CN113873099B - Video image stabilizing method, device and medium for power transmission channel - Google Patents
Video image stabilizing method, device and medium for power transmission channel Download PDFInfo
- Publication number
- CN113873099B CN113873099B CN202110993062.7A CN202110993062A CN113873099B CN 113873099 B CN113873099 B CN 113873099B CN 202110993062 A CN202110993062 A CN 202110993062A CN 113873099 B CN113873099 B CN 113873099B
- Authority
- CN
- China
- Prior art keywords
- transmission channel
- power transmission
- motion
- grid
- motion vector
- 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.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 132
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000000087 stabilizing effect Effects 0.000 title claims abstract description 33
- 230000033001 locomotion Effects 0.000 claims abstract description 281
- 239000013598 vector Substances 0.000 claims abstract description 157
- 230000006641 stabilisation Effects 0.000 claims abstract description 20
- 238000011105 stabilization Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000009499 grossing Methods 0.000 claims description 20
- 238000005457 optimization Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 5
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009466 transformation Effects 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
- H04N23/682—Vibration or motion blur correction
-
- 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
- H04N23/682—Vibration or motion blur correction
- H04N23/683—Vibration or motion blur correction performed by a processor, e.g. controlling the readout of an image memory
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/81—Camera processing pipelines; Components thereof for suppressing or minimising disturbance in the image signal generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N25/00—Circuitry of solid-state image sensors [SSIS]; Control thereof
- H04N25/60—Noise processing, e.g. detecting, correcting, reducing or removing noise
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The embodiment of the application discloses a video image stabilizing method, equipment and medium for a power transmission channel. Performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of characteristic points are uniformly distributed in the video images of the power transmission channel; determining a corresponding geometric area by taking the characteristic points as the centers; obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more motion vectors; and calculating to obtain smooth paths corresponding to the grid crossing points according to the motion vectors corresponding to the grid crossing points in the power transmission channel images of different frames, obtaining the motion trail of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing the video image stabilization of the power transmission channel according to the motion trail. By the method, the image stabilizing effect is improved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a video image stabilizing method, equipment and medium for a power transmission channel.
Background
When the camera is used, the camera body is often dithered due to extreme weather, accidental collision and the like, so that imaging effect is affected, the problems of instability and jitter of recorded video are caused, and particularly when a specific target needs to be tracked in a scene, a user cannot accurately position or estimate the position of the moving target, so that the position of the target in the video is unstable, and the subjective effect of the video becomes unsatisfactory.
In the case of high cost and fragile physical anti-shake devices, in order to solve this problem, it is necessary to design a video stabilization algorithm to recognize such nonsensical movements and try to achieve a stable state of the video scene position by means of compensation.
In the traditional image stabilizing system based on the characteristic track, motion blur is caused by rapid translation of a camera, long tracks are difficult to obtain in a video which is irregularly and greatly dithered, the characteristic tracks are generally sparse in space and are unevenly distributed, the characteristic tracks can end or start in any frame of the video, and finally, the image stabilizing processing effect is poor.
Disclosure of Invention
The embodiment of the application provides a video image stabilizing method, equipment and medium for a power transmission channel, which are used for solving the following technical problems: the traditional image stabilizing system based on the characteristic track has poor image stabilizing processing effect.
The embodiment of the application adopts the following technical scheme:
the embodiment of the application provides a video image stabilizing method for a power transmission channel. The method comprises the steps of performing characteristic point matching on adjacent frame video images of a power transmission channel shot by a high-voltage tower camera, and tracking characteristic points to determine motion vectors of the characteristic points, wherein a plurality of characteristic points are uniformly distributed in the video images of the power transmission channel; determining a corresponding geometric area by taking the characteristic points as the centers; obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more motion vectors; and calculating to obtain smooth paths corresponding to the grid crossing points according to the motion vectors corresponding to the grid crossing points in the power transmission channel images of different frames, obtaining the motion trail of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing the video image stabilization of the power transmission channel according to the motion trail.
According to the embodiment of the application, the geometric area corresponding to the feature points is determined, and the motion vector of the feature points is sent to the grid intersection point where the geometric area coincides with the preset regular grid. So that each grid intersection can receive the motion vectors of a plurality of surrounding feature points, thereby determining the motion vectors of the accurately derived grid intersections. In addition, in the embodiment of the application, only the grid intersection points are subjected to smooth path calculation, and compared with a dense pixel path smoothing method, the embodiment of the application can ensure accuracy and reduce calculation amount at the same time, so that the path optimization speed is improved.
In one implementation manner of the present application, according to motion vectors corresponding to grid intersections in video images of transmission channels of different frames, a smooth path of each grid intersection in a motion field is obtained by calculation, and according to the smooth path of each grid intersection, a motion track of the video images of the transmission channels is obtained, which specifically includes: according to the time sequence of shooting video images of the power transmission channels, connecting motion vectors corresponding to any grid intersection point in different power transmission channel images respectively to obtain a local motion path corresponding to any grid intersection point, and determining the local motion paths of other grid intersection points; and respectively carrying out smooth calculation on the local motion path of any grid intersection point and the local motion paths of other grid intersection points, and aggregating the calculated results into the motion trail of the video image of the power transmission channel.
