CN105791705A - Video anti-shake method and system suitable for movable time-lapse photography and shooting terminal - Google Patents
Video anti-shake method and system suitable for movable time-lapse photography and shooting terminal Download PDFInfo
- Publication number
- CN105791705A CN105791705A CN201610357076.9A CN201610357076A CN105791705A CN 105791705 A CN105791705 A CN 105791705A CN 201610357076 A CN201610357076 A CN 201610357076A CN 105791705 A CN105791705 A CN 105791705A
- Authority
- CN
- China
- Prior art keywords
- video
- picture frame
- frame
- homography matrix
- key
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
- H04N23/6811—Motion detection based on the image signal
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a video anti-shake method and system suitable for movable time-lapse photography and a shooting terminal.According to the method, key point extracting and key point matching are conducted on image frames of video to be processed, homography matrixes between the adjacent image frames are worked out according to the result of the feature point matching, a movement locus of the video to be processed is calculated according to the homography matrixes of the adjacent image frames, key frames in the image frames of the video to be processed are extracted according to the movement locus, and smoothing is conducted on the homography matrixes of the key frames so that stable video can be obtained.Only the video image information is utilized, frame extracting and smoothing are conducted by combining the relation between the image key point information and homography, the method is independent of hardware, the algorithm robustness is high, the anti-shake effect is remarkable, and the method is especially suitable for movable time-lapse photography with large shaking and is also suitable for anti-shake processing of ordinary video.
Description
Technical field
The present invention relates to technical field of video processing, particularly a kind of video anti-fluttering method being applicable to portable time-lapse photography and the application system of the method, camera terminal.
Background technology
Portable time-lapse photography is a branch of time-lapse photography, is a kind of performance fast-changing photography maneuver of photographic subjects, has extremely strong Time Compression ability, it is possible to the change of long things is compressed in the very short time and displays.Adopt the equipment fixed cameras such as spider different from traditional time-lapse photography, portable time-lapse photography is in the process of shooting, and the capture apparatus such as camera mostly is manually hand-held, and track shot person constantly moves.Owing to the unstability of hand-held photography and the process of compression video time can cause the irregular high dither phenomenon of photographic.In order to improve the shooting effect of portable time-lapse photography, it is necessary to shooting video is carried out stabilization process.
In the video anti-fluttering method of prior art, generally by the gyro data and the vedio data that obtain mobile equipment, then estimate the motion conditions of mobile equipment according to gyro data and then vedio data compensated, cuts etc. and to process.This stabilization mode based on gyroscope is higher to the requirement of hardware, it is easy to the situations such as appearance zero is waftd, time delay, and the stabilization effect for significantly shaking is undesirable.
Summary of the invention
The present invention solves the problems referred to above, providing a kind of suitable in the portable video anti-fluttering method of time-lapse photography, system and camera terminal, it is independent of hardware mainly by video image information, algorithm robustness is higher, and the video image stabilization process for different scenes all has good effect.
For achieving the above object, the technical solution used in the present invention is:
First, the present invention provides a kind of video anti-fluttering method being applicable to portable time-lapse photography, and it comprises the following steps:
10. the picture frame of pending video is carried out key point extraction；
20. according to the key point extracted, neighbor map picture frame is carried out key point coupling；
30. the result according to described Feature Points Matching, calculate the homography matrix between described neighbor map picture frame；
40. the homography matrix according to described neighbor map picture frame, calculate the movement locus of described pending video；
50. the key frame extracted according to described movement locus in the picture frame of pending video；
60. the homography matrix of described key frame is smoothed, obtain stable video.
Preferably, in described step 10, the picture frame of pending video is carried out key point extraction, it it is each two field picture frame by traveling through pending video, and each pixel of described picture frame and neighbor pixel are carried out the comparison of gray value, and carry out the labelling of key point according to the gray scale difference value of each pixel Yu neighbor pixel.
Preferably, in described step 20, neighbor map picture frame is carried out key point coupling, farther includes:
21. calculate the histogram of gradients of current key neighborhood of a point scope, and using this histogram of gradients descriptor as current key point；
22. the descriptor according to described key point, the corresponding key point of described neighbor map picture frame is carried out the coupling of similarity.
