Video processing system

Abstract

The invention discloses a video processing system, and the system determines first target video information based on first grid mapping information.

Description

Technical Field

[0001] This application relates to the field of video processing technology, and more specifically to a video processing system. Background Technology

[0002] With the rapid development of mobile terminals, more and more users are shooting videos with handheld devices. Videos shot with handheld devices often suffer from image distortion, thus requiring video stabilization processing. Video stabilization processing refers to converting the original shot video into a stabilized video through special cropping and interpolation methods, so that the stabilized video playback content presents a uniform motion. However, existing video stabilization methods require additional hardware to achieve video stabilization. Summary of the Invention

[0003] This application provides a video processing system.

[0004] In a first aspect, this application provides a method comprising:

[0005] Obtain the first video information;

[0006] Based on the first video information, determine the first grid mapping information;

[0007] Based on the first grid mapping information, the first target video information is determined.

[0008] Secondly, this application provides a system comprising:

[0009] The information acquisition module is used to acquire the first video information;

[0010] The first determining module is used to determine the first grid mapping information based on the first video information;

[0011] The second determining module is used to determine the first target video information based on the first grid mapping information.

[0012] Thirdly, this application also provides a computer device, which includes:

[0013] One or more processors;

[0014] Memory; and

[0015] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor to implement the methods of any one of the first aspects.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of the method in any of the first aspects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of an embodiment of the video processing method provided by the present invention;

[0019] Figure 2 This is a logical schematic diagram of the video stabilization transformation provided in an embodiment of the present invention;

[0020] Figure 3 This is a flowchart illustrating a specific embodiment of determining the first grid mapping information provided by this invention.

[0021] Figure 4 This is a flowchart illustrating a specific embodiment of determining the first target video information provided by this invention.

[0022] Figure 5 This is a schematic flowchart of another embodiment of the video processing method provided in this invention;

[0023] Figure 6 This is a schematic block diagram of the video processing system provided in an embodiment of the present invention;

[0024] Figure 7 This is a schematic diagram of an embodiment of the computer device provided in this invention. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, features defined with "first," "second," "third," etc., may explicitly or implicitly include one or more features. In the description of this application, "multiple" means two or more, and "several" means one or more, unless otherwise explicitly specified.

[0027] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0028] It should be noted that since the method in this application embodiment is executed in a computer device, the processing objects of each computer device exist in the form of data or information, such as time, which is essentially time information. It is understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the computer device can process them. Specific details will not be elaborated here.

[0029] The content of this application will be further explained below with reference to the accompanying drawings and the description of the embodiments.

[0030] This embodiment provides a video processing method, such as... Figure 1 As shown, the method includes:

[0031] Step S201: Obtain the first video information.

[0032] Optionally, the first video information is video data that needs to be stabilized. Stabilization refers to the smoothness and stability of the video image. Video stabilization processing refers to the process of reducing the jitter and shaking of the video image through algorithms and technical means, making the video image smoother and more stable. The first video information can be video data collected by the imaging module configured on the computer device itself, or it can be video data collected by the imaging module of other computer devices through networks, Bluetooth, infrared, etc. This embodiment does not limit it. For example, when the video processing method of this application is applied to a smartphone, the smartphone can directly collect the first video information through its own imaging module; when the video processing method of this application is applied to a server, the server can collect the first video information through the imaging module of the smartphone and obtain the first video information from the smartphone through networks, Bluetooth, infrared, etc.

[0033] Step S202: Determine the first grid mapping information based on the first video information.

[0034] In one specific embodiment, the first video information includes first video frame information, which is the video frame information that currently needs video stabilization processing. The first grid mapping information represents the mapping relationship between the image content of the first video frame information and the image content of the corresponding first stabilized video frame information. The first stabilized video frame information is the stabilized first video frame information obtained after mapping the first video frame information using the first grid mapping information. The image content of the first video frame information and the image content of the corresponding first stabilized video frame information can be mutually converted through the first grid mapping information. For example, as... Figure 2 As shown, the first video frame of the first video information (i.e., the first video frame) is denoted as F1, the second video frame as F2, the third video frame as F3, the fourth video frame as F4, and so on. S1 represents the first stabilized video frame of F1, S2 represents the first stabilized video frame of F2, ..., S n F represents n The first stabilized video frame information, in which each video frame information and its corresponding first stabilized video frame information have a mapping relationship, can be represented by the first grid mapping information R. For example, F i Image content and F i First stabilized video frame information S i The image content can be correlated with each other based on the first grid mapping information R. i The approximate representation of the two-dimensional planar projective transformation, i.e., S i ≈f(F i R i), F i ≈f(S i R i -1 ), where the function f(·) represents the projective transformation.

[0035] In one specific embodiment, the first video information further includes second video frame information, which is historical video frame information of the first video frame information. For example, the second video frame information can be the previous video frame information of the first video frame information. There can also be multiple video frame information between the second video frame information and the first video frame information. This embodiment does not limit this.

[0036] In a specific implementation method, refer to Figure 3 As shown, the step S202 above, which determines the first grid mapping information based on the first video information, may include steps S301 to S302, as follows:

[0037] Step S301: Based on the second video frame information, determine the first shooting information of the first video frame information.

[0038] In one specific embodiment, the first shooting information includes first motion information, second motion information, third motion information, and fourth motion information. The first motion information represents the parameters of motion changes generated between the first video frame information and the second video frame information. The image content of the first video frame information and the image content of the second video frame information can be converted into each other through the first motion information. The second motion information is information obtained by performing a similar transformation on the first motion information based on camera intrinsic parameters. The third motion information is obtained by updating the initial third motion information based on the second motion information using multiple rotation matrices. The fourth motion information is information obtained by performing a similar transformation on the third motion information based on camera intrinsic parameters.

[0039] For example, continue to refer to Figure 2 As shown, there is a mapping transformation relationship between two adjacent video frames. This mapping transformation relationship can be represented by a first motion parameter M. For example, the mapping transformation relationship between F1 and F2 is represented by the first motion parameter M1, the mapping transformation relationship between F2 and F3 is represented by the first motion parameter M2, and so on. t-1 With F t The mapping transformation relationship between them is achieved through the first motion parameter M. t This is represented as follows. For example, the information for the first video frame is F. i The second video frame information is F i-1 The first motion information is M i Then F i ≈f(F i-1 M i ), F i-1≈f(F i M i -1 ), where the function f(·) represents the projective transformation.