In one implementation manner of the present application, the smoothing calculation is performed on the local motion path of any grid intersection and the local motion paths of the other grid intersections, which specifically includes: the motion paths corresponding to all grid intersections in the video image of the power transmission channel of the current frame are aggregated into the motion path of the whole frame image; according to the formula
Carrying out smooth calculation on the local motion path; wherein,representing the motion path of the whole frame of image, +.>For a t-frame camera motion path, P represents the camera optimal path,/-for the camera motion path>Representing the optimal path of the camera at t frames; />Representing the similarity of the optimal path and the original path; />Is a balance parameter; />The larger P is, the smoother P is, when +.>When taking 0, P is equal to the original path C; r represents the frame number within the time smoothing window, < >>Indicating that the smooth path P is at the r frame position, < > where>Representing a time smooth radius>Representing Gaussian weights, +.>Representing the optimization objective function.
In one implementation manner of the present application, feature point matching is performed on video images of adjacent frames of a power transmission channel shot by a high-voltage tower camera, and feature points are tracked to determine motion vectors of the feature points, which specifically includes: according to the formulaCalculating coordinates corresponding to the feature points between the t frame and the t-1 frame, and determining motion vectors of the feature points; wherein,the coordinates of the feature points in the t-frame image; />The coordinates of the feature points in the t-1 frame image; />The motion vector is corresponding to the feature point; t is a positive integer.
In one implementation of the present application, before calculating the smooth path of each grid intersection in the motion field, the method further includes: filtering the motion vector received by the grid intersection point through a first median filter to obtain a sparse motion field; the first median filter covers the area range corresponding to all grid crossing points; denoising the sparse motion field through a second median filter to obtain a smooth sparse motion field; the second median filter covers a region range corresponding to the geometric region; in the smoothing sparse motion field, a smoothing path of each grid intersection is calculated.
In one implementation manner of the present application, before performing feature point matching, the method further includes: dividing a video image of a power transmission channel into a plurality of small areas with preset sizes; setting different local thresholds for the small areas according to the image texture features corresponding to the small areas respectively; and screening out a plurality of characteristic points in each small area according to the local threshold value corresponding to each small area so as to uniformly distribute the characteristic points in the video image of the transmission channel.
According to the embodiment of the application, the video image of the power transmission channel is divided into a plurality of small areas, and the image can be divided according to different image texture characteristics. And secondly, setting different thresholds for each region, and determining corresponding characteristic points in each small region according to the different thresholds, so that the determined characteristic points are uniformly distributed in the whole image.
In one implementation of the present application, before determining the motion vector of the feature point, the method further includes: dividing the power transmission channel image into a plurality of sub-images; removing abnormal values in the sub-images through a random sampling coincidence algorithm; wherein the outliers include at least one or more of mismatching, motion bias caused by dynamic objects.
In an implementation manner of the present application, after obtaining a motion vector corresponding to a grid intersection point in the geometric area according to the motion vector of the feature point, the method further includes: according to all grid intersections in the current power transmission channel image, a global motion vector field is established;
according to the formula
Calculating the local motion corresponding to the grid intersection points which do not receive the feature point motion vector; wherein,is a local motion vector; />The characteristic point coordinates of the t frame image; />The characteristic point coordinates of the t-1 frame image; />Global homography estimation is performed for utilizing all the matched features;
according to the formula
Estimating the motion vector corresponding to each grid intersection point when the grid intersection point does not receive the motion vector of the corresponding feature point; wherein,local motion vectors of the feature points corresponding to the grid intersecting points; />For global movementA vector field.
The embodiment of the application provides a video image stabilizing device of a power transmission channel, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to: performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of characteristic points are uniformly distributed in the video images of the power transmission channel; determining a corresponding geometric area by taking the characteristic points as the centers; obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more motion vectors; and calculating to obtain smooth paths corresponding to the grid crossing points according to the motion vectors corresponding to the grid crossing points in the power transmission channel images of different frames, obtaining the motion trail of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing the video image stabilization of the power transmission channel according to the motion trail.
The embodiment of the application provides a nonvolatile computer storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to: performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of characteristic points are uniformly distributed in the video images of the power transmission channel; determining a corresponding geometric area by taking the characteristic points as the centers; obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more motion vectors; and calculating to obtain smooth paths corresponding to the grid crossing points according to the motion vectors corresponding to the grid crossing points in the power transmission channel images of different frames, obtaining the motion trail of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing the video image stabilization of the power transmission channel according to the motion trail.
The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect: according to the embodiment of the application, the geometric area corresponding to the feature points is determined, and the motion vector of the feature points is sent to the grid intersection point where the geometric area coincides with the preset regular grid. So that each grid intersection can receive the motion vectors of a plurality of surrounding feature points, thereby determining the motion vectors of the accurately derived grid intersections. In addition, in the embodiment of the application, only the grid intersection points are subjected to smooth path calculation, and compared with a dense pixel path smoothing method, the embodiment of the application can ensure accuracy and reduce calculation amount at the same time, so that the path optimization speed is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art. In the drawings:
fig. 1 is a flowchart of a video image stabilizing method for a power transmission channel according to an embodiment of the present application;
fig. 2 is a schematic diagram of a motion track in a video horizontal direction of a power transmission channel according to an embodiment of the present application;
fig. 3 is a schematic diagram of a smooth track of a video of a power transmission channel according to an embodiment of the present application;
fig. 4 is a schematic diagram of a transmission motion vector according to an embodiment of the present application;
fig. 5 is a schematic diagram of filtering by a first median filter according to an embodiment of the present application;
fig. 6 is a schematic diagram of denoising performed by a second median filter according to an embodiment of the present application;
fig. 7 is a flowchart of video image stabilization motion estimation and path smoothing of a power transmission channel according to an embodiment of the present application;
Fig. 8 is a schematic structural diagram of a video image stabilizing device for a power transmission channel according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a video image stabilizing method, equipment and medium for a power transmission channel.