Preferably, in described step 30, the homography matrix between described neighbor map picture frame, is the calculating by the corresponding key point matched of described neighbor map picture frame carries out linear transformation, obtaining the homography matrix between described neighbor map picture frame, computing formula is as follows:
X ,=Hx；
Wherein, x, for the set of keypoints of picture frame to be matched, x is the corresponding set of keypoints of reference image frame, and H is described homography matrix.
Preferably, in described step 40, homography matrix according to described neighbor map picture frame calculates the movement locus of described pending video, it is process, by being undertaken the homography matrix of all picture frames before current image frame being multiplied, the kinestate obtaining described current image frame, thus calculating the kinestate of each picture frame obtaining described pending video, the kinestate of each picture frame is finally fitted obtaining the movement locus of described pending video.
Preferably, in described step 50, extract the key frame in the picture frame of pending video according to described movement locus, yet further still according to the spacing distance of the accelerations degree calculating of time-lapse photography key frame to be extracted, carry out the extraction of key frame according to described movement locus and described spacing distance.
Preferably, in described step 60, the computing formula of the homography matrix of described key frame is as follows:
Wherein, h represents the homography matrix of three row three row, the index number 1,2,3 of h represents the 1st of described homography matrix the, 2,3 row, T represents the transposition of described homography matrix, x, y represent the coordinate figure of the corresponding pixel points before the affine transformation of described key frame, and x ', y ' represent the coordinate figure of the corresponding pixel points after the affine transformation of described key frame.
Preferably, in described step 60, the homography matrix of described key frame is smoothed, be by by the homography matrix after smoothing processing divided by the homography matrix before smoothing processing, obtain revising transformation matrix, and adopt this correction transformation matrix that described key frame is interpolated calculating, obtain stable video.
Secondly, the present invention provides a kind of video stabilization system being applicable to portable time-lapse photography, comprising:
Key point extraction module, for carrying out key point extraction to the picture frame of pending video；
Key point matching module, neighbor map picture frame is carried out key point coupling according to the key point extracted by it；
Homography matrix solves module, its result according to described Feature Points Matching, calculates the homography matrix between described neighbor map picture frame；
Movement locus solves module, its homography matrix according to described neighbor map picture frame, calculates the movement locus of described pending video；
Key Frame Extraction module, it extracts the key frame in the picture frame of pending video according to described movement locus；
Smoothing module, for the homography matrix of described key frame is smoothed, obtains stable video.
It addition, the present invention also provides for a kind of camera terminal, it includes the video stabilization system being applicable to portable time-lapse photography as above.
The invention has the beneficial effects as follows:
nullA kind of video anti-fluttering method being applicable to portable time-lapse photography of the present invention、System and camera terminal，It by carrying out key point extraction and key point coupling to the picture frame of pending video，Result according to described Feature Points Matching calculates the homography matrix between described neighbor map picture frame，And the movement locus of the homography matrix described pending video of calculating according to described neighbor map picture frame，Then the key frame in the picture frame of pending video is extracted according to described movement locus，It is smoothed obtaining stable video to the homography matrix of described key frame，It utilizes video image information，The key point information of combining image and homography relation carry out taking out frame and smoothing processing，It is independent of hardware，Algorithm robustness is high，Stabilization effect is notable，It is particularly well-suited to shake bigger portable time-lapse photography，And the stabilization being also applied for ordinary video processes.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the present invention, and the schematic description and description of the present invention is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the general flow chart that the present invention is applicable to the video anti-fluttering method of portable time-lapse photography；
Fig. 2 is the structural representation that the present invention is applicable to the video stabilization system of portable time-lapse photography.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention, rather than whole embodiments.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
As it is shown in figure 1, a kind of video anti-fluttering method being applicable to portable time-lapse photography of the present invention, it comprises the following steps:
10. the picture frame of pending video is carried out key point extraction；
20. according to the key point extracted, neighbor map picture frame is carried out key point coupling；
30. the result according to described Feature Points Matching, calculate the homography matrix between described neighbor map picture frame；
40. the homography matrix according to described neighbor map picture frame, calculate the movement locus of described pending video；
50. the key frame extracted according to described movement locus in the picture frame of pending video；
60. the homography matrix of described key frame is smoothed, obtain stable video.