[0040] Furthermore, the second motion information is motion information determined based on the first motion information, and the second motion information and the first motion information satisfy the following: Among them, M i Indicates the first motion information, Let H represent the second motion information, and H represent the camera intrinsic parameter matrix. The third motion information is obtained by updating the initial third motion information based on multiple rotation matrices, using the second motion information as the initial information. The third motion information can be represented as: Where C represents the number of rotation matrices. The fourth motion information is the motion information determined based on the third motion information, and the third and fourth motion information satisfy: in, Indicates the fourth motion information, H represents the third motion information, and H represents the camera intrinsic parameter matrix.

[0041] In one specific implementation, the step of determining the first shooting information of the first video frame information based on the second video frame information specifically includes: sampling the first feature point information of the first video frame information and the second feature point information of the second video frame information to obtain feature point pair information; determining the first motion information and the second motion information based on the feature point pair information; determining the third motion information based on the feature point pair information and the second motion information; and performing a similarity transformation on the third motion information to obtain the fourth motion information.

[0042] In one specific embodiment, the first feature point information is the set of mapping points corresponding to sparse points on the reference image information in the first video frame information, and the second feature point information is the set of mapping points corresponding to sparse points on the reference image information in the second video frame information. The first feature point information and the second feature point information can be calculated and obtained from the first video frame information and the second video frame information respectively using a sparse optical flow algorithm. The first feature point information can be represented as... The second feature point information can be represented as: This represents the position information of the j-th feature point in the first video frame. This represents the position information of the j-th feature point in the second video frame information, and N represents the number of feature points.

[0043] In one specific embodiment, the step of sampling and processing the first feature point information of the first video frame information and the second feature point information of the second video frame information to obtain feature point pair information includes: converting the first feature point information of the first video frame information to obtain converted first feature point information; converting the second feature point information of the second video frame information to obtain converted second feature point information; obtaining the number of feature point pairs in the feature point set composed of the converted first feature point information and the converted second feature point information; if the number of feature point pairs is greater than a first number threshold, randomly sampling the first feature point information and the second feature point information a preset number of times to obtain feature point pair information.

[0044] The process of transforming the information of the first feature point can be represented as follows: The process of transforming the information of the second feature point can be represented as follows: This represents the information of the first feature point after conversion. P represents the transformed second feature point information. i P represents the information of the first feature point. i-1 H represents the second feature point information, and H represents the camera intrinsic parameter matrix.

[0045] In one specific embodiment, the step of determining the first motion information and the second motion information based on feature point pair information includes: determining the second motion information based on feature point pair information; and performing a similarity transformation on the second motion information to obtain the first motion information.

[0046] Optionally, the process of determining the second motion information can be expressed as: This represents the j-th feature point in the transformed first feature point information. r represents the j-th feature point in the transformed second feature point information. j R represents the sampled random number. j ∈[1, N], where N represents the number of feature points. This indicates the second motion information.

[0047] In one specific embodiment, the process of performing a similarity transformation on the second motion information can be represented as: M i = Among them, M i Indicates the first motion information, H represents the second motion information, and H represents the camera intrinsic parameter matrix.

[0048] Furthermore, considering that when the first feature point information and the second feature point information are randomly sampled multiple times, each random sampling will yield the first motion information M corresponding to that sampling. i In this embodiment, the first motion information M corresponding to each sampling is obtained. i Then, based on the first motion information M corresponding to each sampling... i The distance information between feature point pairs in the feature point set composed of the first feature point information and the second feature point information is determined; based on the distance information of the feature point pairs, the number of matching points corresponding to each sampling is determined, and the first motion information M corresponding to the sampling with the largest number of matching points is selected. i This was determined as the final first motion information.

[0049] The number of matching points corresponding to each sampling is based on the first motion information M corresponding to each sampling. i The number of matching points whose distance information is less than a preset distance threshold from the determined distance information. The process of determining the distance information of feature point pairs can be expressed as: d=||p i j -M i *p i-1 j ||2, d represents the distance information between feature point pairs, p i j p represents the j-th feature point in the first feature point information. i-1 j M represents the j-th feature point in the second feature point information. i This indicates the first motion information.

[0050] In one specific embodiment, the step of determining the third motion information based on feature point pair information and second motion information includes: determining the second motion information as the initial third motion information; updating the initial third motion information based on the feature point pair information to obtain the updated third motion information. The updating process of the third motion information can be represented as follows: L represents the number of samples, C represents the first motion information M. i Quantity, g k (p i-1 j .y) represents The corresponding weighting coefficients, This indicates information about the third movement.

[0051] In one specific embodiment, the process of performing a similarity transformation on the third motion information can be represented as follows: in, Indicates the third motion information, H represents the fourth motion information, and H represents the camera intrinsic parameter matrix.

[0052] Step S302: Determine the first grid mapping information based on the second grid mapping information of the first shooting information and the second video frame information.

[0053] In this embodiment, the second grid mapping information represents the mapping relationship between the image content of the second video frame information and the image content of the first stabilized video frame information corresponding to the second video frame information. For example, continuing to refer to... Figure 2 As shown, when the second video frame information is F1, the second grid mapping information of the second video frame information is R1; when the second video frame information is F2, the second grid mapping information of the second video frame information is R2, and so on. i The second grid mapping information of the second video frame is R. i .

[0054] In one specific embodiment, the step of determining the first grid mapping information based on the second grid mapping information of the first shooting information and the second video frame information specifically includes: determining the first stabilization information based on the first shooting information; and determining the first grid mapping information based on the second grid mapping information of the first stabilization information and the second video frame information.

[0055] Continue to refer to Figure 2 As shown, S1 represents the preview stabilized video frame information of F1, S2 represents the preview stabilized video frame information of F2, ..., S n F represents n The preview stabilized video frame information shows that there is a mapping transformation relationship between two adjacent preview stabilized video frames. This mapping transformation relationship between two adjacent preview stabilized video frames can be represented by the preview stabilization parameter K, for example, F. i Preview stabilized video frame information S i Image content and F i-1 Preview stabilized video frame information S i-1 The image content can be correlated with each other based on the preview stabilization parameter K. i The approximate representation of the two-dimensional planar projective transformation, i.e., S i ≈f(S i-1 K i ), S i-1 ≈f(S i K i -1 ), where the function f(·) represents the projective transformation. The aforementioned first stabilization information is the virtual stabilization frame information S corresponding to the second video frame information. i-1 Converted into virtual stabilized frame information S corresponding to the first video frame information iThe preview shows the stabilization parameters. Stabilization refers to the process of using technical means to improve the image distortion caused by shaking during video shooting, making the video image more stable.