In order to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
When the high-voltage tower camera is used, the camera body is often dithered due to extreme weather, accidental collision and the like, so that imaging effect is affected, the problems of instability and jumping of recorded video are caused, and particularly when a specific target needs to be tracked in a scene, a user cannot accurately position or estimate the position of the moving target, so that the position of the target in the video is unstable, and the subjective effect of the video becomes unsatisfactory.
In the case of high cost and fragile physical anti-shake devices, in order to solve this problem, it is necessary to design a video stabilization algorithm to recognize such nonsensical movements and try to stabilize the video scene position in a compensating manner.
The traditional image stabilizing system based on the characteristic track is mostly applied to complex irregular jitter of a handheld camera, but long tracks are difficult to obtain in video with random and large-amplitude jitter due to rapid camera translation or motion blur, the characteristic tracks are generally sparse in space and are unevenly distributed, the characteristic tracks can end or start in any frame of the video, and finally the problem that the image stabilizing processing effect of the characteristic tracks on the camera is poor is caused.
In order to solve the above problems, embodiments of the present application provide a method, an apparatus, and a medium for video stabilization of a power transmission channel. And determining a geometric area corresponding to the feature points, and transmitting the motion vector of the feature points to grid crossing points where the geometric area coincides with a preset regular grid. So that each grid intersection can receive the motion vectors of a plurality of surrounding feature points, thereby determining the motion vectors of the accurately derived grid intersections. In addition, in the embodiment of the application, only the grid intersection points are subjected to smooth path calculation, and compared with a dense pixel path smoothing method, the embodiment of the application can ensure accuracy and reduce calculation amount at the same time, so that the path optimization speed is improved.
The following describes in detail the technical solution proposed in the embodiments of the present application through the accompanying drawings.
Fig. 1 is a flowchart of a video image stabilizing method for a power transmission channel according to an embodiment of the present application. As shown in fig. 1, the video image stabilizing method for the power transmission channel comprises the following steps:
s101, carrying out feature point matching on adjacent frame video images of a power transmission channel shot by a high-voltage tower camera by using a power transmission channel video stabilizing device, and tracking the feature points to determine motion vectors of the feature points.
In one embodiment of the application, the power transmission is performed through a video image stabilizing device, and a power transmission channel video image is divided into a plurality of small areas with preset sizes. And setting different local thresholds for the small areas according to the image texture features corresponding to the small areas. And screening out a plurality of characteristic points in each small area according to the local threshold value corresponding to each small area so as to uniformly distribute the plurality of characteristic points in the video image of the power transmission channel.
Specifically, in the video image of the power transmission channel, there may be regions with different texture characteristics. For example, texture characteristics of sky regions may be relatively similar, while texture characteristics of ground regions may be relatively widely separated. Therefore, it is necessary to determine the corresponding feature points according to different texture characteristics. The image is divided into a plurality of small areas, for example, a sky area and a ground area. Since the texture characteristics of the sky area are relatively similar, a lower texture characteristic threshold value can be set, and a larger number of characteristic points can be selected. Because the texture characteristic difference of the ground area is larger, a higher texture characteristic threshold can be set to reduce the number of the selected feature points. Therefore, the number of the characteristic points of the sky area and the ground area is uniformly distributed in the video image of the whole transmission channel.
According to the embodiment of the application, the accuracy of the calculation result can be improved by extracting the feature points in an equalizing mode. In a power transmission scene, the sky area in a picture shot by a camera has large duty ratio and large depth of field change. The characteristic points provided by the traditional method are seriously unevenly distributed, and the sky area often has no effective characteristic points to calculate stable images. According to the embodiment of the application, the characteristic distribution is balanced, so that the stability of a final image stabilizing result is improved by 2.7% compared with that of a traditional method.
In one embodiment of the present application, the formula is followedAnd calculating coordinates corresponding to the feature points between the t frame and the t-1 frame, and determining the motion vector of the feature points. Wherein (1)>The coordinates of the feature points in the t-frame image; />The coordinates of the feature points in the t-1 frame image; />The motion vector is corresponding to the feature point; t is a positive integer.
Specifically, the feature points between two adjacent frames are subjected to tracking matching. Wherein FAST features may be used and tracked by KLT optical flow algorithms. The obtained position change of the same feature point in two adjacent frames of images is the motion vector of the feature point.
In the embodiment of the present application, a coordinate system is set in advance for a video image of a power transmission channel, so that coordinates of each feature point are determined according to the coordinate system, and a motion vector of each feature point is obtained. For example, the embodiment of the present application may use the intersection point of the left edge and the upper edge of the image as the origin of the coordinate system, the direction extending rightward as the abscissa axis, and the direction extending downward as the ordinate axis.