In described step 10, the picture frame of pending video is carried out key point extraction, it it is each two field picture frame by traveling through pending video, and each pixel of described picture frame and neighbor pixel are carried out the comparison of gray value, and carry out the labelling of key point according to the gray scale difference value of each pixel Yu neighbor pixel.The extracting method of image key points can also adopt the additive method of prior art, such as can also adopt SIFT critical point detection, quickly ask for the extreme value in Laplacian space by employing laplacian image pyramid and gaussian filtering difference image.
In described step 20, neighbor map picture frame being carried out key point coupling, mainly the similarity according to the corresponding key point of neighbor map picture frame mates, and in the present embodiment, adopts following steps:
21. calculate the histogram of gradients of current key neighborhood of a point scope, and using this histogram of gradients descriptor as current key point；
22. the descriptor according to described key point, the corresponding key point of described neighbor map picture frame is carried out the coupling of similarity.
In described step 30, the homography matrix between described neighbor map picture frame, being the calculating by the corresponding key point matched of described neighbor map picture frame being carried out linear transformation, obtaining the homography matrix between described neighbor map picture frame, computing formula is as follows:
X ,=Hx；
Wherein, x, set of keypoints for picture frame to be matched, x is the corresponding set of keypoints of reference image frame, H is described homography matrix, by by the Coordinate Conversion of the corresponding key point of picture frame to be matched and reference image frame to homogeneous coordinate system, and method of least square is adopted to calculate the homography relation obtained between corresponding key point.
Or, the present invention can also adopt the calculating of nonlinear transformation to obtain the homography matrix between described neighbor map picture frame, such as by image is cut, assume the fritter cutting into 10 row 10 row, each fritter is calculated a homography matrix, the matching effect that so can make image is finer, it is possible to reach better stabilization effect, but operand is very big；Or, it is also possible to by different types of homography matrix, such as affine transformation matrix and similitude transformation matrix are weighted summation as final homography matrix, it is possible to be stabilization effect more robust, do not have big pattern distortion.
In described step 40, homography matrix according to described neighbor map picture frame calculates the movement locus of described pending video, it is process, by being undertaken the homography matrix of all picture frames before current image frame being multiplied, the kinestate obtaining described current image frame, thus calculating the kinestate of each picture frame obtaining described pending video, the kinestate of each picture frame is finally fitted obtaining the movement locus of described pending video.Homography matrix indicates that the variation relation between consecutive frame, namely next frame relative to previous frame some translations, rotate, the change of convergent-divergent, by the motion change of accumulative each frame, simulate complete movement locus.Homography matrix calculates that the process of movement locus is exactly constantly tired takes advantage of homography matrix, for instance, n-th frame image state in which to be calculated, just by the tired homography matrix taking advantage of above 1 to n.
In described step 50, the key frame in the picture frame of pending video is extracted according to described movement locus, calculate the spacing distance of key frame to be extracted yet further still according to the acceleration degree of time-lapse photography, carry out the extraction of key frame according to described movement locus and described spacing distance.Common time-lapse photography video is to carry out taking out frame according to fixing spacing distance, such as set the words accelerating 2 times, it is exactly extract an image every a frame, for video, it is simply that take out a frame, lose a frame, take out a frame, to a frame, the video ultimately produced is formed for the effect put soon in visual effect, and the taking out frame method and can cause the huge shake between consecutive frame of this simple violence.The present invention carries out the extraction of key frame according to described movement locus and described spacing distance, it is possible to obtain stable video effect.
In described step 60, the computing formula of the homography matrix of described key frame is as follows:
Wherein, h represents the homography matrix of three row three row, the index number 1,2,3 of h represents the 1st of described homography matrix the, 2,3 row, T represents the transposition of described homography matrix, such as it is originally the matrix of 1 row 3 row, subscript adds T and has reformed into the matrix of 3 row 1 row, and x, y represent the coordinate figure of the corresponding pixel points before the affine transformation of described key frame, and x ', y ' represent the coordinate figure of the corresponding pixel points after the affine transformation of described key frame.
In described step 60, the homography matrix of described key frame is smoothed, be by by the homography matrix after smoothing processing divided by the homography matrix before smoothing processing, obtain revising transformation matrix, and adopt this correction transformation matrix that described key frame is interpolated calculating, obtain stable video.