[0056] In one specific embodiment, the step of determining the first stabilization information based on the first shooting information may specifically include: determining the third stabilization information based on the second stabilization information and the second motion information of the second video frame information; and performing a similarity transformation on the third stabilization information to obtain the first stabilization information.

[0057] In one specific embodiment, the process of determining the third stabilization information can be represented as follows: This represents the third stabilization information. Indicates the second motion information, The second stabilization information is represented by ρ, which represents the preset radial interpolation ratio. Quad() converts the rotation matrix into a quaternion, and the function slerp represents quaternion radial interpolation. The similarity transformation process of the third stabilization information can be represented as follows: K i This represents the first stabilization information. H represents the third stabilization information, and H represents the camera intrinsic parameter matrix.

[0058] In one specific embodiment, when the second stabilization information The calculation failed and the second stabilization information could not be obtained. At that time, the first motion parameter M can be directly used. i It was identified as the first stabilizing information.

[0059] In one specific embodiment, the step of determining the first grid mapping information based on the first stabilization information and the second grid mapping information specifically includes: determining the first fusion information based on the first stabilization information and the second grid mapping information; determining the second fusion information based on the first fusion information; determining the third feature point information and the fourth feature point information based on the first fusion information and the second fusion information; and determining the first grid mapping information based on the third feature point information and the fourth feature point information.

[0060] Optionally, the step of determining the first fused information based on the first stabilization information and the second grid mapping information specifically includes: determining the first image position information based on the first stabilization information and the second grid mapping information; determining the third grid mapping information based on the second grid mapping information; determining the second image position information based on the third grid mapping information and the first stabilization information; and performing fusion processing on the first image position information and the second image position information to obtain the first fused information.

[0061] The step of determining the first image position information based on the first stabilization information and the second grid mapping information specifically includes: obtaining the first optical flow point set of the first video frame information; the first optical flow point set is the set of optical flow points that are hit in the first video frame information; calculating the image coordinate position set of the first optical flow point set in the preview stabilized video frame information corresponding to the first video frame information based on the first stabilization information and the second grid mapping information to obtain the first image position information.

[0062] Furthermore, the third grid mapping information is a least-squares estimate of the rotation matrix of the second grid mapping information. The steps for determining the second image position information based on the third grid mapping information and the first stabilization information specifically include: obtaining the second optical flow point set of the second video frame information; the second optical flow point set is the set of optical flow points that are hit in the second video frame information; and calculating the image coordinate position set of the second optical flow point set in the preview stabilized video frame information corresponding to the first video frame information based on the third grid mapping information and the first stabilization information to obtain the second image position information.

[0063] In one specific embodiment, the step of fusing the first image position information and the second image position information to obtain the first fused information specifically includes: determining feature point distance information based on the first image position information and the second image position information; determining fusion weight information based on the feature point distance information and the preset reset distance information; and fusing the first image position information and the second image position information based on the fusion weight information to obtain the first fused information.

[0064] Optionally, the process of determining the feature point distance information can be represented as: dis mean =mean(||p1-p2||), dis mean Represents the distance information between feature points. Indicates the position information of the first image. This represents the location information of the second image. The process of determining the fusion weight information can be represented as follows: w represents the fusion weight information, dis reset Here, ε represents the preset reset distance information, and ε represents the preset threshold. The process of determining the first fusion information can be expressed as follows: This represents the first piece of information that has been integrated.

[0065] In one specific embodiment, the step of determining the second fusion information based on the first fusion information specifically includes: dividing the first fusion information into a grid to obtain fifth feature point information; fusing the fifth feature point information, the first stabilization information, the second grid mapping information, and the fourth motion information of the first video frame information to obtain sixth feature point information; fusing the fifth feature point information, the first stabilization information, the third grid mapping information, and the fourth motion information to obtain seventh feature point information; and fusing the sixth feature point information and the seventh feature point information to obtain the second fusion information.

[0066] Optionally, when dividing the first fused information into a grid, the first fused information can be divided into the grid corresponding to the preview stabilized video frame information of the first video frame information to obtain a grid without optical flow points, and the fifth feature point information can be determined based on the center point of the grid without optical flow points.

[0067] In one specific embodiment, the step of determining the third feature point information and the fourth feature point information based on the first fusion information and the second fusion information may specifically include: determining the third feature point information based on the first fusion information and the fifth feature point information; and determining the fourth feature point information based on the second fusion information and the first optical flow point set. The process of determining the third feature point information can be expressed as follows: The process of determining the information of the fourth feature point can be represented as follows: Indicates the information of the third feature point. Indicates the information of the fourth feature point. This represents the first fused information. This represents the information of the fifth feature point. This indicates the second fused information. This represents the set of the first optical flow points.

[0068] Step S203: Determine the first target video information based on the first grid mapping information.

[0069] Optionally, the first target video information is the stabilized first video information determined based on the first grid mapping information. In this embodiment, the first grid mapping information is determined based on the first video information, and the first target video information is determined based on the first grid mapping information. Video stabilization can be achieved without additional hardware devices, and the motion consistency between the obtained first target video information and the first video frame information can be ensured.

[0070] In one specific embodiment, reference is made to Figure 4 As shown, the determination of the first target video information based on the first grid mapping information may include steps S401 to S403, as follows:

[0071] Step S401: The video mapping information corresponding to the first grid mapping information and the first video frame information is fused to obtain the fourth grid mapping information.

[0072] In one specific embodiment, the video mapping information corresponding to the first video frame information is a mapping matrix related to the image height and image width corresponding to the first video frame information. The video mapping information corresponding to the first video frame information is used to perform mapping processing on the first grid mapping information. The video mapping information corresponding to the first video frame information is obtained through the following steps: obtaining the image size information of the first video frame information; determining the video mapping information corresponding to the first video frame information based on the image size information. The process of determining the video mapping information corresponding to the first video frame information can be expressed as follows: image_width represents the image width of the first video frame, image_height represents the image height of the first video frame, C represents the video mapping information, and k represents a preset coefficient, k∈[0,1).

[0073] In one specific embodiment, the process of fusing the video mapping information corresponding to the first grid mapping information and the first video frame information can be represented as follows: Represents the fourth grid mapping information, R i C represents the first grid mapping information, and C represents the video mapping information.

[0074] Step S402: Determine the fifth grid mapping information based on the fourth grid mapping information and the first grid mapping information.