Fig. 2 is a schematic diagram of a motion track in a video horizontal direction of a power transmission channel according to an embodiment of the present application. After the motion direction between the image frames is detected, matching the images of the adjacent frames to obtain a transformation matrix between the two images, and extracting corresponding horizontal displacement, vertical displacement and rotation angle from the matrix to obtain a video image motion track. Fig. 3 is a schematic diagram of a smooth track of a video of a power transmission channel according to an embodiment of the present application. Planning a virtual camera smoothing path for the obtained video image motion track, wherein the smoothing path can be a smooth camera posture change during shooting, and is characterized by smooth shooting pictures and no scene change of severe jitter, and a curve is generally smoothed by using methods such as filtering, fitting or optimizing.
S102, the video image stabilizing device of the power transmission channel takes the characteristic points as the center to determine the corresponding geometric areas.
In one embodiment of the present application, a unified regular grid is set for a video image of a power transmission channel, and then a corresponding geometric area is set for each feature point. And determining the region where the geometric region coincides with the regular grid so as to determine the motion vector of the grid intersection point in the part of the coinciding region through the motion vector of the characteristic point.
Fig. 4 is a schematic diagram of a transmission motion vector according to an embodiment of the present application. As shown in fig. 4, feature pointsMotion vector +.>Can be calculated as +.>. Characteristic points->The grid crossing points in the vicinity should be +.>There is a similar movement. Thus, define +.>Is a central circle covering 3 x 3 grids.
In the embodiment of the present application, the geometric area corresponding to the feature points is preferably set to be a circle covering 3×3 meshes. In the application, the shape and size of the geometric area may be set according to the actual situation, which is not limited in the present application.
And S103, obtaining a motion vector corresponding to the grid crossing points in the geometric area according to the motion vector of the feature points.
In one embodiment of the present application, the power transmission channel image is divided into a plurality of sub-images before determining the motion vector of the feature point. And removing abnormal values in the sub-images through a random sampling coincidence algorithm. Wherein the outliers include at least one or more of mismatching, motion bias caused by dynamic objects.
Specifically, the image can be divided into sub-images of 4×4, and the outlier can be removed by local homography fitting by using a random sampling coincidence algorithm. Large motion deviations due to mismatching or dynamic objects can be filtered out, and only changes due to depth changes or translational jitter are calculated.
In one embodiment of the present application, a 16 x 16 preset regular grid may be used for each frame of the power transmission channel video image. The geometric area corresponding to the feature point contains a plurality of grid crossing points, and the grid crossing points near the feature point have similar motion with the feature point. Thus, the motion vector of the feature point is sent to the grid intersection in the geometric region. And determining the motion vector of each grid intersection point through the motion vector received by the grid intersection point, and further obtaining the motion field of the video image of the power transmission channel according to the motion vector of each grid intersection point.
As shown in fig. 4 b, the circle center of the circular area formed by the broken lines is the position of the feature point, and the direction indicated by the arrow is the motion vector of the feature point. Grid intersections within the circular area are determined and the motion vector is sent to the grid intersections within the circular area. As can be seen from the lower image in fig. b, each grid intersection within the circular area receives a motion vector of the feature point and each grid intersection has the same arrow pointing as the feature point.
In one embodiment of the present application, the motion vectors received by the grid intersections are filtered by a first median filter to obtain a sparse motion field. The first median filter covers the area range corresponding to all grid crossing points. Denoising the sparse motion field through a second median filter to obtain a smooth sparse motion field. Wherein the second median filter covers a region range corresponding to the geometric region. In the smoothing sparse motion field, a smoothing path of each grid intersection is calculated.
Specifically, a sparse motion field is obtained after applying the first median filter to all the intersections. Fig. 5 is a schematic diagram of filtering by a first median filter according to an embodiment of the present application, as shown in fig. 5. A grid intersection may obtain motion vectors for a plurality of feature points, and there may be some differences between the motion vectors. A sparse motion field is obtained by means of a first median filter. The sparsity allows the motion estimation calculation of spatial variations to be light.
Specifically, noise may be present on the motion field due to feature matching errors, object dynamics, etc. Fig. 6 is a schematic diagram of denoising performed by the second median filter according to the embodiment of the present application. As shown in the left image of fig. 6, the white arrows in the figure are noise due to a matching error or other reasons. As shown in the right image of fig. 6, the noise is removed by a second median filter, resulting in a spatially smooth sparse motion field. Wherein each second median filter covers 3 x 3 cells.
In one embodiment of the present application, after obtaining a motion vector corresponding to grid intersections in the geometric area according to the motion vector of the feature point, a global motion vector field is established according to all grid intersections in the current power transmission channel image.
According to the formula
Calculating the local motion vector corresponding to the grid intersection point which does not receive the feature point motion vector; wherein,is a local motion vector; />The characteristic point coordinates of the t frame image; />The characteristic point coordinates of the t-1 frame image; />Global homography estimation is performed for utilizing all the matched features.
According to the formula
Estimating the motion vector corresponding to each grid intersection point when the grid intersection point does not receive the motion vector of the corresponding feature point; wherein,local motion vectors of the feature points corresponding to the grid intersecting points; />Is a global motion vector field.
