CN109688329A - A kind of anti-fluttering method for high-precision panoramic video - Google Patents
A kind of anti-fluttering method for high-precision panoramic video Download PDFInfo
- Publication number
- CN109688329A CN109688329A CN201811584520.6A CN201811584520A CN109688329A CN 109688329 A CN109688329 A CN 109688329A CN 201811584520 A CN201811584520 A CN 201811584520A CN 109688329 A CN109688329 A CN 109688329A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- shake
- precision
- fluttering
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 12
- 230000006641 stabilisation Effects 0.000 claims description 8
- 238000011105 stabilization Methods 0.000 claims description 8
- 238000002156 mixing Methods 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 229910017435 S2 In Inorganic materials 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
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
- H04N23/6811—Motion detection based on the image signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of anti-fluttering methods for high-precision panoramic video, comprising: S1, video image input;S2, splicing fusion is carried out to the video image of input;S3, foreground extraction, shake judgement, characteristic point estimation, image processing work are carried out to spliced image;S4, panorama stablize video output.Anti-fluttering method of the present invention for high-precision panoramic video has obtained high-precision panorama and has stablized image, improved the Y-PSNR of output video, visual effect is reliable and stable by ant-shaking algorithm.
Description
Technical field
The invention belongs to the field of security video surveillance, more particularly, to a kind of stabilization side for high-precision panoramic video
Method.
Background technique
For the panoramic video monitor camera at wide area visual angle, the features such as, ultra high-definition wide with its shooting visual angle is differentiated, more
To get over the favor by client.The scene numerous for observation point, environment is complicated is applicable in very much, such as square, station, supermarket et al.
Stream aggregation, its comprehensive 360 degree advantages without dead angle monitoring can be highlighted.
It the phenomenon that since installation environment becomes increasingly complex, being influenced by wind-force and vibration, video jitter can be generated, preferably adds
Stabilization function improves the ease for use of equipment.Panoramic video monitor camera has multiple video acquisition input terminals, and structure is complicated,
Image can not be directly applicable in 360 degree of coverings, traditional electronic flutter-proof algorithm.
Summary of the invention
In view of this, the present invention is directed to propose a kind of anti-fluttering method for high-precision panoramic video, traditional to solve
Monitor camera does not have the case where electronic flutter-proof algorithm.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of anti-fluttering method for high-precision panoramic video, comprising:
S1, video image input;
S2, splicing fusion is carried out to the video image of input;
S3, foreground extraction, shake judgement, characteristic point estimation, image processing work are carried out to spliced image;
S4, panorama stablize video output.
Further, in the step S1, video image input is received multiple for more visually frequency image input modules
The video image of sensor input.
Further, in the step S2, the method for video image splicing fusion is as follows:
S201, to each sensor input image be filtered and noise reduction process;
S202, to sensor input image splice before distortion correction;
S203, since the exposure parameter of image of each sensor acquisition is not quite similar, utilize the method adjustment of Estimation of Mean
Image luminance information is exposed compensation;
S204, panoramic picture is spliced using blending algorithm.
Further, in the step S202, the method for distortion correction is as follows:
Angle point to obtain image utilizes the distortion of affine transformation correction image as characteristic point.
Further, the step S204, the characteristic point acquired according to distortion correction carry out image spelling using blending algorithm
It connects.
Further, in the step S3, the method for foreground extraction is to be divided panoramic picture by foreground extracting module
For prospect and background, the prospect that is concerned by people of panoramic picture is obtained.
The method that shake determines is the prospect and background by shake determination module according to extraction, carries out frequency domain point to image
Analysis makes the judgement that video has shake if there are periodic high fdrequency components for image;If foreground moving, background
It is moving, is then needing to pre-process background motion according to Movement consistency principle;
Characteristic point method for estimating is the characteristic point that panoramic picture is obtained by characteristic point motion estimation module, to image
Pixel carries out optical flow computation, carries out the estimation of motion vector, the path as motion compensation.
Further, in the step S3, image procossing includes shake filtering processing, and shake filtering processing is
It is carried out smoothly by shake filtering module using motion profile of the Kalman filter to image, filtering out flating causes
High fdrequency component.
Further, it also needs to handle by jitter compensation and characteristic frame replacement after the processing of shake filtering;
Jitter compensation and the method for characteristic frame replacement processing are by jitter compensation and characteristic frame replacement module according to original
Track and smoothed out desired trajectory carry out Contrary compensation to image movement vector, the video after obtaining stabilization;In this way at stabilization
Video frame after reason exists discontinuously and the case where object distortion, to discontinuous video frame, using the respective pixel of characteristic frame,
Discontinuous pixel is replaced;For there is the pixel of distortion, kept using edge extracting, feature contour, weighted average
Smooth manner eliminate distortion.