[0075] In one specific embodiment, the step of determining the fifth grid mapping information based on the fourth grid mapping information and the first grid mapping information specifically includes: performing a transformation process on the first grid mapping information to obtain first rotation information; determining whether the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information; if the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information and the rotation amplitude of the second motion information of the first video frame information is less than a first threshold, updating the rotation angle of the first rotation information, and fusing the updated first rotation information and the first grid mapping information to obtain the fifth grid mapping information; if the feature point corresponding to the fourth grid mapping information is not located within the image region corresponding to the first video frame information, performing projection decomposition on the first rotation information based on the boundary distance information between the first grid mapping information and the first video frame information to obtain reset axis information; updating the first grid mapping information based on the reset axis information to obtain the fifth grid mapping information.

[0076] The first rotation information is the rotation axis information obtained by converting the quadruple of the first mesh mapping information into the form of a rotation axis. The process of updating the rotation angle of the first rotation information can be represented as follows:

[0077] axis update This represents the updated first rotation information, axis. reset Indicates the first rotation information, axis′ reset This represents the first rotation information after adjusting the rotation angle, and σ represents the preset angle threshold. The process of fusing the updated first rotation information and the first mesh mapping information can be represented as: R i * =axis update *R i R i * Represents the fifth grid mapping information, R i This indicates the first grid mapping information.

[0078] In one specific embodiment, the boundary distance information includes first distance information, second distance information, third distance information, and fourth distance information. The first distance information and the second distance information are the distances between the first preview mapping information and the left and right boundaries of the first video frame information, respectively. The third distance information and the fourth distance information are the distances between the first preview mapping information and the upper and lower boundaries of the first video frame information, respectively. The step of projecting and decomposing the first rotation information based on the boundary distance information between the first grid mapping information and the first video frame information to obtain the reset axis information specifically includes: if the sum of the first distance information and the second distance information is greater than 0, the first distance information is less than 0, and / or the second distance information is less than 0, projecting and decomposing the first rotation information along the x-axis, and determining the rotation axis of the x-axis component of the first rotation information as the reset axis information; if the sum of the third distance information and the fourth distance information is greater than 0, the third distance information is less than 0, and / or the fourth distance information is less than 0, projecting and decomposing the first rotation information along the y-axis, and determining the rotation axis of the y-axis component of the first rotation information as the reset axis information; otherwise, the first rotation information is determined as the reset axis information.

[0079] In one specific embodiment, the step of updating the first grid mapping information based on the reset axis information to obtain the fifth grid mapping information specifically includes: projecting the rotation vector of the first rotation information of the first grid mapping information based on the reset axis information to obtain the first rotation axis information and the second rotation axis information; determining the initial binary search interval based on the first rotation axis information; and resetting the first grid mapping information based on the initial binary search interval to obtain the fifth grid mapping information.

[0080] When determining the initial binary search interval based on the first rotation axis information, the rotation angle corresponding to the first rotation axis information can be determined as the endpoint of the initial binary search interval. For example, the rotation angle corresponding to the first rotation axis information is axis. reset When .angle() is called, the initial binary search interval is [0, axis]. reset ·angle()].

[0081] Furthermore, when updating the first grid mapping information based on the initial binary search interval to obtain the fifth grid mapping information, the rotation angle of the first rotation information can be updated based on the initial binary search interval to obtain the updated first rotation information. Then, the first grid mapping information is updated based on the updated first rotation information, and the updated fourth grid mapping information is determined based on the updated first grid mapping information. Next, the boundary conditions of the updated first grid mapping information are determined based on the updated fourth grid mapping information. Finally, the initial binary search interval is updated based on the boundary conditions of the updated first grid mapping information, and the step of updating the rotation angle of the first rotation information based on the initial binary search interval continues until the interval length of the initial binary search interval is less than a preset length threshold.

[0082] The process of updating the rotation angle of the first rotation information based on the initial binary search interval can be expressed as: axis update This represents the updated first rotation information, axis. reset Indicates the first rotation information, axis′ reset This represents the first rotation information after the rotation angle adjustment, and [a, b] represents the initial binary search interval. When updating the initial binary search interval based on the out-of-bounds condition of the updated first mesh mapping information, if the updated first mesh mapping information does not exceed the bounds, then... The updated initial binary search interval is determined. If the updated first grid mapping information exceeds the limit, then... This is determined as the updated initial binary search interval.

[0083] Step S403: Map the first video frame information based on the fifth grid mapping information to obtain the first target video information.

[0084] This embodiment determines the fifth grid mapping information based on the fourth grid mapping information and the first grid mapping information, and performs mapping processing on the first video frame information based on the fifth grid mapping information, which can improve the stabilization effect of the obtained first target video information.

[0085] In a specific implementation method, refer to Figure 5As shown, after determining the first target video information based on the first grid mapping information in step S203 above, steps S501 to S503 may be included, as follows:

[0086] Step S501: Based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information, process the first grid mapping information to obtain the sixth grid mapping information.

[0087] In one specific embodiment, the fourth stabilization information is obtained through the following steps: determining the second rotation information based on the first shooting information and historical motion information; interpolating the third stabilization information of the first video frame information based on the first shooting information and historical motion information to obtain the fifth stabilization information; adjusting the fifth stabilization information based on the second rotation information to obtain the sixth stabilization information; and determining the fourth stabilization information based on the sixth stabilization information and the seventh stabilization information of the second video frame information.

[0088] The step of determining the second rotation information based on the first shooting information and historical motion information specifically includes: determining the fourth candidate information based on the first shooting information and historical motion information; updating the rotation angle of the fourth candidate information to obtain the fifth candidate information; and converting the fifth candidate information to obtain the second rotation information.

[0089] Optionally, the process of determining the fourth candidate information can be expressed as: This represents the fourth candidate information, where `idx` represents the frame number of the selected frame with the minimum motion velocity relative to frame `i` in the historical information window, `axis` represents the rotation axis of the quaternion transformation, and `angle()` represents the rotation angle of the rotation axis. The update process of the rotation angle of the fourth candidate information can be represented as follows: Let k represent the rotation angle of the fourth candidate information, k ∈ [iw, i], where [iw, i] represents the frame number. The process of transforming the fifth candidate information can be represented as follows: Indicates the second rotation information. Indicates the form of rotation axis and rotation amplitude. This indicates that the rotation axis is converted to a rotation quaternion.

[0090] In one specific embodiment, the process of adjusting the fifth stabilization information based on the second rotation information can be represented as follows: This represents the sixth stabilization information, where ρ1 represents the preset proportional threshold. This indicates the rotation angle information corresponding to the second rotation information. This indicates the rotation angle information corresponding to the fifth stabilization information.

