CN112866556A - Image stabilization method and system based on gyroscope and feature point matching - Google Patents

Image stabilization method and system based on gyroscope and feature point matching Download PDF

Info

Publication number
CN112866556A
CN112866556A CN201911191686.6A CN201911191686A CN112866556A CN 112866556 A CN112866556 A CN 112866556A CN 201911191686 A CN201911191686 A CN 201911191686A CN 112866556 A CN112866556 A CN 112866556A
Authority
CN
China
Prior art keywords
image stabilization
video
video image
processing
image sequence
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.)
Pending
Application number
CN201911191686.6A
Other languages
Chinese (zh)
Inventor
隋修宝
郝亚辛
陈钱
顾国华
钱惟贤
白宏阳
路东明
于雪莲
张思凡
李悟馨
张文辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN201911191686.6A priority Critical patent/CN112866556A/en
Publication of CN112866556A publication Critical patent/CN112866556A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/68Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
    • H04N23/681Motion detection
    • H04N23/6811Motion detection based on the image signal
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/68Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
    • H04N23/681Motion detection
    • H04N23/6812Motion detection based on additional sensors, e.g. acceleration sensors
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/68Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
    • H04N23/682Vibration or motion blur correction
    • H04N23/685Vibration or motion blur correction performed by mechanical compensation

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)

Abstract

The invention discloses an image stabilizing method and system based on gyroscope and feature point matching, wherein the method comprises the following steps: acquiring a video image sequence by using video acquisition equipment, and simultaneously recording the angular speed of the video acquisition equipment by using a gyroscope; filtering the collected angular velocity data; performing primary image stabilization processing on the video image sequence based on the angular speed data after the filtering processing; further image stabilization processing is carried out on the video image sequence after the preliminary image stabilization processing by utilizing a characteristic point matching method; and splicing the video image sequence subjected to the image stabilization processing in the last step to obtain a final image-stabilized video image sequence. The system comprises an acquisition module, a preprocessing module, a primary image stabilizing module, a secondary image stabilizing module and a post-processing module so as to realize the method. The invention combines the gyroscope and the feature point matching, can realize accurate and rapid image stabilization of the infrared video sequence, and reduces the difficulty of the subsequent processing of the infrared video sequence.

Description

Image stabilization method and system based on gyroscope and feature point matching
Technical Field
The invention relates to the field of video image stabilization, in particular to an image stabilization method and system based on gyroscope and feature point matching.
Background
In recent years, with the development of science and technology and the popularization of video equipment, video is favored by more and more people, and is an important way for people to acquire and record information. People want to obtain rich and valuable information through video. Due to the particularity of infrared thermography, a clear image can be obtained even in an environment with extremely low brightness. Therefore, the infrared image can provide much convenience in night vision, security and the like.
However, during shooting, the image pickup apparatus is affected by environmental factors, and shaking occurs, causing instability and blurring of a shot video or image. This not only seriously affects people to obtain useful information from video images, but also causes great inconvenience to the subsequent processing and utilization of video images. Especially, the influence on the infrared image is more prominent. Therefore, image stabilization is a problem to be solved urgently.
Image stabilization is the mechanical processing of the camera or the reorganization of the acquired image sequence so that a stable image sequence is finally output. Image stabilization includes three modes: electronic image stabilization, namely finding a motion vector according to the obtained image sequence and then directly performing motion compensation on the image; optical image stabilization, which compensates image movement by self-adaptively adjusting an optical path through an optical component, thereby achieving an image stabilization effect; and mechanical image stabilization, namely recording the shaking condition of the camera platform through a traditional gyroscope sensor, and then performing reverse adjustment on a servo system to achieve an image stabilization effect. Compared with optical image stabilization and mechanical image stabilization, the electronic image stabilization does not need mechanical equipment, is simpler, more convenient and flexible, has high stability and precision, is more prominent on long-focus and high-resolution camera equipment, and has wide development prospect. At present, research on an electronic image stabilization algorithm mainly focuses on the aspect of visible light images, and due to the fact that gray levels of infrared images are not obvious, accurate motion vector estimation can not be carried out through the existing electronic image stabilization algorithm.
Disclosure of Invention
The invention aims to provide a method for realizing accurate image stabilization of an infrared video image.
The technical solution for realizing the purpose of the invention is as follows: an image stabilization method based on gyroscope and feature point matching comprises the following steps:
step 1, acquiring a video image sequence by using video acquisition equipment, and simultaneously recording the angular speed of the video acquisition equipment by using a gyroscope;
step 2, filtering the collected angular velocity data;
step 3, performing primary image stabilization processing on the video image sequence based on the angular velocity data after the filtering processing;
step 4, further image stabilization processing is carried out on the video image sequence after the preliminary image stabilization processing by utilizing a characteristic point matching method;
and 5, splicing the video image sequence subjected to image stabilization processing in the step 4 to obtain a final image-stabilized video image sequence.
Further, in step 3, performing preliminary image stabilization on the video image sequence based on the filtered angular velocity data specifically includes:
step 3-1, solving a rotation matrix of the video image sequence according to the angular velocity data after filtering processing, wherein the rotation matrix is a vector matrix generated based on rotation angles phi, theta and psi of the video image sequence around an x axis, a y axis and a z axis;
wherein the rotation matrix is:
Figure BDA0002293725510000021
wherein, the calculation formula of the rotation angle is as follows:
θ=ω·t
in the formula, theta is phi or theta or psi, omega is an angular velocity, and t is the frame length of the video image;
3-2, carrying out interpolation processing on the rotation matrix to obtain the rotation angle of the adjacent images;
and 3-3, performing rotation operation on the images in the video image sequence according to the rotation angle to realize primary image stabilization.
An image stabilization system based on gyroscope and feature point matching, comprising:
the acquisition module is used for acquiring a video image sequence by using video acquisition equipment and recording the angular speed of the video acquisition equipment by using a gyroscope;
the preprocessing module is used for filtering the angular velocity data acquired by the acquisition module;
the preliminary image stabilization module is used for carrying out preliminary image stabilization treatment on the video image sequence based on the angular velocity data processed by the preprocessing module;
the secondary image stabilizing module is used for further stabilizing the video image sequence processed by the primary image stabilizing module by using a characteristic point matching method;
and the post-processing module is used for splicing the video image sequence processed by the secondary image stabilizing module to obtain a final image stabilized video image sequence.
Compared with the prior art, the invention has the following remarkable advantages: 1) the MEMS gyroscope is adopted for data acquisition, and an electronic image stabilization is adopted for outputting a high-quality stable video sequence, so that the MEMS gyroscope has a cost advantage compared with the conventional mechanical image stabilization and optical image stabilization; 2) the RANSAC algorithm is adopted to correct the feature points, so that the matching precision is improved; 3) the image edges are spliced by adopting a weighted fusion method, so that the smoothness of the image edges after image stabilization is improved; 4) irregular jitter in the infrared video sequence can be effectively removed, accurate and fast image stabilization is realized, and the difficulty of subsequent processing of the infrared video sequence is reduced.
The present invention is described in further detail below with reference to the attached drawing figures.
Drawings
Fig. 1 is a flowchart of an image stabilization method based on gyroscope and feature point matching according to the present invention.
Fig. 2 is a diagram illustrating an exemplary feature point matching.
Fig. 3 is an exemplary diagram of a feature point matching result corrected using a neighbor mismatch removal algorithm.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
With reference to fig. 1, the present invention provides an image stabilization method based on gyroscope and feature point matching, which includes the following steps:
step 1, acquiring a video image sequence by using video acquisition equipment, and simultaneously recording the angular speed of the video acquisition equipment by using a gyroscope;
step 2, filtering the collected angular velocity data;
step 3, performing primary image stabilization processing on the video image sequence based on the angular speed data after the filtering processing;
step 4, further image stabilization processing is carried out on the video image sequence after the preliminary image stabilization processing by utilizing a characteristic point matching method;
and 5, splicing the video image sequence subjected to image stabilization processing in the step 4 to obtain a final image-stabilized video image sequence.
Further exemplarily, in one embodiment, the acquired angular velocity data is subjected to filtering processing in step 2, specifically, kalman filtering is adopted.
Further, in one embodiment, the step 3 performs preliminary image stabilization on the video image sequence based on the angular velocity data after the filtering processing, and specifically includes:
step 3-1, solving a rotation matrix of the video image sequence according to the angular velocity data after filtering processing, wherein the rotation matrix is a vector matrix generated based on rotation angles phi, theta and psi of the video image sequence around an x axis, a y axis and a z axis;
wherein the rotation matrix is:
Figure BDA0002293725510000041
the calculation formula of the rotation angle is as follows:
θ=ω·t
in the formula, theta is phi or theta or psi, omega is an angular velocity, and t is the frame length of the video image;
step 3-2, carrying out interpolation processing on the rotation matrix to obtain the rotation angle of the adjacent images;
and 3-3, performing rotation operation on the images in the video image sequence according to the rotation angle to realize primary image stabilization.
Further exemplarily, in one embodiment, the interpolation processing in step 3-2 specifically employs a linear interpolation method.
Further exemplarily, in one embodiment, the feature point matching method in step 4 specifically adopts a SIFT/SURF feature point matching method.
Further, in one embodiment, in the step 4, in the process of further image stabilization of the video image sequence after the preliminary image stabilization processing by using the feature point matching method, the feature points on the moving object in the video image are removed by using the doyle criterion.
Further, in one embodiment, in the step 4, in the process of further image stabilization of the video image sequence after the preliminary image stabilization processing by using the feature point matching method, a neighboring mismatching removal algorithm is used to remove mismatching points, and the specific process includes:
the vertical disparity set of all matched points after feature point matching is assumed as follows:
ΔY={Δy1,...,Δyn}
in the formula,. DELTA.yiThe vertical parallax of the ith pair of matching points is represented, i is 1,2, and n represents the logarithm of the matching points;
step 4-1, solving the proximity degree corresponding to each vertical parallax: for any Δ yiLet us assume that the k nearest neighbors with the smallest distance therefrom are Δ y'1、...、Δy'kThen Δ yiThe degree of adjacency S is as follows:
Figure BDA0002293725510000042
and 4-2, removing the matching points corresponding to the vertical parallax with the proximity greater than a preset threshold value p.
As shown in fig. 2, which is a schematic diagram of a matching result of a feature point, and fig. 3, which is a schematic diagram of a matching result of a feature point after a mismatching point is removed by using a neighbor mismatching removal method, it can be seen that the matching effect is better after the processing by using the neighbor mismatching removal method, and the calculation amount of the subsequent processing can be reduced.