Compared with the existing technology, the anti-fluttering method of the present invention for high-precision panoramic video has the advantage that
Anti-fluttering method of the present invention for high-precision panoramic video has been obtained high-precision complete by ant-shaking algorithm
Scape stablizes image, improves the Y-PSNR of output video, and visual effect is reliable and stable.
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the anti-fluttering method flow chart that high-precision panoramic video is directed to described in the embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " etc. are used for description purposes only, it is not understood to indicate or imply phase
To importance or implicitly indicate the quantity of indicated technical characteristic.The feature for defining " first ", " second " etc. as a result, can
To explicitly or implicitly include one or more of the features.In the description of the present invention, unless otherwise indicated, " multiple "
It is meant that two or more.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood by concrete condition
Concrete meaning in the present invention.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
As shown in Figure 1, a kind of anti-fluttering method for high-precision panoramic video, comprising:
S1, video image input;
S2, splicing fusion is carried out to the video image of input;
S3, foreground extraction, shake judgement, characteristic point estimation, image processing work are carried out to spliced image;
The stable Video Output Modules of S4, panorama will synthesize stable panoramic video stream.
In the step S1, video image input is the received multiple sensor inputs of more visually frequency image input modules
Video image.
In the step S2, the method for video image splicing fusion is as follows:
S201, to each sensor input image be filtered and noise reduction process;
S202, to sensor input image splice before distortion correction;
S203, since the exposure parameter of image of each sensor acquisition is not quite similar, utilize the method adjustment of Estimation of Mean
Image luminance information is exposed compensation;
S204, panoramic picture is spliced using blending algorithm.
In the step S202, the method for distortion correction is as follows:
Angle point to obtain image utilizes the distortion of affine transformation correction image as characteristic point.
The step S204, the characteristic point acquired according to distortion correction carry out image mosaic using blending algorithm.
In the step S3, the method for foreground extraction is that panoramic picture is divided into prospect with after by foreground extracting module
Scape obtains the prospect that is concerned by people of panoramic picture.
The method that shake determines is the prospect and background by shake determination module according to extraction, carries out frequency domain point to image
Analysis makes the judgement that video has shake if there are periodic high fdrequency components for image;If foreground moving, background
It is moving, is then needing to pre-process background motion according to Movement consistency principle;
Characteristic point method for estimating is the characteristic point that panoramic picture is obtained by characteristic point motion estimation module, to image
Pixel carries out optical flow computation, carries out the estimation of motion vector, the path as motion compensation.
In the step S3, image procossing includes shake filtering processing, and shake filtering processing is to pass through shake
Filtering module carries out smoothly, filtering out high frequency division caused by flating using motion profile of the Kalman filter to image
Amount.
It also needs to handle by jitter compensation and characteristic frame replacement after shake filtering processing;Jitter compensation and characteristic frame
The method of replacement processing is by jitter compensation and characteristic frame replacement module according to initial trace and smoothed out desired trajectory, right
Image movement vector carries out Contrary compensation, the video after obtaining stabilization;In this way stabilization treated video frame exist discontinuously and
The case where object distorts, discontinuous video frame is replaced using the respective pixel of characteristic frame to discontinuous pixel;It is right
In the pixel that there is distortion, kept using edge extracting, feature contour, average weighted smooth manner eliminates distortion.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of anti-fluttering method for high-precision panoramic video characterized by comprising
S1, video image input;
S2, splicing fusion is carried out to the video image of input;
S3, foreground extraction, shake judgement, characteristic point estimation, image processing work are carried out to spliced image;
S4, panorama stablize video output.
2. the anti-fluttering method according to claim 1 for high-precision panoramic video, it is characterised in that: the step S1
In, video image input is the video image that mostly visually the received multiple sensor of frequency image input modules are inputted.
3. the anti-fluttering method according to claim 1 for high-precision panoramic video, it is characterised in that: the step S2
In, the method for video image splicing fusion is as follows:
S201, to each sensor input image be filtered and noise reduction process;
S202, to sensor input image splice before distortion correction;
S203, since the exposure parameter of image of each sensor acquisition is not quite similar, the method for utilizing Estimation of Mean adjusts image
Luminance information is exposed compensation;
S204, panoramic picture is spliced using blending algorithm.