[0091] In one specific embodiment, the step of determining the fourth stabilization information based on the seventh stabilization information of the sixth stabilization information and the second video frame information specifically includes: interpolating the seventh stabilization information of the sixth stabilization information and the second video frame information to obtain the eighth stabilization information; and converting the eighth stabilization information to obtain the fourth stabilization information.

[0092] The process of determining the eighth stabilization information can be expressed as follows: λ rate =min(λ) rate +λ plus ,1), This represents the eighth stabilization information. This represents the seventh stabilization information. Represents the sixth stabilization information, λ rate λ represents the dynamic interpolation scale value. plus This is a preset threshold.

[0093] In one specific embodiment, the step of processing the first grid mapping information based on the first captured information, the first stabilized information of the first video frame information, and the fourth stabilized information of the first video frame information to obtain the sixth grid mapping information specifically includes: calculating and processing the first stabilized information of the first captured information and the first video frame information to obtain first candidate information; calculating and processing the fourth stabilized information of the first captured information and the first video frame information to obtain second candidate information; fusing the first candidate information and the second candidate information to obtain third candidate information; and fusing the third candidate information and the first grid mapping information to obtain the sixth grid mapping information.

[0094] The process of determining the first candidate information can be expressed as follows: The process of determining the second candidate information can be represented as follows: The process of determining the third candidate information can be represented as follows: The process of determining the mapping information of the sixth grid can be represented as follows: Indicates the first candidate information. Indicates the second candidate information. M represents the third candidate information. i K represents the first motion information. i This represents the first stabilization information. Represents the fourth stabilization information, R i This indicates the first grid mapping information. This indicates the mapping information for the sixth grid.

[0095] Step S502: Map the first video frame information based on the sixth grid mapping information to obtain the second target video information.

[0096] Optionally, the second target video information is the first video information stabilized based on the sixth grid mapping information. The sixth grid mapping information represents the mapping relationship between the first video frame information and the second stabilized video frame information corresponding to the first video frame information. After determining the sixth grid mapping information, the first video frame information can be mapped based on the sixth grid mapping information to obtain the second target video information.

[0097] Step S503: Process the second target video information based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information.

[0098] Optionally, the third video frame information is the delayed video frame information corresponding to the first video frame information. For example, the first video frame information is the i-th video frame information F. i The information of the third video frame is the information of the iwth video frame F. i-w The seventh grid mapping information represents the mapping relationship between the third video frame information and the corresponding preview stabilized video frame, while the eighth grid mapping information represents the mapping relationship between the third video frame information and the corresponding encoded stabilized video frame. The process for determining the seventh grid mapping information of the third video frame information is the same as the process for determining the first grid mapping information of the first video frame information. For details, please refer to the process for determining the first grid mapping information of the first video frame information. To avoid repetition, this embodiment will not elaborate further.

[0099] In one specific embodiment, the first video frame information is the information of the i-th video frame, and the eighth grid mapping information is obtained through the following steps: performing boundary checks on the w / z frames after the iw frame; if a boundary violation exists, locking the out-of-bounds frame number i-w+v; if v>1, based on... and Sure based on Sure Definite This refers to the mapping information of the eighth grid. It is determined using the following formula. based on Sure The process can be represented as: H represents the camera intrinsic parameter matrix.

[0100] It should be noted that, and The determination process is related to the aforementioned six stable information. The determination process is the same, and for details, please refer to the sixth stabilization information mentioned above. To avoid repetition, the process of determining the method will not be described in detail here.

[0101] Optionally, if v = 1, i.e., frame i-w+1 is out of bounds, then... and Perform interpolation to obtain based on Sure Definite This refers to the mapping information of the eighth grid. Among them, for and The interpolation process can be represented as follows: λ rate =λ const , λ const These are preset coefficients.

[0102] Optionally, if v = 0, i.e., the iw frame goes out of bounds, then λ is determined. rate =λ const Based on the aforementioned sixth stabilization information The determination process based on Sure For details, please refer to the foregoing. To avoid repetition, the process of determining the method will not be described in detail here.

[0103] In one specific embodiment, the step of processing the second target video information based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information specifically includes: calculating and processing the seventh grid mapping information and preset mapping information of the third video frame information to obtain the first target mapping information; calculating and processing the eighth grid mapping information and preset mapping information of the third video frame information to obtain the second target mapping information; fusing the first target mapping information and the second target mapping information to obtain the third target mapping information; and mapping the second target video information based on the third target mapping information and the first target mapping information to obtain the third target video information.

[0104] The process of determining the first target mapping information can be represented as: P org_cen = matrix(R i-w )·P stab_cen The process of determining the second target mapping information can be represented as follows: The process of determining the third target mapping information can be represented as follows: P org_cenThis indicates the first target mapping information. This indicates the mapping information for the second target. Represents the third target mapping information, R i-w This indicates the mapping information for the seventh grid. This represents the mapping information of the eighth grid, ε represents the preset reset distance information, and P... stab_cen P represents the preset mapping information. stab_cen It can be configured as needed; in one specific embodiment, P stab_cen =[0.5 0.5 1].

[0105] In one specific embodiment, the step of mapping the second target video information based on the third target mapping information and the first target mapping information to obtain the third target video information specifically includes: determining a rotation quaternion based on the third target mapping information and the first target mapping information; and processing the second target video information based on the rotation quaternion to obtain the third target video information.

[0106] The process of determining the rotation quaternion can be expressed as: V = The process of processing the second target video information based on rotation quaternions can be represented as follows: V represents a rotation quaternion. P represents the third target mapping information. org_cen This indicates the first target mapping information. This indicates the third target video information. This indicates the second target video information.

[0107] In one specific implementation, after determining the first target video information based on the first grid mapping information in step S203, the method may further include: rendering the first target video information to obtain a first target rendered image. The rendering method may include, but is not limited to, GPU rendering, CPU rendering, etc., and this embodiment does not impose any limitations.

[0108] In one specific implementation, when GPU rendering is used, the steps for rendering the first target video information specifically include: obtaining the vertex data V of the first target video information. ij and vertex data V ij Corresponding texture coordinates T ij Determine vertex data V ij The row block to which it belongs; based on vertex data V ij Mapping information of the line block to which it belongs For vertex data V ij Perform vertex transformation to obtain the transformed vertex data. Based on the transformed vertex data and texture coordinates T ij Draw and render the image to obtain the first target rendered image. Wherein, texture coordinates T... ij It can be represented as: The rendered image contains 2*L*C triangles, where i and j represent vertex data V. ij The number of rows and columns of the rendering grid to which it belongs, where L represents the number of rows of the rendering grid and C represents the number of columns of the rendering grid.

