CN113938576A - Wide-angle view-based helmet video anti-shake method and system - Google Patents
Wide-angle view-based helmet video anti-shake method and system Download PDFInfo
- Publication number
- CN113938576A CN113938576A CN202111450053.XA CN202111450053A CN113938576A CN 113938576 A CN113938576 A CN 113938576A CN 202111450053 A CN202111450053 A CN 202111450053A CN 113938576 A CN113938576 A CN 113938576A
- Authority
- CN
- China
- Prior art keywords
- video
- wide
- angle view
- camera path
- video frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000033001 locomotion Effects 0.000 claims description 39
- 239000013598 vector Substances 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 238000002360 preparation method Methods 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 12
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 208000012788 shakes Diseases 0.000 description 25
- 238000005457 optimization Methods 0.000 description 7
- 230000000087 stabilizing effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 240000000136 Scabiosa atropurpurea Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a safety helmet video anti-shake method and system based on a wide-angle view. The wide-angle view is combined with the camera path curve to be applied to a high-altitude operation scene of a power transmission line, stable video frames are intercepted on the basis of the wide-angle view, even if violent vibration, light change or rotation change occurs, the video frames with large changes are indirectly filtered, and the anti-shake performance is effectively improved.
Description
Technical Field
The invention relates to the technical field of video anti-shake, in particular to a safety helmet video anti-shake method and system based on a wide-angle view.
Background
In the high-altitude operation of the power transmission line, constructors are required to wear the intelligent safety helmet, remote construction guidance and quality control can be realized, and the problem that supervision personnel cannot supervise the station in the high-altitude operation is solved. However, as the intelligent safety helmet is worn on the head of a constructor, the shot video can shake irregularly, the quality of a video picture is seriously affected, and a supervisor cannot see the measurement data in the video clearly in case of serious conditions. In order to improve the video picture quality of the intelligent safety helmet, the anti-shake processing of the video is very important. In the high-altitude operation, the light change of video shooting is large, the existing video anti-shake method based on interval gray value statistics is not suitable for the intelligent safety helmet of the high-altitude operation, and the method using four pairs of vertexes corresponding to the image as the offset calculation label does not fully consider the change generated in the image.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the invention aims to provide a safety helmet video anti-shake method and system based on a wide-angle view, which aim to solve the technical problems.
The invention is realized by the following technical scheme:
the scheme provides a wide-angle view-based helmet video anti-shake method, which comprises the following steps:
the method comprises the following steps: collecting video data and camera path data in the use process of the safety helmet;
step two: parsing the video data into video frame data;
step three: splicing according to video frame data to generate a wide-angle view operation map, and obtaining a camera path curve according to camera path data;
step four: taking a camera path curve as a path for stabilizing a video camera, and intercepting a video frame from a wide-angle view operation map;
step five: and generating and outputting a stable video based on the intercepted video frame.
The working principle of the scheme is as follows: the traditional intelligent safety helmet system has poor video image quality, the image quality effect of a video is poor along with the change of shooting light in high-altitude operation, the change of image frames in the video is not fully considered in the anti-shake treatment when the action amplitude of an operator is large, most of videos shot by people have small scene change, and shake in the shooting process also shakes around a certain central point, so that the existing anti-shake method is generally designed for small shake and is not suitable for the video shake with the premise of severe scene change in the high-altitude operation of a power transmission line, and under the conventional condition, the background in the video shakes
The method and the system for preventing the helmet video from shaking based on the wide-angle view have the advantages that the wide-angle view is obtained by splicing video frames through an image splicing technology, and then the camera path is analyzed and estimated to obtain an ideal camera path curve to regenerate a stable video. The wide-angle view is combined with the camera path curve to be applied to a high-altitude operation scene of a power transmission line, stable video frames are intercepted on the basis of the wide-angle view, even if violent vibration, light change or rotation change occurs, the video frames with large changes are indirectly filtered, and the anti-shake performance is effectively improved.