As in figure 2 it is shown, the present invention also provides for a kind of video stabilization system 100 being applicable to portable time-lapse photography, comprising:
Key point extraction module 101, for carrying out key point extraction to the picture frame of pending video；
Key point matching module 102, neighbor map picture frame is carried out key point coupling according to the key point extracted by it；
Homography matrix solves module 103, its result according to described Feature Points Matching, calculates the homography matrix between described neighbor map picture frame；
Movement locus solves module 104, its homography matrix according to described neighbor map picture frame, calculates the movement locus of described pending video；
Key Frame Extraction module 105, it extracts the key frame in the picture frame of pending video according to described movement locus；
Smoothing module 106, for the homography matrix of described key frame is smoothed, obtains stable video.
Additionally, the present invention also provides for a kind of camera terminal, this camera terminal includes the video stabilization system being applicable to portable time-lapse photography as above, wherein, it is adaptable to the video stabilization system of portable time-lapse photography can adopt the structure of Fig. 2 embodiment, and it is accordingly, the technical scheme of embodiment of the method shown in Fig. 1 can be performed, it is similar with technique effect that it realizes principle, may refer to the relevant record in above-described embodiment in detail, repeats no more herein.
Described camera terminal includes: mobile phone, digital camera or panel computer etc. are configured with the equipment of photographic head.
It should be noted that each embodiment in this specification all adopts the mode gone forward one by one to describe, what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually referring to.For system embodiment and terminal embodiment, due to itself and embodiment of the method basic simlarity, so what describe is fairly simple, relevant part illustrates referring to the part of embodiment of the method.And, in this article, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include the process of a series of key element, method, article or equipment not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.When there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, article or equipment.Additionally, one of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can be completed by hardware, can also be completed by the hardware that program carrys out instruction relevant, described program can be stored in a kind of computer-readable recording medium, storage medium mentioned above can be read only memory, disk or CD etc..
Described above illustrate and describes the preferred embodiments of the present invention, it is to be understood that the present invention is not limited to form disclosed herein, it is not to be taken as the eliminating to other embodiments, and can be used for other combinations various, amendment and environment, and in invention contemplated scope herein, can be modified by the technology of above-mentioned instruction or association area or knowledge.And the change that those skilled in the art carry out and change are without departing from the spirit and scope of the present invention, then all should in the protection domain of claims of the present invention.
Claims (10)
1. the video anti-fluttering method being applicable to portable time-lapse photography, it is characterised in that comprise the following steps:
10. the picture frame of pending video is carried out key point extraction；
20. according to the key point extracted, neighbor map picture frame is carried out key point coupling；
30. the result according to described Feature Points Matching, calculate the homography matrix between described neighbor map picture frame；
40. the homography matrix according to described neighbor map picture frame, calculate the movement locus of described pending video；
50. the key frame extracted according to described movement locus in the picture frame of pending video；
60. the homography matrix of described key frame is smoothed, obtain stable video.
2. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to claim 1, it is characterized in that: in described step 10, the picture frame of pending video is carried out key point extraction, it it is each two field picture frame by traveling through pending video, and each pixel of described picture frame and neighbor pixel are carried out the comparison of gray value, and carry out the labelling of key point according to the gray scale difference value of each pixel Yu neighbor pixel.
3. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to claim 1, it is characterised in that: in described step 20, neighbor map picture frame is carried out key point coupling, farther includes:
21. calculate the histogram of gradients of current key neighborhood of a point scope, and using this histogram of gradients descriptor as current key point；
22. the descriptor according to described key point, the corresponding key point of described neighbor map picture frame is carried out the coupling of similarity.
4. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to claim 1, it is characterized in that: in described step 30, homography matrix between described neighbor map picture frame, it is the calculating by the corresponding key point matched of described neighbor map picture frame being carried out linear transformation, obtaining the homography matrix between described neighbor map picture frame, computing formula is as follows:
X '=Hx；
Wherein, x ' is the set of keypoints of picture frame to be matched, and x is the corresponding set of keypoints of reference image frame, and H is described homography matrix.
5. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to claim 1, it is characterized in that: in described step 40, homography matrix according to described neighbor map picture frame calculates the movement locus of described pending video, it is process, by being undertaken the homography matrix of all picture frames before current image frame being multiplied, the kinestate obtaining described current image frame, thus calculating the kinestate of each picture frame obtaining described pending video, the kinestate of each picture frame is finally fitted obtaining the movement locus of described pending video.
6. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to any one of claim 1 to 5, it is characterized in that: in described step 50, the key frame in the picture frame of pending video is extracted according to described movement locus, calculate the spacing distance of key frame to be extracted yet further still according to the acceleration degree of time-lapse photography, carry out the extraction of key frame according to described movement locus and described spacing distance.
7. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to any one of claim 1 to 5, it is characterised in that: in described step 60, the computing formula of the homography matrix of described key frame is as follows:
Wherein, h represents the homography matrix of three row three row, the index number 1,2,3 of h represents the 1st of described homography matrix the, 2,3 row, T represents the transposition of described homography matrix, x, y represent the coordinate figure of the corresponding pixel points before the affine transformation of described key frame, and x ', y ' represent the coordinate figure of the corresponding pixel points after the affine transformation of described key frame.
8. a kind of video anti-fluttering method being applicable to portable time-lapse photography according to any one of claim 1 to 5, it is characterized in that: in described step 60, the homography matrix of described key frame is smoothed, be by by the homography matrix after smoothing processing divided by the homography matrix before smoothing processing, obtain revising transformation matrix, and adopt this correction transformation matrix that described key frame is interpolated calculating, obtain stable video.
9. the video stabilization system being applicable to portable time-lapse photography, it is characterised in that including:
Key point extraction module, for carrying out key point extraction to the picture frame of pending video；
Key point matching module, neighbor map picture frame is carried out key point coupling according to the key point extracted by it；
Homography matrix solves module, its result according to described Feature Points Matching, calculates the homography matrix between described neighbor map picture frame；
Movement locus solves module, its homography matrix according to described neighbor map picture frame, calculates the movement locus of described pending video；
Key Frame Extraction module, it extracts the key frame in the picture frame of pending video according to described movement locus；
Smoothing module, for the homography matrix of described key frame is smoothed, obtains stable video.
10. a camera terminal, it is characterised in that include the video stabilization system being applicable to portable time-lapse photography described in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610357076.9A CN105791705B (en) | 2016-05-26 | 2016-05-26 | Video anti-fluttering method, system and camera terminal suitable for mobile time-lapse photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610357076.9A CN105791705B (en) | 2016-05-26 | 2016-05-26 | Video anti-fluttering method, system and camera terminal suitable for mobile time-lapse photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105791705A true CN105791705A (en) | 2016-07-20 |
| CN105791705B CN105791705B (en) | 2019-06-11 |
Family
ID=56379515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610357076.9A Active CN105791705B (en) | 2016-05-26 | 2016-05-26 | Video anti-fluttering method, system and camera terminal suitable for mobile time-lapse photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105791705B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106961551A (en) * | 2017-03-23 | 2017-07-18 | 余仁集 | A kind of VR panoramic videos later stage stabilization technology |
| CN107330410A (en) * | 2017-07-03 | 2017-11-07 | 南京工程学院 | Method for detecting abnormality based on deep learning under complex environment |
| CN107809590A (en) * | 2017-11-08 | 2018-03-16 | 青岛海信移动通信技术股份有限公司 | A kind of photographic method and device |
| CN108600622A (en) * | 2018-04-12 | 2018-09-28 | 联想(北京)有限公司 | A kind of method and device of video stabilization |
| CN109089015A (en) * | 2018-09-19 | 2018-12-25 | 厦门美图之家科技有限公司 | Video stabilization display methods and device |
| CN110366848A (en) * | 2016-12-20 | 2019-10-22 | 国立大学法人东京大学 | Image processing apparatus and program |
| CN110572534A (en) * | 2019-09-19 | 2019-12-13 | 浙江大搜车软件技术有限公司 | Digital video image stabilization method, device, equipment and storage medium of panoramic image |
| CN110892731A (en) * | 2018-07-25 | 2020-03-17 | 深圳市大疆创新科技有限公司 | Video playing speed control method and system, control terminal and movable platform |
| CN112396639A (en) * | 2019-08-19 | 2021-02-23 | 虹软科技股份有限公司 | Image alignment method |