[0109] In one specific implementation, after processing the second target video information based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information in step S503 to obtain the third target video information, the process may further include: rendering the third target video information to obtain a second target rendered image. The process of rendering the third target video information to obtain the second target rendered image is the same as the process of rendering the first target video information to obtain the first target rendered image. For details, please refer to the foregoing discussion of rendering the first target video information to obtain the first target rendered image; to avoid repetition, this embodiment will not repeat the details here.

[0110] In summary, the video processing method provided in this implementation scheme obtains first video information, determines first grid mapping information based on the first video information, and determines first target video information based on the first grid mapping information. This scheme determines the first grid mapping information based on the first video information, and then determines the first target video information based on the first grid mapping information. This achieves video stabilization without additional hardware and ensures motion consistency between the obtained first target video information and the first video frame information. Furthermore, the first grid mapping information is processed based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information. The first video frame information is then mapped based on the sixth grid mapping information to obtain the second target video information. Finally, the second target video information is processed based on the seventh and eighth grid mapping information of the third video frame information to obtain the third target video information. This allows for simultaneous preview stabilization and encoding stabilization, and can constrain the differences between preview stabilization and encoding stabilization.

[0111] To better implement the video processing method in the embodiments of this application, a video processing system is also provided in the embodiments of this application, such as... Figure 6 As shown, the video processing system includes:

[0112] Information acquisition module 710 is used to acquire first video information;

[0113] The first determining module 720 is used to determine the first grid mapping information based on the first video information;

[0114] The second determining module 730 is used to determine the first target video information based on the first grid mapping information.

[0115] In this embodiment, by determining the first grid mapping information based on the first video information, and then determining the first target video information based on the first grid mapping information, video stabilization can be achieved without additional hardware devices, and the motion consistency between the obtained first target video information and the first video frame information can be ensured.

[0116] In some embodiments of this application, the first video information includes first video frame information and second video frame information. The first determining module 720 determines the first grid mapping information based on the first video information, including:

[0117] Based on the information of the second video frame, determine the first shooting information of the first video frame;

[0118] The first grid mapping information is determined based on the second grid mapping information of the first shooting information and the second video frame information.

[0119] In some embodiments of this application, the first shooting information includes first motion information, second motion information, third motion information, and fourth motion information. The first determining module 720 determines the first shooting information of the first video frame information based on the second video frame information, including:

[0120] The first feature point information of the first video frame and the second feature point information of the second video frame are sampled and processed to obtain feature point pair information;

[0121] Based on feature point pair information, determine the first motion information and the second motion information;

[0122] The third motion information is determined based on feature point pair information and second motion information;

[0123] The third motion information is transformed by similarity to obtain the fourth motion information.

[0124] In some embodiments of this application, the first determining module 720 determines the first grid mapping information based on the second grid mapping information of the first shooting information and the second video frame information, including:

[0125] Based on the first image information, determine the first stabilization information;

[0126] The first grid mapping information is determined based on the second grid mapping information of the first stabilization information and the second video frame information.

[0127] In some embodiments of this application, the first determining module 720 determines first stabilization information based on the first captured information, including:

[0128] The third stabilization information is determined based on the second stabilization information and the second motion information of the second video frame.

[0129] The first stabilization information is obtained by performing a similarity transformation on the third stabilization information.

[0130] In some embodiments of this application, the first determining module 720 determines the first mesh mapping information based on the first stabilization information and the second mesh mapping information, including:

[0131] The first fusion information is determined based on the first stabilization information and the second grid mapping information;

[0132] Based on the first fused information, the second fused information is determined;

[0133] Based on the first fused information and the second fused information, the third feature point information and the fourth feature point information are determined;

[0134] Based on the information of the third and fourth feature points, the first grid mapping information is determined.

[0135] In some embodiments of this application, the first determining module 720 determines the first fusion information based on the first stabilization information and the second mesh mapping information, including:

[0136] Based on the first stabilization information and the second grid mapping information, the first image position information is determined;

[0137] Based on the second grid mapping information, determine the third grid mapping information;

[0138] Based on the third grid mapping information and the first stabilization information, the second image position information is determined;

[0139] The positional information of the first image and the positional information of the second image are fused to obtain the first fused information.

[0140] In some embodiments of this application, the first determining module 720 determines second fusion information based on the first fusion information, including:

[0141] The first fused information is divided into grids to obtain the fifth feature point information;

[0142] The fifth feature point information, the first stabilization information, the second grid mapping information, and the fourth motion information of the first video frame information are fused to obtain the sixth feature point information.

[0143] The fifth feature point information, the first stabilization information, the third grid mapping information, and the fourth motion information are fused to obtain the seventh feature point information.

[0144] The information from the sixth and seventh feature points is fused to obtain the second fused information.

[0145] In some embodiments of this application, the second determining module 730 determines the first target video information based on the first grid mapping information, including:

[0146] The video mapping information corresponding to the first grid mapping information and the first video frame information is fused to obtain the fourth grid mapping information;

[0147] Based on the fourth grid mapping information and the first grid mapping information, the fifth grid mapping information is determined;

[0148] The first video frame information is mapped based on the fifth grid mapping information to obtain the first target video information.

[0149] In some embodiments of this application, the second determining module 730 determines the fifth mesh mapping information based on the fourth mesh mapping information and the first mesh mapping information, including:

[0150] The first grid mapping information is transformed to obtain the first rotation information;

[0151] Determine whether the feature points corresponding to the fourth grid mapping information are located within the image region corresponding to the first video frame information;

[0152] If the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information and the rotation amplitude of the second motion information of the first video frame information is less than the first threshold, the rotation angle of the first rotation information is updated, and the updated first rotation information and the first grid mapping information are fused to obtain the fifth grid mapping information; or,

[0153] If the feature point corresponding to the fourth grid mapping information is not located in the image area corresponding to the first video frame information, the first rotation information is projected and decomposed based on the boundary distance information between the first grid mapping information and the first video frame information to obtain the reset axis information.

[0154] The first grid mapping information is updated based on the reset axis information to obtain the fifth grid mapping information.

[0155] In some embodiments of this application, after the second determining module 730 determines the first target video information based on the first grid mapping information, the second determining module 730 is further configured to:

[0156] The first grid mapping information is processed based on the first shooting information, the first stable information of the first video frame information, and the fourth stable information of the first video frame information to obtain the sixth grid mapping information;

[0157] The first video frame information is mapped based on the sixth grid mapping information to obtain the second target video information;

[0158] The second target video information is processed based on the seventh grid mapping information and the eighth grid mapping information of the third video frame to obtain the third target video information.