The further optimization scheme is that the camera path data acquisition method comprises the following steps:
extracting feature points of a video frame based on a harris corner detection method, tracking the position of the feature points in the current frame based on an optical flow tracking algorithm, and estimating according to motion vectors of the tracked feature points to obtain camera path data.
The further optimization scheme is that the method for acquiring the wide-angle view operation map comprises the following substeps:
carrying out image preprocessing on video frame data;
carrying out image registration on video frame data subjected to image preprocessing;
and after the image registration is finished, carrying out image fusion processing and boundary smoothing processing on the video frame data to generate a wide-angle view operation map.
The further optimization scheme is that the image preprocessing comprises the following steps: correcting image distortion and suppressing image noise, wherein the image noise suppression method comprises the following steps:
selecting a template area in the image, wherein the template area is composed of a plurality of adjacent pixels;
calculating the average value of a plurality of pixels adjacent to the template area;
and replacing the original pixel value of the template area with the mean value.
Pincushion or barrel distortion, which is caused by the limitations of optical imaging systems or electronic scanning systems, is a typical case of image distortion; image distortion can cause a great problem to image splicing and fusion, and originally, the same objects in the two images can become unmatched due to distortion, so that a great problem is brought to image registration; therefore, according to the image distortion reason, a corresponding mathematical model is established, required information is extracted from the polluted or distorted image signal, and the original appearance of the image is restored along the reverse process of image distortion; the actual restoration process is to design a filter that can compute an estimate of the true image from the distorted image, so that it approximates the true image to the maximum extent according to a predefined error criterion.
The further optimization scheme is that the image registration method comprises the following steps:
setting a search graph as S, setting a template to be registered as T, setting the size of S as M × N and the size of T as U × V; wherein M is greater than U and N is greater than V;
taking the point (i, j) as a base point in the search map S, and cutting out a partitioning pattern with the same size as T in the search map S;
traversing all base points of the whole search graph S to obtain (M-U +1) (N-V +1) block patterns;
and comparing all the block patterns with the T one by one to obtain the block pattern with the highest similarity, and matching by taking the block pattern as the optimal registration point.
Due to the special shooting scene of the safety helmet, the image quality of the video frame is usually not ideal, and some mismatching is easily caused to influence the splicing accuracy if the image is not preprocessed before the image splicing; in order to process the jittering video in real time, the image registration method is used for accelerating the algorithm, not all the block patterns can meet the requirements, and the best registration point is screened out for matching.
The further optimization scheme is that the camera path curve acquiring method comprises the following steps:
obtaining a motion vector between adjacent video frames based on the optimal registration point;
calculating the moving distance of the camera in the horizontal direction according to the motion vector of the video frame before the current video frame in the camera path data, regarding the moving distance as the projection of the motion vector between the video frames in the horizontal direction, calculating the compensated displacement in the vertical direction of the camera path according to the motion vector of the video frame before the current video frame, and drawing a camera path curve according to the moving distance of the camera in the horizontal direction and the compensated displacement in the vertical direction of the camera path.
The further optimization scheme is that the method for acquiring the compensated displacement in the vertical direction of the camera path comprises the following steps:
assigning a calculated length of K1And a calculated length of K2The short window of (2) sets the camera relative position of the first video frame as the origin of coordinates, if:
a. and when the motion vectors of all the video frames in the long window relative to the first video frame are not changed in the vertical direction, measuring the average value of the vertical components of all the motion vectors in the short window by using the vertical component of the motion vector of the current frame.
b. When the motion vectors of all the video frames in the long window are changed in the vertical direction relative to the motion vector of the first video frame, the vertical component of the motion vector of the current frame is taken as the mean value of the vertical components of all the motion vectors in the long window.