4. the anti-fluttering method according to claim 3 for high-precision panoramic video, which is characterized in that the step S202
In, the method for distortion correction is as follows:
Angle point to obtain image utilizes the distortion of affine transformation correction image as characteristic point.
5. the anti-fluttering method according to claim 4 for high-precision panoramic video, it is characterised in that: the step
S204, the characteristic point acquired according to distortion correction carry out image mosaic using blending algorithm.
6. the anti-fluttering method according to claim 1 for high-precision panoramic video, which is characterized in that the step S3
In, the method for foreground extraction is that panoramic picture is divided into prospect and background by foreground extracting module, obtains panoramic picture
Be concerned by people prospect.
The method that shake determines is the prospect and background by shake determination module according to extraction, carries out frequency-domain analysis to image,
If there are periodic high fdrequency components for image, the judgement that video has shake is made;If foreground moving, background is also being transported
It is dynamic, then it needs to pre-process background motion according to Movement consistency principle;
Characteristic point method for estimating is the characteristic point that panoramic picture is obtained by characteristic point motion estimation module, to image pixel
Point carries out optical flow computation, carries out the estimation of motion vector, the path as motion compensation.
7. the anti-fluttering method according to claim 1 for high-precision panoramic video, it is characterised in that: the step S3
In, image procossing includes shake filtering processing, and shake filtering processing is by shake filtering module using card
Thalmann filter carries out the motion profile of image smoothly, to filter out high fdrequency component caused by flating.
8. the anti-fluttering method according to claim 7 for high-precision panoramic video, it is characterised in that: shake filtering
It also needs to handle by jitter compensation and characteristic frame replacement after processing;
Jitter compensation and the method for characteristic frame replacement processing are by jitter compensation and characteristic frame replacement module according to initial trace
With smoothed out desired trajectory, Contrary compensation is carried out to image movement vector, the video after obtaining stabilization;In this way after stabilization processing
Video frame exist discontinuously and object distortion the case where, to discontinuous video frame, using the respective pixel of characteristic frame, to not
Contiguous pixels are replaced;For there is the pixel of distortion, being kept using edge extracting, feature contour, is average weighted flat
Sliding mode eliminates distortion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811584520.6A CN109688329B (en) | 2018-12-24 | 2018-12-24 | Anti-shake method for high-precision panoramic video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811584520.6A CN109688329B (en) | 2018-12-24 | 2018-12-24 | Anti-shake method for high-precision panoramic video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109688329A true CN109688329A (en) | 2019-04-26 |
CN109688329B CN109688329B (en) | 2020-12-11 |
Family
ID=66188930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811584520.6A Active CN109688329B (en) | 2018-12-24 | 2018-12-24 | Anti-shake method for high-precision panoramic video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109688329B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110175011A (en) * | 2019-05-06 | 2019-08-27 | 长春理工大学 | A kind of full-view image seamless joint method |
CN111062881A (en) * | 2019-11-20 | 2020-04-24 | RealMe重庆移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
WO2022033344A1 (en) * | 2020-08-13 | 2022-02-17 | 华为技术有限公司 | Video stabilization method, and terminal device and computer-readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140176670A1 (en) * | 2009-12-15 | 2014-06-26 | Sony Corporation | Image capturing apparatus and image capturing method |
CN104184961A (en) * | 2013-05-22 | 2014-12-03 | 辉达公司 | Mobile device and system used for generating panoramic video |
CN104732542A (en) * | 2015-03-27 | 2015-06-24 | 安徽省道一电子科技有限公司 | Image processing method for panoramic vehicle safety system based on multi-camera self calibration |
CN105005964A (en) * | 2015-06-30 | 2015-10-28 | 南京师范大学 | Video sequence image based method for rapidly generating panorama of geographic scene |
CN107154022A (en) * | 2017-05-10 | 2017-09-12 | 北京理工大学 | A kind of dynamic panorama mosaic method suitable for trailer |
CN107274346A (en) * | 2017-06-23 | 2017-10-20 | 中国科学技术大学 | Real-time panoramic video splicing system |