[0159] In some embodiments of this application, the second determining module 730 processes the first grid mapping information based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information, including:

[0160] The first stabilized information of the first captured information and the first video frame information is calculated and processed to obtain the first candidate information;

[0161] The fourth stabilization information of the first shooting information and the first video frame information is calculated and processed to obtain the second candidate information;

[0162] The first and second candidate information are fused to obtain the third candidate information;

[0163] The third candidate information and the first grid mapping information are fused to obtain the sixth grid mapping information.

[0164] In some embodiments of this application, the second determining module 730 processes the second target video information based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information, including:

[0165] The seventh grid mapping information and the preset mapping information of the third video frame are calculated and processed to obtain the first target mapping information;

[0166] The eighth grid mapping information and the preset mapping information of the third video frame information are calculated and processed to obtain the second target mapping information;

[0167] The first target mapping information and the second target mapping information are fused to obtain the third target mapping information;

[0168] The second target video information is mapped based on the third target mapping information and the first target mapping information to obtain the third target video information.

[0169] This application also provides a computer device that integrates any of the video processing systems provided in this application. The computer device includes:

[0170] One or more processors;

[0171] Memory; and

[0172] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor from the steps of the video processing method in any of the embodiments described above.

[0173] This application also provides a computer device that integrates any of the video processing systems provided in this application. For example... Figure 7 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0174] The computer device may include components such as a processor 801 with one or more processing cores, a memory 802 with one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will understand that... Figure 7 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0175] The processor 801 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 802, and by calling data stored in the memory 802, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the computer device. Optionally, the processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 801.

[0176] The memory 802 can be used to store software programs and modules. The processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 with access to the memory 802.

[0177] The computer device also includes a power supply 803 that supplies power to the various components. Preferably, the power supply 803 can be logically connected to the processor 801 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 803 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0178] The computer device may also include an input unit 804, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0179] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 801 in the computer device loads the executable files corresponding to the processes of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802 to realize various functions, as follows:

[0180] Obtain the first video information;

[0181] Based on the first video information, determine the first grid mapping information;

[0182] Based on the first grid mapping information, the first target video information is determined.

[0183] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0184] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the video processing methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0185] Obtain the first video information;

[0186] Based on the first video information, determine the first grid mapping information;

[0187] Based on the first grid mapping information, the first target video information is determined.

[0188] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0189] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0190] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0191] The foregoing has provided a detailed description of a video processing method, system, computer device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method, characterized in that, include: Obtain the first video information; Based on the first video information, determine the first grid mapping information; Based on the first grid mapping information, the first target video information is determined.

2. The method according to claim 1, characterized in that, The first video information includes first video frame information and second video frame information. The step of determining the first grid mapping information based on the first video information includes: Based on the second video frame information, determine the first shooting information of the first video frame information; The first grid mapping information is determined based on the second grid mapping information of the first shooting information and the second video frame information.

3. The method according to claim 2, characterized in that, The first shooting information includes first motion information, second motion information, third motion information, and fourth motion information. The step of determining the first shooting information based on the second video frame information includes: The first feature point information of the first video frame information and the second feature point information of the second video frame information are sampled to obtain feature point pair information; Based on the feature point pair information, the first motion information and the second motion information are determined; The third motion information is determined based on the feature point pair information and the second motion information; The third motion information is transformed by similarity to obtain the fourth motion information.

4. The method according to claim 2, characterized in that, The determination of the first grid mapping information based on the second grid mapping information of the first shooting information and the second video frame information includes: Based on the first captured information, the first stabilization information is determined; The first grid mapping information is determined based on the second grid mapping information of the first stabilization information and the second video frame information.

5. The method according to claim 4, characterized in that, The first shooting information includes first motion information and second motion information. The step of determining the first stabilization information based on the first shooting information includes: Based on the second stabilization information and the second motion information of the second video frame information, the third stabilization information is determined; The third stabilization information is transformed by similarity transformation to obtain the first stabilization information.

6. The method according to claim 4, characterized in that, The step of determining the first grid mapping information based on the first stabilization information and the second grid mapping information includes: Based on the first stabilization information and the second grid mapping information, the first fusion information is determined; Based on the first fused information, the second fused information is determined; Based on the first fusion information and the second fusion information, the third feature point information and the fourth feature point information are determined; Based on the third feature point information and the fourth feature point information, the first grid mapping information is determined.

7. The method according to claim 6, characterized in that, The step of determining the first fusion information based on the first stabilization information and the second mesh mapping information includes: Based on the first stabilization information and the second grid mapping information, the first image position information is determined; Based on the second grid mapping information, the third grid mapping information is determined; Based on the third grid mapping information and the first stabilization information, the second image position information is determined; The first image location information and the second image location information are fused to obtain the first fused information.

8. The method according to claim 7, characterized in that, The step of determining the second fusion information based on the first fusion information includes: The first fused information is divided into grids to obtain the fifth feature point information; The fifth feature point information, the first stabilization information, the second grid mapping information, and the fourth motion information of the first video frame information are fused to obtain the sixth feature point information. The fifth feature point information, the first stabilization information, the third grid mapping information, and the fourth motion information are fused to obtain the seventh feature point information. The information of the sixth feature point and the information of the seventh feature point are fused to obtain the second fused information.

9. The method according to claim 1, characterized in that, The first video information includes first video frame information, and the step of determining the first target video information based on the first grid mapping information includes: The first grid mapping information and the video mapping information corresponding to the first video frame information are fused to obtain the fourth grid mapping information. Based on the fourth grid mapping information and the first grid mapping information, the fifth grid mapping information is determined; The first video frame information is mapped based on the fifth grid mapping information to obtain the first target video information.

10. The method according to claim 9, characterized in that, Determining the fifth grid mapping information based on the fourth grid mapping information and the first grid mapping information includes: The first mesh mapping information is transformed to obtain the first rotation information; Determine whether the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information; If the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information and the rotation amplitude of the second motion information of the first video frame information is less than the first threshold, the rotation angle of the first rotation information is updated, and the updated first rotation information and the first grid mapping information are fused to obtain the fifth grid mapping information; or... If the feature point corresponding to the fourth grid mapping information is not located in the image area corresponding to the first video frame information, the first rotation information is projected and decomposed based on the boundary distance information between the first grid mapping information and the first video frame information to obtain the reset axis information. The first grid mapping information is updated based on the reset axis information to obtain the fifth grid mapping information.