In a further preferred embodiment, the helmet using process includes a work preparation process and a work process, and the work preparation process represents a process of performing preparation work within a work range. In order to generate a more accurate wide-angle view job map, the job preparation process is also considered in the video data, so that a more accurate background basis is provided for the wide-angle view job map.
In practical application, the main direction of a shot video is generally horizontal movement, a lot of shakes exist in the power operation process, the shakes are generally vertical movement, the movement track of a camera directly obtained by neglecting the vertical direction is not consistent with the actual situation, and obvious distortion phenomenon can occur.
A further optimization scheme is that the camera path data is also used as a reference during the process of intercepting the video frames.
The scheme also provides a wide-angle view-based helmet video anti-shake system, which is applied to the helmet video anti-shake method and comprises the following steps: the device comprises an acquisition module, an analysis module, a processing module, an interception module and an output module;
the acquisition module is used for acquiring video data and camera path data in the using process of the safety helmet;
the analysis module is used for analyzing the video data into video frame data;
the processing module is used for generating a wide-angle view map according to video frame data splicing, and the processing module also obtains a camera path curve according to the camera path data;
the intercepting module is used for intercepting video frames from a wide-angle view map by taking a camera path curve as a stable video camera path;
the output module is used for generating and outputting a stable video based on the intercepted video frame.
Compared with the prior art, the invention has the following advantages and beneficial effects:
according to the safety helmet video anti-shake method and system based on the wide-angle view, video frames are spliced through an image splicing technology to obtain the wide-angle view, then the camera path is analyzed and estimated, an ideal camera path curve is obtained, and stable videos are regenerated. The wide-angle view is combined with the camera path curve to be applied to a high-altitude operation scene of a power transmission line, stable video frames are intercepted on the basis of the wide-angle view, even if violent vibration, light change or rotation change occurs, the video frames with large changes are indirectly filtered, and the anti-shake performance is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that for those skilled in the art, other related drawings can be obtained from these drawings without inventive effort. In the drawings:
FIG. 1 is a schematic flow chart of a wide-angle view-based video anti-shaking method for a safety helmet;
FIG. 2 is a schematic view of a template region;
fig. 3 is a schematic diagram of a search graph and a template to be registered.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
The embodiment provides a wide-angle view-based video anti-shake method for a safety helmet, as shown in fig. 1, comprising the following steps:
the method comprises the following steps: collecting video data and camera path data in the use process of the safety helmet;
step two: parsing the video data into video frame data;
step three: splicing according to video frame data to generate a wide-angle view operation map, and obtaining a camera path curve according to camera path data;
step four: taking a camera path curve as a path for stabilizing a video camera, and intercepting a video frame from a wide-angle view operation map;
step five: and generating and outputting a stable video based on the intercepted video frame.
The camera path data acquisition method comprises the following steps:
extracting feature points of a video frame based on a harris corner detection method, tracking the position of the feature points in the current frame based on an optical flow tracking algorithm, and estimating according to motion vectors of the tracked feature points to obtain camera path data.
The method for acquiring the wide-angle view operation map comprises the following substeps:
carrying out image preprocessing on video frame data;
carrying out image registration on video frame data subjected to image preprocessing;
and after the image registration is finished, carrying out image fusion processing and boundary smoothing processing on the video frame data to generate a wide-angle view operation map.
The image preprocessing comprises: correcting image distortion and suppressing image noise, wherein the image noise suppression method comprises the following steps:
selecting a template area in the image, wherein the template area is composed of a plurality of adjacent pixels;
calculating the average value of a plurality of pixels adjacent to the template area;
and replacing the original pixel value of the template area with the mean value.
As shown in fig. 2, the sequence number 0 is the pixel of the current template region, the sequence numbers 1 to 8 are the neighboring pixels, the average value of all the pixels neighboring the template is obtained, and the average value is assigned to the pixel of the current template region as the data basis of the subsequent processing.