Further, in one embodiment, the splicing processing in step 5 specifically adopts a weighted fusion method, which specifically includes:
carrying out weighted summation processing on gray values of overlapping areas of adjacent frame images in a video image sequence, wherein the processing formula is as follows:
f(x,y)=ω1(x,y)f1(x,y)+ω2(x,y)f2(x,y)
wherein,
Figure BDA0002293725510000051
ω2(x,y)=1-ω1(x,y)
in the formula, f (x, y) is the gray value of the pixel point (x, y) after weighted summation processing, and f1(x,y)、f2(x, y) are gray values, omega, at the pixel points (x, y) to be subjected to weighted summation processing in two adjacent frames of images respectively1(x,y)、ω2(x, y) are each f1(x,y)、f2(x, y) weight; x is the number ofiIs the abscissa, x, of the current pixel point (x, y)r、xlRespectively, the horizontal coordinates of the left and right boundaries of the overlapping area of the adjacent frame images.
The invention provides an image stabilization system based on gyroscope and feature point matching, which comprises:
the acquisition module is used for acquiring a video image sequence by using video acquisition equipment and simultaneously recording the angular speed of the video acquisition equipment by using a gyroscope;
the preprocessing module is used for filtering the angular velocity data acquired by the acquisition module;
the preliminary image stabilization module is used for carrying out preliminary image stabilization processing on the video image sequence based on the angular speed data processed by the preprocessing module;
the secondary image stabilizing module is used for further stabilizing the video image sequence processed by the primary image stabilizing module by utilizing a characteristic point matching method;
and the post-processing module is used for splicing the video image sequence processed by the secondary image stabilizing module to obtain a final image stabilized video image sequence.
Further, in one embodiment, the preliminary image stabilization module includes:
the rotation matrix calculation unit is used for calculating a rotation matrix of the video image sequence according to the angular velocity data processed by the preprocessing module, wherein the rotation matrix is a vector matrix generated based on rotation angles phi, theta and psi of the video image sequence around an x axis, a y axis and a z axis;
wherein the rotation matrix is:
Figure BDA0002293725510000061
the calculation formula of the rotation angle is as follows:
θ=ω·t
in the formula, theta is phi or theta or psi, omega is an angular velocity, and t is the frame length of the video image;
the rotation angle solving unit is used for carrying out interpolation processing on the rotation matrix to obtain the rotation angles of the adjacent images;
and the image stabilizing unit is used for performing rotation operation on the images in the video image sequence according to the rotation angle to realize preliminary image stabilization.
In conclusion, the invention combines the gyroscope and the feature point matching, can realize accurate and rapid image stabilization of the infrared video sequence, and reduces the difficulty of the subsequent processing of the infrared video sequence.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. An image stabilization method based on gyroscope and feature point matching is characterized by comprising the following steps:
step 1, acquiring a video image sequence by using video acquisition equipment, and simultaneously recording the angular speed of the video acquisition equipment by using a gyroscope;
step 2, filtering the collected angular velocity data;
step 3, performing primary image stabilization processing on the video image sequence based on the angular velocity data after the filtering processing;
step 4, further image stabilization processing is carried out on the video image sequence after the preliminary image stabilization processing by utilizing a characteristic point matching method;
and 5, splicing the video image sequence subjected to image stabilization processing in the step 4 to obtain a final image-stabilized video image sequence.
2. The image stabilization method based on the gyroscope and the feature point matching according to claim 1, characterized in that in step 2, the acquired angular velocity data is subjected to filtering processing, specifically kalman filtering.
3. The image stabilization method based on the gyroscope and the feature point matching according to claim 1, wherein the step 3 is to perform preliminary image stabilization on the video image sequence based on the angular velocity data after the filtering processing, and specifically includes:
step 3-1, solving a rotation matrix of the video image sequence according to the angular velocity data after filtering processing, wherein the rotation matrix is a vector matrix generated based on rotation angles phi, theta and psi of the video image sequence around an x axis, a y axis and a z axis;
wherein the rotation matrix is:
Figure FDA0002293725500000011
wherein, the calculation formula of the rotation angle is as follows:
θ=ω·t
in the formula, theta is phi or theta or psi, omega is an angular velocity, and t is the frame length of the video image;
3-2, carrying out interpolation processing on the rotation matrix to obtain the rotation angle of the adjacent images;
and 3-3, performing rotation operation on the images in the video image sequence according to the rotation angle to realize primary image stabilization.
4. The image stabilization method based on the gyroscope and the feature point matching according to claim 3, characterized in that the interpolation processing in step 3-2 specifically adopts a linear interpolation method.
5. The image stabilization method based on gyroscope and feature point matching according to claim 1, characterized in that the feature point matching method in step 4 specifically adopts a SIFT/SURF feature point matching method.
6. The method according to claim 1, wherein in the step 4 of further image stabilization of the video image sequence after the preliminary image stabilization by the feature point matching method, the feature points on the moving object in the video image are removed by using the doyle criterion.
7. The image stabilization method based on the gyroscope and the feature point matching according to claim 1 or 6, wherein in the process of further image stabilization of the video image sequence after the preliminary image stabilization by using the feature point matching method in the step 4, a neighbor mismatching removal algorithm is further used to remove mismatching points, and the specific process includes:
the vertical disparity set of all matched points after feature point matching is assumed as follows:
ΔY={Δy1,...,Δyn}
in the formula,. DELTA.yiThe vertical parallax of the ith pair of matching points is represented, i is 1,2, and n represents the logarithm of the matching points;
step 4-1, solving the proximity degree corresponding to each vertical parallax: for any Δ yiLet us assume that the k nearest neighbors with the smallest distance therefrom are Δ y'1、...、Δy'kThen Δ yiThe degree of adjacency S is as follows:
Figure FDA0002293725500000021
and 4-2, removing the matching points corresponding to the vertical parallax with the proximity greater than a preset threshold value p.
8. The image stabilization method based on the matching of the gyroscope and the feature points according to claim 1, wherein the stitching process in step 5 specifically adopts a weighted fusion method, and specifically includes:
carrying out weighted summation processing on gray values of overlapping areas of adjacent frame images in a video image sequence, wherein the processing formula is as follows:
f(x,y)=ω1(x,y)f1(x,y)+ω2(x,y)f2(x,y)
wherein,
Figure FDA0002293725500000022
ω2(x,y)=1-ω1(x,y)
in the formula, f (x, y) is the gray value of the pixel point (x, y) after weighted summation processing, and f1(x,y)、f2(x, y) are gray values, omega, at the pixel points (x, y) to be subjected to weighted summation processing in two adjacent frames of images respectively1(x,y)、ω2(x, y) are each f1(x,y)、f2(x, y) weight; x is the number ofiIs the abscissa, x, of the current pixel point (x, y)r、xlRespectively, the horizontal coordinates of the left and right boundaries of the overlapping area of the adjacent frame images.
9. An image stabilization system based on gyroscope and feature point matching, comprising:
the acquisition module is used for acquiring a video image sequence by using video acquisition equipment and recording the angular speed of the video acquisition equipment by using a gyroscope;
the preprocessing module is used for filtering the angular velocity data acquired by the acquisition module;
the preliminary image stabilization module is used for carrying out preliminary image stabilization treatment on the video image sequence based on the angular velocity data processed by the preprocessing module;
the secondary image stabilizing module is used for further stabilizing the video image sequence processed by the primary image stabilizing module by using a characteristic point matching method;
and the post-processing module is used for splicing the video image sequence processed by the secondary image stabilizing module to obtain a final image stabilized video image sequence.
10. The gyroscope and feature point matching based image stabilization system of claim 9, wherein the preliminary image stabilization module comprises:
the rotation matrix calculation unit is used for calculating a rotation matrix of the video image sequence according to the angular velocity data processed by the preprocessing module, wherein the rotation matrix is a vector matrix generated based on rotation angles phi, theta and psi of the video image sequence around an x axis, a y axis and a z axis;
wherein the rotation matrix is:
Figure FDA0002293725500000031
wherein, the calculation formula of the rotation angle is as follows:
θ=ω·t
in the formula, theta is phi or theta or psi, omega is an angular velocity, and t is the frame length of the video image;
the rotation angle calculating unit is used for carrying out interpolation processing on the rotation matrix to obtain the rotation angles of the adjacent images;
and the image stabilizing unit is used for performing rotation operation on the images in the video image sequence according to the rotation angle so as to realize preliminary image stabilization.
CN201911191686.6A 2019-11-28 2019-11-28 Image stabilization method and system based on gyroscope and feature point matching Pending CN112866556A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911191686.6A CN112866556A (en) 2019-11-28 2019-11-28 Image stabilization method and system based on gyroscope and feature point matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911191686.6A CN112866556A (en) 2019-11-28 2019-11-28 Image stabilization method and system based on gyroscope and feature point matching