| CN113612923A (en) * | 2021-07-30 | 2021-11-05 | 重庆电子工程职业学院 | Dynamic visual effect enhancement system and control method |
| CN113689458A (en) * | 2021-10-27 | 2021-11-23 | 广州市玄武无线科技股份有限公司 | 2D shooting track path calculation method and device |
| CN114095659A (en) * | 2021-11-29 | 2022-02-25 | 厦门美图之家科技有限公司 | Video anti-shake method, device, equipment and storage medium |
| CN114257748A (en) * | 2022-01-26 | 2022-03-29 | Oppo广东移动通信有限公司 | Video anti-shake method and device, computer readable medium and electronic device |
| CN114429191A (en) * | 2022-04-02 | 2022-05-03 | 深圳深知未来智能有限公司 | Electronic anti-shake method, system and storage medium based on deep learning |
| CN115209031A (en) * | 2021-04-08 | 2022-10-18 | 北京字跳网络技术有限公司 | Video anti-shake processing method and device, electronic equipment and storage medium |
| WO2022222113A1 (en) * | 2021-04-22 | 2022-10-27 | 深圳市大疆创新科技有限公司 | Video processing method, apparatus and system, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101521740A (en) * | 2009-04-01 | 2009-09-02 | 北京航空航天大学 | Real-time athletic estimating method based on multiple dimensioned unchanged characteristic |
| CN101854465A (en) * | 2010-02-01 | 2010-10-06 | 杭州海康威视软件有限公司 | Image processing method and device based on optical flow algorithm |
| WO2013109335A1 (en) * | 2012-01-16 | 2013-07-25 | Google Inc. | Methods and systems for processing a video for stablization using dynamic crop |
| CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
| CN105141807A (en) * | 2015-09-23 | 2015-12-09 | 北京二郎神科技有限公司 | Video signal image processing method and device |
| CN105141872A (en) * | 2015-08-20 | 2015-12-09 | 成都鹰眼视觉科技有限公司 | Video image time-lapse processing method |
-
2016
- 2016-05-26 CN CN201610357076.9A patent/CN105791705B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101521740A (en) * | 2009-04-01 | 2009-09-02 | 北京航空航天大学 | Real-time athletic estimating method based on multiple dimensioned unchanged characteristic |
| CN101854465A (en) * | 2010-02-01 | 2010-10-06 | 杭州海康威视软件有限公司 | Image processing method and device based on optical flow algorithm |
| WO2013109335A1 (en) * | 2012-01-16 | 2013-07-25 | Google Inc. | Methods and systems for processing a video for stablization using dynamic crop |
| CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
| CN105141872A (en) * | 2015-08-20 | 2015-12-09 | 成都鹰眼视觉科技有限公司 | Video image time-lapse processing method |
| CN105141807A (en) * | 2015-09-23 | 2015-12-09 | 北京二郎神科技有限公司 | Video signal image processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| MICHAEL L. GLEICHER 等: "Re-Cinematography:Improving the Camerawork of Casual Video", 《ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS, AND APPLICATIONS》 * |
| 徐千昆: "高效视频稳定与内容浏览方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110366848A (en) * | 2016-12-20 | 2019-10-22 | 国立大学法人东京大学 | Image processing apparatus and program |
| CN106961551A (en) * | 2017-03-23 | 2017-07-18 | 余仁集 | A kind of VR panoramic videos later stage stabilization technology |
| CN107330410B (en) * | 2017-07-03 | 2020-06-30 | 南京工程学院 | Anomaly detection method based on deep learning in complex environment |
| CN107330410A (en) * | 2017-07-03 | 2017-11-07 | 南京工程学院 | Method for detecting abnormality based on deep learning under complex environment |
| CN107809590A (en) * | 2017-11-08 | 2018-03-16 | 青岛海信移动通信技术股份有限公司 | A kind of photographic method and device |
| CN108600622A (en) * | 2018-04-12 | 2018-09-28 | 联想(北京)有限公司 | A kind of method and device of video stabilization |
| CN108600622B (en) * | 2018-04-12 | 2021-12-24 | 联想(北京)有限公司 | Video anti-shake method and device |
| CN110892731B (en) * | 2018-07-25 | 2022-01-25 | 深圳市大疆创新科技有限公司 | Video playing speed control method and system, control terminal and movable platform |
| CN110892731A (en) * | 2018-07-25 | 2020-03-17 | 深圳市大疆创新科技有限公司 | Video playing speed control method and system, control terminal and movable platform |
| CN109089015B (en) * | 2018-09-19 | 2020-12-22 | 厦门美图之家科技有限公司 | Video anti-shake display method and device |
| CN109089015A (en) * | 2018-09-19 | 2018-12-25 | 厦门美图之家科技有限公司 | Video stabilization display methods and device |
| CN112396639A (en) * | 2019-08-19 | 2021-02-23 | 虹软科技股份有限公司 | Image alignment method |