The image registration method comprises the following steps:
as shown in fig. 3, let the search map be S, the template to be registered be T, the size of S be M × N, and the size of T be U × V; wherein M is greater than U and N is greater than V;
taking the point (i, j) as a base point in the search map S, and cutting out a partitioning pattern with the same size as T in the search map S;
traversing all base points of the whole search graph S to obtain (M-U +1) (N-V +1) block patterns;
and comparing all the block patterns with the T one by one to obtain the block pattern with the highest similarity, and matching by taking the block pattern as the optimal registration point.
The camera path curve acquiring method comprises the following steps:
obtaining a motion vector between adjacent video frames based on the optimal registration point;
calculating the moving distance of the camera in the horizontal direction according to the motion vector of the video frame before the current video frame in the camera path data, regarding the moving distance as the projection of the motion vector between the video frames in the horizontal direction, calculating the compensated displacement in the vertical direction of the camera path according to the motion vector of the video frame before the current video frame, and drawing a camera path curve according to the moving distance of the camera in the horizontal direction and the compensated displacement in the vertical direction of the camera path.
The method for acquiring the compensated displacement in the vertical direction of the camera path comprises the following steps:
assigning a calculated length of K1And a calculated length of K2The short window of (2) sets the camera relative position of the first video frame as the origin of coordinates, if:
a. and when the motion vectors of all the video frames in the long window relative to the first video frame are not changed in the vertical direction, measuring the average value of the vertical components of all the motion vectors in the short window by using the vertical component of the motion vector of the current frame.
b. When the motion vectors of all the video frames in the long window are changed in the vertical direction relative to the motion vector of the first video frame, the vertical component of the motion vector of the current frame is taken as the mean value of the vertical components of all the motion vectors in the long window.
The helmet using process includes a work preparation process and a work process, and the work preparation process represents a process of performing preparation work within a work range.
The camera path data also serves as a reference during the capture of video frames.
Example 2
The embodiment provides a wide-angle view-based helmet video anti-shake system, which applies the helmet video anti-shake method of the previous embodiment, and includes: the device comprises an acquisition module, an analysis module, a processing module, an interception module and an output module;
the acquisition module is used for acquiring video data and camera path data in the using process of the safety helmet;
the analysis module is used for analyzing the video data into video frame data;
the processing module is used for generating a wide-angle view map according to video frame data splicing, and the processing module also obtains a camera path curve according to the camera path data;
the intercepting module is used for intercepting a video frame from the wide-angle view map by taking a camera path curve as a path for stabilizing the video camera;
the output module is used for generating and outputting a stable video based on the intercepted video frame.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A safety helmet video anti-shake method based on wide-angle view is characterized by comprising the following steps:
the method comprises the following steps: collecting video data and camera path data in the use process of the safety helmet;
step two: parsing the video data into video frame data;
step three: splicing according to video frame data to generate a wide-angle view operation map, and obtaining a camera path curve according to camera path data;
step four: taking a camera path curve as a camera path of a stable video, and intercepting a video frame from a wide-angle view operation map;
step five: and generating and outputting a stable video based on the intercepted video frame.
2. The wide-angle view-based helmet video anti-shake method according to claim 1, wherein the camera path data obtaining method is:
extracting feature points of a video frame based on a harris corner detection method, tracking the position of the feature points in the current frame based on an optical flow tracking algorithm, and estimating according to motion vectors of the tracked feature points to obtain camera path data.
3. The wide-angle view-based helmet video anti-shake method according to claim 2, wherein the wide-angle view job map obtaining method comprises the following sub-steps:
carrying out image preprocessing on video frame data;
carrying out image registration on video frame data subjected to image preprocessing;
and performing image fusion processing and boundary smoothing processing on the video frame data subjected to image registration to generate a wide-angle view operation map.
4. The wide-angle view-based helmet video anti-shake method according to claim 3, wherein the image pre-processing comprises: correcting image distortion and suppressing image noise, wherein the image noise suppression method comprises the following steps:
selecting a template area in the image, wherein the template area is composed of a plurality of adjacent pixels;
calculating the average value of a plurality of pixels adjacent to the template area;
and replacing the original pixel value of the template area with the mean value.
5. The wide-angle view-based helmet video anti-shake method according to claim 3, wherein the image registration method is as follows:
setting a search graph as S, setting a template to be registered as T, setting the size of S as M × N and the size of T as U × V; wherein M is greater than U and N is greater than V;
taking the point (i, j) as a base point in the search map S, and cutting out a partitioning pattern with the same size as T in the search map S;
traversing all base points of the whole search graph S to obtain (M-U +1) (N-V +1) block patterns;
and comparing all the block patterns with the template T to be registered one by one to obtain the block pattern with the highest similarity, and matching by taking the block pattern as an optimal registration point.
6. The wide-angle view-based helmet video anti-shake method according to claim 5, wherein the camera path curve obtaining method is:
obtaining a motion vector between adjacent video frames based on the optimal registration point;
calculating the moving distance of the camera in the horizontal direction according to the motion vector of the video frame before the current video frame in the camera path data, regarding the moving distance as the projection of the motion vector between the video frames in the horizontal direction, calculating the compensated displacement in the vertical direction of the camera path according to the motion vector of the video frame before the current video frame, and drawing a camera path curve according to the moving distance of the camera in the horizontal direction and the compensated displacement in the vertical direction of the camera path.
7. The wide-angle view-based helmet video anti-shake method according to claim 6, wherein the compensated displacement acquisition method in the vertical direction of the camera path is as follows:
assigning a calculated length of K1And a calculated length of K2The short window of (2) sets the relative position of the camera of the video frame as the origin of coordinates, if:
a. and when the motion vectors of all the video frames in the long window relative to the first video frame are not changed in the vertical direction, measuring the average value of the vertical components of all the motion vectors in the short window by using the vertical component of the motion vector of the current frame.
b. When the motion vectors of all the video frames in the long window are changed in the vertical direction relative to the motion vector of the first video frame, the vertical component of the motion vector of the current frame is taken as the mean value of the vertical components of all the motion vectors in the long window.
8. The wide-angle view-based helmet video anti-shake method according to claim 1, wherein the helmet use procedure includes a work preparation procedure and a work procedure, the work preparation procedure representing a procedure of performing a preparation work within a work scope.
9. A wide-angle view-based helmet video anti-shake method according to claim 1, wherein the camera path data is also used as a reference during the process of capturing video frames.
10. A wide-angle view-based helmet video anti-shake system, applied to the helmet video anti-shake method of any one of claims 1 to 9, comprising: the device comprises an acquisition module, an analysis module, a processing module, an interception module and an output module;
the acquisition module is used for acquiring video data and camera path data in the using process of the safety helmet;
the analysis module is used for analyzing the video data into video frame data;
the processing module is used for generating a wide-angle view map according to video frame data splicing, and the processing module also obtains a camera path curve according to the camera path data;
the intercepting module is used for intercepting a video frame from the wide-angle view map by taking a camera path curve as a stable video camera path;
the output module is used for generating and outputting a stable video based on the intercepted video frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111450053.XA CN113938576A (en) | 2021-11-30 | 2021-11-30 | Wide-angle view-based helmet video anti-shake method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111450053.XA CN113938576A (en) | 2021-11-30 | 2021-11-30 | Wide-angle view-based helmet video anti-shake method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113938576A true CN113938576A (en) | 2022-01-14 |