Publications (1)

Publication Number Publication Date
CN112866556A true CN112866556A (en) 2021-05-28

Family

ID=75995605

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911191686.6A Pending CN112866556A (en) 2019-11-28 2019-11-28 Image stabilization method and system based on gyroscope and feature point matching

Country Status (1)

Country Link
CN (1) CN112866556A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114511448A (en) * 2022-04-19 2022-05-17 深圳思谋信息科技有限公司 Method, device, equipment and medium for splicing images
CN114626991A (en) * 2022-05-13 2022-06-14 深圳思谋信息科技有限公司 Image stitching method, device, equipment, medium and computer program product
CN114979489A (en) * 2022-05-30 2022-08-30 西安理工大学 Gyroscope-based heavy equipment production scene video monitoring and image stabilizing method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106534692A (en) * 2016-11-24 2017-03-22 腾讯科技(深圳)有限公司 Video image stabilization method and device
CN107241544A (en) * 2016-03-28 2017-10-10 展讯通信(天津)有限公司 Video image stabilization method, device and camera shooting terminal

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107241544A (en) * 2016-03-28 2017-10-10 展讯通信(天津)有限公司 Video image stabilization method, device and camera shooting terminal
CN106534692A (en) * 2016-11-24 2017-03-22 腾讯科技(深圳)有限公司 Video image stabilization method and device

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
吉淑娇等: "基于特征匹配的视频稳像算法", 《吉林大学学报(工学版)》 *
吴磊: "红外双目立体视觉显著目标测距技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *
赵赛等: "基于MEMS陀螺仪的电子稳像算法", 《西北大学学报(自然科学版)》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114511448A (en) * 2022-04-19 2022-05-17 深圳思谋信息科技有限公司 Method, device, equipment and medium for splicing images
CN114511448B (en) * 2022-04-19 2022-07-26 深圳思谋信息科技有限公司 Method, device, equipment and medium for splicing images
CN114626991A (en) * 2022-05-13 2022-06-14 深圳思谋信息科技有限公司 Image stitching method, device, equipment, medium and computer program product
CN114979489A (en) * 2022-05-30 2022-08-30 西安理工大学 Gyroscope-based heavy equipment production scene video monitoring and image stabilizing method and system

Similar Documents

Publication Publication Date Title
US8891625B2 (en) Stabilization method for vibrating video frames
US10506164B2 (en) Depth information obtaining method and apparatus, and image acquisition device
KR100985805B1 (en) Apparatus and method for image stabilization using adaptive Kalman filter
US8885067B2 (en) Multocular image pickup apparatus and multocular image pickup method
CN112866556A (en) Image stabilization method and system based on gyroscope and feature point matching
CN106331480B (en) Video image stabilization method based on image splicing
CN108363946B (en) Face tracking system and method based on unmanned aerial vehicle
US20090028462A1 (en) Apparatus and program for producing a panoramic image
CN106469444B (en) Rapid image fusion method for eliminating splicing gap
WO2015039067A1 (en) Method for combining multiple image fields
WO2017045326A1 (en) Photographing processing method for unmanned aerial vehicle
TW201319954A (en) Image stabilization method and image stabilization device
JP6202879B2 (en) Rolling shutter distortion correction and image stabilization processing method
WO2022086237A1 (en) Kernel-aware super resolution
WO2017012372A1 (en) Photographing control method and apparatus for terminal, and terminal
KR20180102639A (en) Image processing apparatus, image processing method, image processing program, and storage medium
CN113556464A (en) Shooting method and device and electronic equipment
CN112585644A (en) System and method for creating background blur in camera panning or movement
Hong et al. Video stabilization and rolling shutter distortion reduction
CN115546043B (en) Video processing method and related equipment thereof
CN114429191A (en) Electronic anti-shake method, system and storage medium based on deep learning
WO2020257999A1 (en) Method, apparatus and platform for image processing, and storage medium
CN114143459A (en) Video jitter elimination method suitable for large zoom camera
TW201523516A (en) Video frame stabilization method for the moving camera
Sun et al. Rolling shutter distortion removal based on curve interpolation

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210528

RJ01 Rejection of invention patent application after publication