Specifically, there is a problem that there is no corresponding feature point at an individual mesh intersection, that is, a motion vector without a feature point transmits a motion vector to the mesh intersection, due to matching of images. Therefore, the motion vector cannot be determined for a few grid intersections. In order to ensure that the motion fields corresponding to the grid intersections involved in the calculation are evenly distributed, the motion fields of the grid intersections need to be estimated. At this point, a local motion field can be derived from the globally established motion vector field, and the motion vector at the grid intersection is derived from the local motion field estimate. Thereby ensuring that all grid intersections have corresponding motion fields.
S104, the video image stabilizing device of the power transmission channel calculates to obtain smooth paths corresponding to the grid crossing points according to the motion vectors corresponding to the grid crossing points in the power transmission channel images of different frames, obtains the motion trail of the video image of the power transmission channel according to the smooth paths corresponding to the grid crossing points, and realizes the video image stabilizing of the power transmission channel according to the motion trail.
In one embodiment of the application, according to the time sequence of shooting video images of the power transmission channels, connecting motion vectors corresponding to any grid intersection point in different power transmission channel images respectively to obtain a local motion path corresponding to any grid intersection point, and determining the local motion paths of other grid intersection points. And respectively carrying out smooth calculation on the local motion path of any grid intersection point and the local motion paths of other grid intersection points, and aggregating the calculated results into the motion trail of the video image of the power transmission channel.
Specifically, a single grid intersection motion path is first used as a local camera motion path, and all grid intersection motion paths of the current frame are further aggregated into a camera motion path of the whole frame image. In order to achieve the image stabilizing effect, the path is smoothed through balancing the path smoothness and the similarity with the original path, an optimal path is obtained, and finally smoothing calculation is carried out on each grid intersection point movement path.
In one embodiment of the application, the motion paths corresponding to all grid intersections in the video image of the power transmission channel of the current frame are aggregated into a motion path of the video camera of the whole frame.
According to the formula
Carrying out smooth calculation on the local motion path;
wherein,camera motion path representing whole frame image, +.>For a t-frame camera motion path, P represents the camera optimal path,/-for the camera motion path>Representing the optimal path of the camera at t frames; />Representing the similarity of the optimal path and the original path;is a balance parameter; />The larger P is, the smoother P is, when +.>When taking 0, P is equal to the original path C; r represents the frame number within the time smoothing window, < >>Indicating that the smooth path P is at the r frame position, < > where>Representing a time smooth radius>The gaussian weight is represented by the number of points,representing the optimization objective function.
Specifically, with a single cross point motion path as a local camera motion path, all cross point motion paths of the current frame may be aggregated into a camera motion path C of the entire frame image. In order to achieve the image stabilizing effect, the path C is smoothed and an optimal path P is obtained by balancing the path smoothness and the similarity with the original path.
It should be noted that in the embodiments of the present application, the following description relates to The minimization problem of the function can be solved using a linear solver based on jacobian iterative method.
Because motion estimation itself has strong spatial correlation, embodiments of the present application do not require additional spatial constraints in the smoothing of motion. In addition, in the embodiment of the application, in the process of smoothing each grid intersection point motion path, the smooth intersection point motion paths are calculated in parallel through multithreading, so that the calculation time is further shortened. The balance parameter adjustment flexibility in the traditional algorithm is low, and the smooth effect under different application scenes is difficult to meet. Experimental comparison shows that the independent grid cross point path optimization parallelization method provided by the method has 7-10 times of improvement compared with the traditional method in path optimization speed.
Fig. 7 is a flowchart of video image stabilization motion estimation and path smoothing of a power transmission channel according to an embodiment of the present application. As shown in fig. 7, the video image stabilization motion estimation and path smoothing include the following steps:
in one embodiment of the application, the feature points are matched and the motion vectors of the feature points are determined by optical flow tracking.
Specifically, the transmission channel video image is divided into a plurality of small areas of a preset size. And setting different local thresholds for the small areas according to the image texture features corresponding to the small areas. And screening out a plurality of characteristic points in each small area according to the local threshold value corresponding to each small area so as to uniformly distribute the plurality of characteristic points in the video image of the power transmission channel. And carrying out tracking matching on the characteristic points between two adjacent frames. Wherein FAST features may be used and tracked by KLT optical flow algorithms. The obtained position change of the same feature point in two adjacent frames of images is the motion vector of the feature point
In one embodiment of the present application, the motion vector of the feature point is transmitted to the intersection of the preset mesh.
Specifically, for the power transmission channel video image of each frame, a 16×16 grid may be used. The geometric area corresponding to the feature point contains a plurality of grid crossing points, and the grid crossing points near the feature point have similar motion with the feature point. Thus, the motion vector of the feature point is sent to the grid intersection in the geometric region. And determining the motion vector of each grid intersection point through the motion vector received by the grid intersection point, and further obtaining the motion field of the video image of the power transmission channel according to the motion vector of each grid intersection point.
In one embodiment of the present application, the motion vectors of the grid intersections are filtered by a stop filter.
Specifically, the motion vector received by the grid intersection is filtered through a first median filter, so that a sparse motion field is obtained. The first median filter covers the area range corresponding to all grid crossing points. Denoising the sparse motion field through a second median filter to obtain a smooth sparse motion field. Wherein the second median filter covers a region range corresponding to the geometric region.
In one embodiment of the present application, the filtered grid intersections are formed into a smooth sparse motion field.
In one embodiment of the application, the smooth paths are independently solved for each grid intersection to achieve video stabilization of the power transmission channel.
According to the time sequence of shooting the video images of the power transmission channels, connecting the motion vectors corresponding to any grid intersection point in different power transmission channel images respectively to obtain a local motion path corresponding to any grid intersection point, and determining the local motion paths of other grid intersection points. And respectively carrying out smooth calculation on the local motion path of any grid intersection point and the local motion paths of other grid intersection points, and aggregating the calculated results into the motion trail of the video image of the power transmission channel.
Fig. 8 is a schematic structural diagram of a video image stabilizing device for a power transmission channel according to an embodiment of the present application. As shown in fig. 8, the power transmission channel video image stabilizing apparatus includes:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
Performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of the characteristic points are uniformly distributed in the video images of the power transmission channel;
determining a corresponding geometric area by taking the characteristic points as the centers;
obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more of the motion vectors;
and calculating to obtain a smooth path corresponding to each grid intersection point according to the motion vector corresponding to each grid intersection point in the power transmission channel image of different frames, obtaining a motion track of the power transmission channel video image according to the smooth path corresponding to each grid intersection point, and realizing the video image stabilization of the power transmission channel according to the motion track.
Embodiments of the present application also include a non-volatile computer storage medium storing computer-executable instructions configured to:
performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of the characteristic points are uniformly distributed in the video images of the power transmission channel;
Determining a corresponding geometric area by taking the characteristic points as the centers;
obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more of the motion vectors;
and calculating to obtain a smooth path corresponding to each grid intersection point according to the motion vector corresponding to each grid intersection point in the power transmission channel image of different frames, obtaining a motion track of the power transmission channel video image according to the smooth path corresponding to each grid intersection point, and realizing the video image stabilization of the power transmission channel according to the motion track.
All embodiments in the application are described in a progressive manner, and identical and similar parts of all embodiments are mutually referred, so that each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the embodiments of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the claims of the present application.
Claims (9)
1. The video image stabilizing method for the power transmission channel is characterized by comprising the following steps of:
performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of the characteristic points are uniformly distributed in the video images of the power transmission channel;
determining a corresponding geometric area by taking the characteristic points as the centers;
obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more of the motion vectors;
calculating to obtain smooth paths corresponding to grid crossing points according to motion vectors corresponding to the grid crossing points in different frames of power transmission channel images, obtaining motion tracks of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing power transmission channel video image stabilization according to the motion tracks;
After obtaining the motion vector corresponding to the grid intersection point in the geometric area according to the motion vector of the feature point, the method further comprises:
according to all grid intersections in the current power transmission channel image, a global motion vector field is established;
according to the formula
Calculating the local motion vector corresponding to the grid intersection point which does not receive the feature point motion vector; wherein,is a local motion vector; />The characteristic point coordinates of the t frame image; />The characteristic point coordinates of the t-1 frame image; />Global homography estimation is performed for utilizing all the matched features;
according to the formula
Estimating the motion vector corresponding to each grid intersection point when the grid intersection point does not receive the motion vector of the corresponding feature point; wherein,local motion vectors of the feature points corresponding to the grid intersecting points; />Is a global motion vector field.
2. The method for stabilizing video image of transmission channel according to claim 1, wherein the calculating to obtain the smooth path corresponding to each grid intersection according to the motion vector corresponding to each grid intersection in the video image of transmission channel of different frames, and obtaining the motion track of the video image of transmission channel according to the smooth path corresponding to each grid intersection specifically comprises:
According to the time sequence of shooting the video images of the power transmission channels, connecting motion vectors corresponding to any grid intersection in different power transmission channel images respectively to obtain local motion paths corresponding to any grid intersection, and determining the local motion paths of other grid intersections;
and respectively carrying out smooth calculation on the local motion path of any grid intersection point and the local motion paths of other grid intersection points, and aggregating the calculated results into the motion trail of the video image of the power transmission channel.
3. The video image stabilizing method of the power transmission channel according to claim 2, wherein the smoothing calculation is performed on the local motion path of any grid intersection and the local motion paths of the rest grid intersections, respectively, specifically including:
the motion paths corresponding to all grid intersections in the video image of the power transmission channel of the current frame are aggregated into the motion path of the whole frame image;
according to the formula
Carrying out smooth calculation on the local motion path;
wherein,representing the motion path of the whole frame of image, +.>For a camera motion path of t frames, P represents the camera optimal path,representing the optimal path of the camera at t frames; / >Representing the similarity of the optimal path and the original path;representing temporal smoothness; />Is a balance parameter; />The larger P is, the smoother P is, when +.>When taking 0, P is equal to the original path C; r represents the frame number within the time smoothing window, < >>Indicating that the smooth path P is at the r frame position, < > where>Representing a time smooth radius>Representing Gaussian weights, +.>Representing the optimization objective function.
4. The method for stabilizing video image of power transmission channel according to claim 1, wherein said matching feature points of adjacent frame video images of power transmission channel shot by high voltage tower camera and tracking said feature points to determine motion vector of said feature points comprises:
according to the formulaCalculating coordinates corresponding to the feature points between the t frame and the t-1 frame, and determining motion vectors of the feature points;
wherein,the coordinates of the feature points in the t-frame image; />The coordinates of the feature points in the t-1 frame image; />A motion vector corresponding to the characteristic point;t is a positive integer.
5. The method for video stabilization of transmission channels according to claim 1, wherein before the calculating obtains the smooth paths of the grid intersections, the method further comprises:
Filtering the motion vector received by the grid intersection point through a first median filter to obtain a sparse motion field; the first median filter covers all the area ranges corresponding to the grid intersections;
denoising the sparse motion field through a second median filter to obtain a smooth sparse motion field; wherein the second median filter covers a region range corresponding to the geometric region;
in the smooth sparse motion field, a smooth path of each grid intersection is calculated.
6. The method for video stabilization of a power transmission channel according to claim 1, wherein before the feature point matching, the method further comprises:
dividing the video image of the power transmission channel into a plurality of small areas with preset sizes;
setting different local thresholds for the small areas according to the image texture features corresponding to the small areas respectively;
and screening out a plurality of characteristic points in each small area according to the local threshold value corresponding to each small area so as to uniformly distribute the characteristic points in the video image of the power transmission channel.
7. The method for video stabilization of a transmission channel according to claim 1, wherein before determining the motion vector of the feature point, the method further comprises:
Dividing the power transmission channel image into a plurality of sub-images;
removing abnormal values in the sub-images through a random sampling coincidence algorithm; wherein the outliers include at least one or more of mismatching, motion bias caused by dynamic objects.
8. A power transmission channel video image stabilization device, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of the characteristic points are uniformly distributed in the video images of the power transmission channel;
determining a corresponding geometric area by taking the characteristic points as the centers;
obtaining a motion vector corresponding to grid crossing points in the geometric area according to the motion vector of the feature points; wherein any grid intersection receives one or more of the motion vectors;
Calculating to obtain smooth paths corresponding to grid crossing points according to motion vectors corresponding to the grid crossing points in different frames of power transmission channel images, obtaining motion tracks of the power transmission channel video images according to the smooth paths corresponding to the grid crossing points, and realizing power transmission channel video image stabilization according to the motion tracks;
according to the motion vector of the feature point, after obtaining the motion vector corresponding to the grid intersection point in the geometric area, the method further comprises the following steps:
according to all grid intersections in the current power transmission channel image, a global motion vector field is established;
according to the formula
Calculating the local motion vector corresponding to the grid intersection point which does not receive the feature point motion vector; wherein,is a local motion vector; />The characteristic point coordinates of the t frame image; />The characteristic point coordinates of the t-1 frame image; />Global homography estimation is performed for utilizing all the matched features;
according to the formula
Estimating the motion vector corresponding to each grid intersection point when the grid intersection point does not receive the motion vector of the corresponding feature point; wherein,local motion vectors of the feature points corresponding to the grid intersecting points; / >Is a global motion vector field.
9. A non-transitory computer storage medium storing computer-executable instructions configured to:
performing characteristic point matching on adjacent frame video images of the power transmission channel shot by the high-voltage tower camera, and tracking the characteristic points to determine motion vectors of the characteristic points, wherein a plurality of the characteristic points are uniformly distributed in the video images of the power transmission channel;
determining a corresponding geometric area by taking the characteristic points as the centers;
according to the motion vector of each characteristic point, obtaining a motion vector corresponding to the grid intersection point in the geometric area; wherein any grid intersection receives one or more of the motion vectors;
calculating to obtain smooth paths corresponding to all grid crossing points according to the motion vectors corresponding to the grid crossing points in different frames of power transmission channel images, obtaining the motion trail of the power transmission channel video image according to the smooth paths corresponding to all grid crossing points, and realizing the video image stabilization of the power transmission channel according to the motion trail;
according to the motion vector of the feature point, after obtaining the motion vector corresponding to the grid intersection point in the geometric area, the method further comprises the following steps:
According to all grid intersections in the current power transmission channel image, a global motion vector field is established;
according to the formula
Calculating the local motion vector corresponding to the grid intersection point which does not receive the feature point motion vector; wherein,is a local motion vector; />The characteristic point coordinates of the t frame image; />The characteristic point coordinates of the t-1 frame image; />Global homography estimation is performed for utilizing all the matched features;
according to the formula
Estimating the motion vector corresponding to each grid intersection point when the grid intersection point does not receive the motion vector of the corresponding feature point; wherein,local motion vectors of the feature points corresponding to the grid intersecting points; />Is a global motion vector field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993062.7A CN113873099B (en) | 2021-08-27 | 2021-08-27 | Video image stabilizing method, device and medium for power transmission channel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993062.7A CN113873099B (en) | 2021-08-27 | 2021-08-27 | Video image stabilizing method, device and medium for power transmission channel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113873099A CN113873099A (en) | 2021-12-31 |
| CN113873099B true CN113873099B (en) | 2024-04-12 |
Family
ID=78988578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110993062.7A Active CN113873099B (en) | 2021-08-27 | 2021-08-27 | Video image stabilizing method, device and medium for power transmission channel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113873099B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006075394A1 (en) * | 2005-01-14 | 2006-07-20 | Morhpo, Inc. | Motion vector calculation method, hand-movement correction device using the method, imaging device, and motion picture generation device |
| US8923400B1 (en) * | 2007-02-16 | 2014-12-30 | Geo Semiconductor Inc | Method and/or apparatus for multiple pass digital image stabilization |
| CN106101535A (en) * | 2016-06-21 | 2016-11-09 | 北京理工大学 | A kind of based on local and the video stabilizing method of mass motion disparity compensation |
| CN108805908A (en) * | 2018-06-08 | 2018-11-13 | 浙江大学 | A kind of real time video image stabilization based on the superposition of sequential grid stream |
| CN109361880A (en) * | 2018-11-30 | 2019-02-19 | 三星电子（中国）研发中心 | A kind of method and system showing the corresponding dynamic picture of static images or video |
| CN110753181A (en) * | 2019-09-29 | 2020-02-04 | 湖北工业大学 | A Video Stabilization Method Based on Feature Tracking and Grid Path Motion |
| CN110781903A (en) * | 2019-10-12 | 2020-02-11 | 中国地质大学（武汉） | UAV image mosaic method based on grid optimization and global similarity constraints |
| CN111819837A (en) * | 2018-03-11 | 2020-10-23 | 谷歌有限责任公司 | Static video identification |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7426318B2 (en) * | 2004-06-30 | 2008-09-16 | Accuray, Inc. | Motion field generation for non-rigid image registration |
-
2021
- 2021-08-27 CN CN202110993062.7A patent/CN113873099B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006075394A1 (en) * | 2005-01-14 | 2006-07-20 | Morhpo, Inc. | Motion vector calculation method, hand-movement correction device using the method, imaging device, and motion picture generation device |
| US8923400B1 (en) * | 2007-02-16 | 2014-12-30 | Geo Semiconductor Inc | Method and/or apparatus for multiple pass digital image stabilization |
| CN106101535A (en) * | 2016-06-21 | 2016-11-09 | 北京理工大学 | A kind of based on local and the video stabilizing method of mass motion disparity compensation |
| CN111819837A (en) * | 2018-03-11 | 2020-10-23 | 谷歌有限责任公司 | Static video identification |
| CN108805908A (en) * | 2018-06-08 | 2018-11-13 | 浙江大学 | A kind of real time video image stabilization based on the superposition of sequential grid stream |
| CN109361880A (en) * | 2018-11-30 | 2019-02-19 | 三星电子（中国）研发中心 | A kind of method and system showing the corresponding dynamic picture of static images or video |
| CN110753181A (en) * | 2019-09-29 | 2020-02-04 | 湖北工业大学 | A Video Stabilization Method Based on Feature Tracking and Grid Path Motion |
| CN110781903A (en) * | 2019-10-12 | 2020-02-11 | 中国地质大学（武汉） | UAV image mosaic method based on grid optimization and global similarity constraints |
Non-Patent Citations (1)
| Title |
|---|
| 基于特征跟踪和网格路径运动的视频稳像算法;熊炜;王传胜;管来福;童磊;刘敏;曾春艳;;计算机工程与科学(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113873099A (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10404917B2 (en) | One-pass video stabilization | |
| KR102225410B1 (en) | Cascaded camera motion estimation, rolling shutter detection, and camera shake detection for video stabilization | |
| US10244164B1 (en) | Systems and methods for image stitching | |
| TWI469062B (en) | Image stabilization method and image stabilization device | |
| US8724854B2 (en) | Methods and apparatus for robust video stabilization | |
| CN103139568B (en) | Based on the Video Stabilization method of degree of rarefication and fidelity constraint | |
| KR100985805B1 (en) | Image Stabilization Device and Method Using Adaptive Kalman Filter | |
| CN103929568B (en) | For stablizing the method and image stabilizing device of the First ray of digital image frames | |
| US10565691B2 (en) | Method of multi-view deblurring for 3D shape reconstruction, recording medium and device for performing the method | |
| US9253415B2 (en) | Simulating tracking shots from image sequences | |
| US20210227139A1 (en) | Video stabilization method and apparatus and non-transitory computer-readable medium | |
| US9202128B2 (en) | Image adjusting apparatus and method, and image stabilizing apparatus including the same | |
| CN111028191A (en) | Anti-shake method and device for video image, electronic equipment and storage medium | |
| US20150245071A1 (en) | Motion-compensated temporal filtering based on variable filter parameters | |
| US9626595B2 (en) | Method and apparatus for tracking superpixels between related images | |
| US20170111585A1 (en) | Method and system for stabilizing video frames | |
| CN109685879B (en) | Method, device, equipment and storage medium for determining multi-view image texture distribution | |
| EP2446612A1 (en) | Real time video stabilization | |
| US8988534B2 (en) | Characterizing point checking region setting apparatus and method, and image stabilizing apparatus including the same | |
| CN103813056A (en) | Image stabilization method and device | |
| CN114429191B (en) | Electronic anti-shake method, system and storage medium based on deep learning | |
| KR101806453B1 (en) | Moving object detecting apparatus for unmanned aerial vehicle collision avoidance and method thereof | |
| CN113873099B (en) | Video image stabilizing method, device and medium for power transmission channel | |
| CN107516300B (en) | Hybrid jitter correction method for unmanned aerial vehicle video acquisition | |
| US20230290061A1 (en) | Efficient texture mapping of a 3-d mesh |
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 |