Family
ID=79288784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111450053.XA Pending CN113938576A (en) | 2021-11-30 | 2021-11-30 | Wide-angle view-based helmet video anti-shake method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113938576A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120105654A1 (en) * | 2010-10-28 | 2012-05-03 | Google Inc. | Methods and Systems for Processing a Video for Stabilization and Retargeting |
| CN106331480A (en) * | 2016-08-22 | 2017-01-11 | 北京交通大学 | Video image stabilizing method based on image stitching |
| CN106878612A (en) * | 2017-01-05 | 2017-06-20 | 中国电子科技集团公司第五十四研究所 | A kind of video stabilizing method based on the optimization of online total variation |
| KR20170082945A (en) * | 2016-01-07 | 2017-07-17 | 에스케이텔레콤 주식회사 | Method and Apparatus for Stabilizing Video |
| CN110365902A (en) * | 2019-07-23 | 2019-10-22 | 湖南省湘电试研技术有限公司 | The video anti-fluttering method and system of intelligent safety helmet based on Harris Corner Detection |
-
2021
- 2021-11-30 CN CN202111450053.XA patent/CN113938576A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120105654A1 (en) * | 2010-10-28 | 2012-05-03 | Google Inc. | Methods and Systems for Processing a Video for Stabilization and Retargeting |
| KR20170082945A (en) * | 2016-01-07 | 2017-07-17 | 에스케이텔레콤 주식회사 | Method and Apparatus for Stabilizing Video |
| CN106331480A (en) * | 2016-08-22 | 2017-01-11 | 北京交通大学 | Video image stabilizing method based on image stitching |
| CN106878612A (en) * | 2017-01-05 | 2017-06-20 | 中国电子科技集团公司第五十四研究所 | A kind of video stabilizing method based on the optimization of online total variation |
| CN110365902A (en) * | 2019-07-23 | 2019-10-22 | 湖南省湘电试研技术有限公司 | The video anti-fluttering method and system of intelligent safety helmet based on Harris Corner Detection |
Non-Patent Citations (1)
| Title |
|---|
| 李龙舞: "视频防抖技术的研究", 中国优秀硕士学位论文-信息科技辑, pages 6 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10339386B2 (en) | Unusual event detection in wide-angle video (based on moving object trajectories) | |
| CN104754302B (en) | A kind of target detection tracking method based on rifle ball linked system | |
| CN103517041B (en) | Based on real time panoramic method for supervising and the device of polyphaser rotation sweep | |
| US8891625B2 (en) | Stabilization method for vibrating video frames | |
| US11037308B2 (en) | Intelligent method for viewing surveillance videos with improved efficiency | |
| US10764496B2 (en) | Fast scan-type panoramic image synthesis method and device | |
| CN102857739A (en) | Distributed panorama monitoring system and method thereof | |
| US20110074927A1 (en) | Method for determining ego-motion of moving platform and detection system | |
| WO2003098922A1 (en) | An imaging system and method for tracking the motion of an object | |
| Zhou et al. | Evunroll: Neuromorphic events based rolling shutter image correction | |
| CN114359333A (en) | Moving object extraction method and device, computer equipment and storage medium | |
| KR101396838B1 (en) | Video stabilization method and system by selection one of various motion models | |
| CN114494085A (en) | Video stream restoration method, system, electronic device and storage medium | |
| CN113643206A (en) | Cow breathing condition detection method | |
| US11044399B2 (en) | Video surveillance system | |
| CN113938576A (en) | Wide-angle view-based helmet video anti-shake method and system | |
| CN112347830A (en) | Factory epidemic prevention management method and system | |
| CN111127355A (en) | Method for finely complementing defective light flow graph and application thereof | |
| CN114594770B (en) | Inspection method for inspection robot without stopping | |
| CN111369578A (en) | Intelligent tracking method and system for holder transaction | |
| Lu et al. | Motion Detection Based On Accumulative Optical Flow and Double Background Filtering. | |
| CN114882003A (en) | Method, medium and computing device for detecting shooting pose change of camera | |
| CN115439771A (en) | Improved DSST infrared laser spot tracking method | |
| CN112767446A (en) | Image tracking system for improving target tracking accuracy of infrared image tracking | |
| CN112669207A (en) | Method for enhancing resolution of face image based on television camera |
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 |