| CN110572534A (en) * | 2019-09-19 | 2019-12-13 | 浙江大搜车软件技术有限公司 | Digital video image stabilization method, device, equipment and storage medium of panoramic image |
| CN115209031A (en) * | 2021-04-08 | 2022-10-18 | 北京字跳网络技术有限公司 | Video anti-shake processing method and device, electronic equipment and storage medium |
| CN115209031B (en) * | 2021-04-08 | 2024-03-29 | 北京字跳网络技术有限公司 | Video anti-shake processing method and device, electronic equipment and storage medium |
| WO2022222113A1 (en) * | 2021-04-22 | 2022-10-27 | 深圳市大疆创新科技有限公司 | Video processing method, apparatus and system, and storage medium |
| CN113612923A (en) * | 2021-07-30 | 2021-11-05 | 重庆电子工程职业学院 | Dynamic visual effect enhancement system and control method |
| CN113689458A (en) * | 2021-10-27 | 2021-11-23 | 广州市玄武无线科技股份有限公司 | 2D shooting track path calculation method and device |
| CN113689458B (en) * | 2021-10-27 | 2022-03-29 | 广州市玄武无线科技股份有限公司 | 2D shooting track path calculation method and device |
| CN114095659B (en) * | 2021-11-29 | 2024-01-23 | 厦门美图之家科技有限公司 | Video anti-shake method, device, equipment and storage medium |
| CN114095659A (en) * | 2021-11-29 | 2022-02-25 | 厦门美图之家科技有限公司 | Video anti-shake method, device, equipment and storage medium |
| CN114257748A (en) * | 2022-01-26 | 2022-03-29 | Oppo广东移动通信有限公司 | Video anti-shake method and device, computer readable medium and electronic device |
| CN114429191A (en) * | 2022-04-02 | 2022-05-03 | 深圳深知未来智能有限公司 | Electronic anti-shake method, system and storage medium based on deep learning |
| CN114429191B (en) * | 2022-04-02 | 2023-03-28 | 深圳深知未来智能有限公司 | Electronic anti-shake method, system and storage medium based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105791705B (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105791705A (en) | Video anti-shake method and system suitable for movable time-lapse photography and shooting terminal | |
| Uittenbogaard et al. | Privacy protection in street-view panoramas using depth and multi-view imagery | |
| CN105635588B (en) | A kind of digital image stabilization method and device | |
| US20220148297A1 (en) | Image fusion method based on fourier spectrum extraction | |
| CN107767339B (en) | Binocular stereo image splicing method | |
| CN110248115B (en) | Image processing method, device and storage medium | |
| CN106097383A (en) | A kind of method for tracking target for occlusion issue and equipment | |
| CN112995678B (en) | Video motion compensation method and device and computer equipment | |
| CN103813099A (en) | Video anti-shake method based on feature point matching | |
| CN108109121A (en) | A kind of face based on convolutional neural networks obscures quick removing method | |
| CN104506775A (en) | Image collection jitter removing method and device based on stereoscopic visual matching | |
| CN110378250B (en) | Training method and device for neural network for scene cognition and terminal equipment | |
| CN105100546A (en) | Motion estimation method and device | |
| CN105488777A (en) | System and method for generating panoramic picture in real time based on moving foreground | |
| CN111951325A (en) | Pose tracking method, pose tracking device and electronic equipment | |
| Wu et al. | Global motion estimation with iterative optimization-based independent univariate model for action recognition | |
| Yokoi et al. | Virtual camerawork for generating lecture video from high resolution images | |
| CN114429191B (en) | Electronic anti-shake method, system and storage medium based on deep learning | |
| CN116310105B (en) | Object three-dimensional reconstruction method, device, equipment and storage medium based on multiple views | |
| Li et al. | Deep online video stabilization using imu sensors | |
| CN114095780A (en) | Panoramic video editing method, device, storage medium and equipment | |
| CN111494947A (en) | Method and device for determining moving track of camera, electronic equipment and storage medium | |
| CN114222065B (en) | Image processing method, image processing apparatus, electronic device, storage medium, and program product | |
| CN109995985B (en) | Panoramic image shooting method and device based on robot and robot | |
| CN115293988A (en) | Image deblurring method and system based on deep learning |
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 |