CN207166600U (en) * | 2017-01-23 | 2018-03-30 | 兹曼软件技术(北京)有限公司 | A kind of panorama camera |
CN108038820A (en) * | 2017-11-14 | 2018-05-15 | 深圳岚锋创视网络科技有限公司 | A kind of method, apparatus and panorama camera for realizing bullet time shooting effect |
-
2018
- 2018-12-24 CN CN201811584520.6A patent/CN109688329B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140176670A1 (en) * | 2009-12-15 | 2014-06-26 | Sony Corporation | Image capturing apparatus and image capturing method |
CN104184961A (en) * | 2013-05-22 | 2014-12-03 | 辉达公司 | Mobile device and system used for generating panoramic video |
CN104732542A (en) * | 2015-03-27 | 2015-06-24 | 安徽省道一电子科技有限公司 | Image processing method for panoramic vehicle safety system based on multi-camera self calibration |
CN105005964A (en) * | 2015-06-30 | 2015-10-28 | 南京师范大学 | Video sequence image based method for rapidly generating panorama of geographic scene |
CN207166600U (en) * | 2017-01-23 | 2018-03-30 | 兹曼软件技术(北京)有限公司 | A kind of panorama camera |
CN107154022A (en) * | 2017-05-10 | 2017-09-12 | 北京理工大学 | A kind of dynamic panorama mosaic method suitable for trailer |
CN107274346A (en) * | 2017-06-23 | 2017-10-20 | 中国科学技术大学 | Real-time panoramic video splicing system |
CN108038820A (en) * | 2017-11-14 | 2018-05-15 | 深圳岚锋创视网络科技有限公司 | A kind of method, apparatus and panorama camera for realizing bullet time shooting effect |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110175011A (en) * | 2019-05-06 | 2019-08-27 | 长春理工大学 | A kind of full-view image seamless joint method |
CN110175011B (en) * | 2019-05-06 | 2022-06-03 | 长春理工大学 | Panoramic image seamless splicing method |
CN111062881A (en) * | 2019-11-20 | 2020-04-24 | RealMe重庆移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
WO2021098544A1 (en) * | 2019-11-20 | 2021-05-27 | RealMe重庆移动通信有限公司 | Image processing method and apparatus, storage medium and electronic device |
EP4064176A4 (en) * | 2019-11-20 | 2023-05-24 | RealMe Chongqing Mobile Telecommunications Corp., Ltd. | Image processing method and apparatus, storage medium and electronic device |
WO2022033344A1 (en) * | 2020-08-13 | 2022-02-17 | 华为技术有限公司 | Video stabilization method, and terminal device and computer-readable storage medium |
CN114079725A (en) * | 2020-08-13 | 2022-02-22 | 华为技术有限公司 | Video anti-shake method, terminal device and computer-readable storage medium |
CN114079725B (en) * | 2020-08-13 | 2023-02-07 | 华为技术有限公司 | Video anti-shake method, terminal device, and computer-readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109688329B (en) | 2020-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107292860B (en) | Image processing method and device | |
US8280194B2 (en) | Reduced hardware implementation for a two-picture depth map algorithm | |
US8368766B2 (en) | Video stabilizing method and system using dual-camera system | |
CN104144282B (en) | A kind of fast digital digital image stabilization method suitable for robot for space vision system | |
US8891625B2 (en) | Stabilization method for vibrating video frames | |
AU2017200248A1 (en) | Systems and methods for digital video stabilization via constraint-based rotation smoothing | |
EP2023596A2 (en) | Apparatus and program for producing as panoramic image | |
CN109688329A (en) | A kind of anti-fluttering method for high-precision panoramic video | |
CN107749944A (en) | A kind of image pickup method and device | |
CN105376471A (en) | Panorama shooting system based on moving platform and method | |
CN105635559B (en) | Camera control method and device for terminal | |
CN104284059A (en) | Apparatus and method for stabilizing image | |
CN107222662A (en) | A kind of electronic image stabilization method based on improved KLT and Kalman filtering | |
CN113875219B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
US9172870B2 (en) | Real-time image processing method and device enhancing the resolution of successive images | |
CN113902657A (en) | Image splicing method and device and electronic equipment | |
CN103841298A (en) | Video image stabilization method based on color constant and geometry invariant features | |
EP2680567A1 (en) | Video noise reduction | |
CN115546043B (en) | Video processing method and related equipment thereof | |
KR102003460B1 (en) | Device and Method for dewobbling | |
TW201523516A (en) | Video frame stabilization method for the moving camera | |
CN105472263A (en) | Image capture method and image capture device with use of method | |
Brzeszcz et al. | Real‐time construction and visualisation of drift‐free video mosaics from unconstrained camera motion | |
Thillainayagi | Video stabilization technique for thermal infrared Aerial surveillance | |
Zhen et al. | Multi-image motion deblurring aided by inertial sensors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |