012-01-12 | Gaddy William L | System and method for shot change detection in a video sequence |
US20130258202A1 (en) * | 2010-07-08 | 2013-10-03 | Spinella Ip Holdings, Inc. | System and method for shot change detection in a video sequence |
CN102202164A (en) * | 2011-05-20 | 2011-09-28 | 长安大学 | Motion-estimation-based road video stabilization method |
CN102222349A (en) * | 2011-07-04 | 2011-10-19 | 江苏大学 | Prospect frame detecting method based on edge model |
CN103546726A (en) * | 2013-10-28 | 2014-01-29 | 东南大学 | Method for automatically discovering illegal land use |
CN103763461A (en) * | 2013-12-31 | 2014-04-30 | 合一网络技术(北京)有限公司 | Video jitter detection method and device |
Non-Patent Citations (5)
Title |
---|
HUI QU, ET AL: "Shaking video synthesis for video stabilization performance assessment", 《VISUAL COMMUNICATIONS AND IMAGE PROCESSING(VCIP),2013》 * |
HUI QU, ET AL: "VIdeo stabilization with L1-L2 optimization", 《IMAGE PROCESSING(ICIP),2013 20TH IEEE INTERNATIONAL CONFERENCE》 * |
宋利等: "基于运动矢量的视频去抖动算法", 《上海交通大学学报》 * |
江冬梅等: "基于方向直方图矢量的手势识别", 《信息技术与信息化》 * |
邱家涛等: "稳定运动物体视频的特征方法", 《光学精密工程》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105681663A (en) * | 2016-02-26 | 2016-06-15 | 北京理工大学 | Video jitter detection method based on inter-frame motion geometric smoothness |
CN105681663B (en) * | 2016-02-26 | 2018-06-22 | 北京理工大学 | A kind of video jitter detection method based on interframe movement geometry flatness |
CN105812788A (en) * | 2016-03-24 | 2016-07-27 | 北京理工大学 | Video stability quality assessment method based on interframe motion amplitude statistics |
CN106210448A (en) * | 2016-07-22 | 2016-12-07 | 恒业智能信息技术(深圳)有限公司 | A kind of video image dithering Processing for removing method |
CN106210448B (en) * | 2016-07-22 | 2020-08-18 | 深圳市智慧城市建设运行管理有限公司 | Video image jitter elimination processing method |
CN106713702A (en) * | 2017-01-19 | 2017-05-24 | 博康智能信息技术有限公司 | Method and apparatus of determining video image jitter and camera device jitter |
CN108040225A (en) * | 2017-12-11 | 2018-05-15 | 梁金凤 | A kind of intelligent monitoring machine people |
CN109194878A (en) * | 2018-11-08 | 2019-01-11 | 深圳市闻耀电子科技有限公司 | Video image anti-fluttering method, device, equipment and storage medium |
CN110062222A (en) * | 2019-03-15 | 2019-07-26 | 华为技术有限公司 | A kind of evaluation method of video, terminal, server and Related product |
CN110062222B (en) * | 2019-03-15 | 2021-06-29 | 华为技术有限公司 | Video evaluation method, terminal, server and related products |
CN110248048A (en) * | 2019-06-21 | 2019-09-17 | 苏宁云计算有限公司 | A kind of detection method and device of video jitter |
CN110248048B (en) * | 2019-06-21 | 2021-11-09 | 苏宁云计算有限公司 | Video jitter detection method and device |
WO2020253618A1 (en) * | 2019-06-21 | 2020-12-24 | 苏宁云计算有限公司 | Video jitter detection method and device |
CN110349177A (en) * | 2019-07-03 | 2019-10-18 | 广州多益网络股份有限公司 | A kind of the face key point-tracking method and system of successive frame video flowing |
CN110401796A (en) * | 2019-07-05 | 2019-11-01 | 浙江大华技术股份有限公司 | A kind of jitter compensation method and device of image collecting device |
CN110401796B (en) * | 2019-07-05 | 2020-09-29 | 浙江大华技术股份有限公司 | Jitter compensation method and device of image acquisition device |
WO2021004041A1 (en) * | 2019-07-05 | 2021-01-14 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for video stabilization |
CN110602487A (en) * | 2019-09-06 | 2019-12-20 | 高新兴科技集团股份有限公司 | Video image jitter detection method based on TSN (time delay network) |
CN111372000A (en) * | 2020-03-17 | 2020-07-03 | Oppo广东移动通信有限公司 | Video anti-shake method and apparatus, electronic device, and computer-readable storage medium |
CN111372000B (en) * | 2020-03-17 | 2021-08-17 | Oppo广东移动通信有限公司 | Video anti-shake method and apparatus, electronic device, and computer-readable storage medium |
CN113691733A (en) * | 2021-09-18 | 2021-11-23 | 北京百度网讯科技有限公司 | Video jitter detection method and device, electronic equipment and storage medium |
JP2022160646A (en) * | 2021-09-18 | 2022-10-19 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | Method of detecting video jitter, device, electronic apparatus, and storage medium |
CN113887547A (en) * | 2021-12-08 | 2022-01-04 | 北京世纪好未来教育科技有限公司 | Key point detection method and device and electronic equipment |
CN113887547B (en) * | 2021-12-08 | 2022-03-08 | 北京世纪好未来教育科技有限公司 | Key point detection method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN104135597B (en) | 2017-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104135597A (en) | Automatic detection method of jitter of video | |
US9905031B2 (en) | Method and related apparatus for capturing and processing image data | |
US11748894B2 (en) | Video stabilization method and apparatus and non-transitory computer-readable medium | |
KR102605747B1 (en) | Video noise removal methods, devices, and computer-readable storage media | |
CN108280386B (en) | Monitoring scene detection method and device | |
CN104867134B (en) | A kind of recognition methods for unmanned plane inspection electric power line pole tower | |
US9253402B2 (en) | Video anti-shaking method and video anti-shaking device | |
CN107742307A (en) | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method | |
CN106169173B (en) | Image interpolation method | |
JP6784130B2 (en) | Flicker detection device and method | |
WO2021012965A1 (en) | Image processing method and apparatus, mobile terminal video processing method and apparatus, device and medium | |
JP6198389B2 (en) | Image processing apparatus, image processing method, and computer program | |
KR20150031766A (en) | Method and Apparatus for Using Image Stabilization | |
CN107360435B (en) | Blockiness detection methods, block noise filtering method and device | |
CN106412441A (en) | Video anti-shake control method and terminal | |
KR101202642B1 (en) | Method and apparatus for estimating global motion using the background feature points | |
CN104378549A (en) | Snapshot method and device and terminal | |
CN104010114A (en) | Video denoising method and device | |
KR101860310B1 (en) | Method and apparatus for generating a panoramic image by using a video shot by an unmanned aerial vehicle | |
CN109688329B (en) | Anti-shake method for high-precision panoramic video | |
WO2016192467A1 (en) | Method and device for playing videos | |
JP6206732B2 (en) | Image processing apparatus and image processing method | |
Vuong et al. | Initial direction and speed decision system for auto focus based on blur detection | |
KR20130044793A (en) | Video processing apparatus and method for removing rain from video | |
CN112767446A (en) | Image tracking system for improving target tracking accuracy of infrared image tracking |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171215 |
|
CF01 | Termination of patent right due to non-payment of annual fee |