11. The method according to claim 2, characterized in that, After determining the first target video information based on the first grid mapping information, the process includes: The first grid mapping information is processed based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information. Based on the sixth grid mapping information, the first video frame information is mapped to obtain the second target video information; The second target video information is processed based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information.

12. The method according to claim 11, characterized in that, The process of processing the first grid mapping information based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information includes: The first stabilized information of the first captured information and the first video frame information is calculated and processed to obtain the first candidate information; The fourth stabilization information of the first shooting information and the first video frame information is calculated and processed to obtain the second candidate information; The first candidate information and the second candidate information are fused to obtain the third candidate information; The third candidate information and the first grid mapping information are fused to obtain the sixth grid mapping information.

13. The method according to claim 11, characterized in that, The seventh grid mapping information based on the third video frame information and the eighth grid mapping information based on the third video frame information are used to process the second target video information to obtain the third target video information, including: The seventh grid mapping information and the preset mapping information of the third video frame information are calculated and processed to obtain the first target mapping information; The eighth grid mapping information and the preset mapping information of the third video frame information are calculated and processed to obtain the second target mapping information; The first target mapping information and the second target mapping information are fused to obtain the third target mapping information; The second target video information is mapped based on the third target mapping information and the first target mapping information to obtain the third target video information.

14. A system, characterized in that, include: The information acquisition module is used to acquire the first video information; The first determining module is used to determine the first grid mapping information based on the first video information; The second determining module is used to determine the first target video information based on the first grid mapping information; Preferably, the first video information includes first video frame information and second video frame information, and the first determining module determines the first grid mapping information based on the first video information, including: Based on the second video frame information, determine the first shooting information of the first video frame information; Based on the second grid mapping information of the first shooting information and the second video frame information, the first grid mapping information is determined; Preferably, the first shooting information includes first motion information, second motion information, third motion information, and fourth motion information. The first determining module determines the first shooting information of the first video frame information based on the second video frame information, including: The first feature point information of the first video frame information and the second feature point information of the second video frame information are sampled to obtain feature point pair information; Based on the feature point pair information, the first motion information and the second motion information are determined; The third motion information is determined based on the feature point pair information and the second motion information; The third motion information is transformed using a similarity transformation to obtain the fourth motion information; Preferably, the first determining module determines the first grid mapping information based on the second grid mapping information of the first shooting information and the second video frame information, including: Based on the first captured information, the first stabilization information is determined; Based on the first stabilization information and the second video frame information, the second grid mapping information is used to determine the first grid mapping information; Preferably, the first determining module determines the first stabilization information based on the first captured information, including: Based on the second stabilization information and the second motion information of the second video frame information, the third stabilization information is determined; The first stabilization information is obtained by performing a similarity transformation on the third stabilization information; Preferably, the first determining module determines the first mesh mapping information based on the first stabilization information and the second mesh mapping information, including: Based on the first stabilization information and the second grid mapping information, the first fusion information is determined; Based on the first fused information, the second fused information is determined; Based on the first fusion information and the second fusion information, the third feature point information and the fourth feature point information are determined; Based on the third feature point information and the fourth feature point information, the first grid mapping information is determined; Preferably, the first determining module determines the first fusion information based on the first stabilization information and the second mesh mapping information, including: Based on the first stabilization information and the second grid mapping information, the first image position information is determined; Based on the second grid mapping information, the third grid mapping information is determined; Based on the third grid mapping information and the first stabilization information, the second image position information is determined; The first image location information and the second image location information are fused to obtain first fused information; Preferably, the first determining module determines the second fusion information based on the first fusion information, including: The first fused information is divided into grids to obtain the fifth feature point information; The fifth feature point information, the first stabilization information, the second grid mapping information, and the fourth motion information of the first video frame information are fused to obtain the sixth feature point information. The fifth feature point information, the first stabilization information, the third grid mapping information, and the fourth motion information are fused to obtain the seventh feature point information. The sixth feature point information and the seventh feature point information are fused to obtain the second fused information; Preferably, the second determining module determines the first target video information based on the first grid mapping information, including: The first grid mapping information and the video mapping information corresponding to the first video frame information are fused to obtain the fourth grid mapping information. Based on the fourth grid mapping information and the first grid mapping information, the fifth grid mapping information is determined; Based on the fifth grid mapping information, the first video frame information is mapped to obtain the first target video information; Preferably, the second determining module determines the fifth grid mapping information based on the fourth grid mapping information and the first grid mapping information, including: The first mesh mapping information is transformed to obtain the first rotation information; Determine whether the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information; If the feature point corresponding to the fourth grid mapping information is located within the image region corresponding to the first video frame information and the rotation amplitude of the second motion information of the first video frame information is less than the first threshold, the rotation angle of the first rotation information is updated, and the updated first rotation information and the first grid mapping information are fused to obtain the fifth grid mapping information; or... If the feature point corresponding to the fourth grid mapping information is not located in the image area corresponding to the first video frame information, the first rotation information is projected and decomposed based on the boundary distance information between the first grid mapping information and the first video frame information to obtain the reset axis information. The first grid mapping information is updated based on the reset axis information to obtain the fifth grid mapping information; Preferably, after the second determining module determines the first target video information based on the first grid mapping information, the second determining module is further configured to: The first grid mapping information is processed based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information. Based on the sixth grid mapping information, the first video frame information is mapped to obtain the second target video information; The second target video information is processed based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information. Preferably, the second determining module processes the first grid mapping information based on the first shooting information, the first stabilization information of the first video frame information, and the fourth stabilization information of the first video frame information to obtain the sixth grid mapping information, including: The first stabilized information of the first captured information and the first video frame information is calculated and processed to obtain the first candidate information; The fourth stabilization information of the first shooting information and the first video frame information is calculated and processed to obtain the second candidate information; The first candidate information and the second candidate information are fused to obtain the third candidate information; The third candidate information and the first grid mapping information are fused to obtain the sixth grid mapping information; Preferably, the second determining module processes the second target video information based on the seventh grid mapping information and the eighth grid mapping information of the third video frame information to obtain the third target video information, including: The seventh grid mapping information and the preset mapping information of the third video frame information are calculated and processed to obtain the first target mapping information; The eighth grid mapping information and the preset mapping information of the third video frame information are calculated and processed to obtain the second target mapping information; The first target mapping information and the second target mapping information are fused to obtain the third target mapping information; The second target video information is mapped based on the third target mapping information and the first target mapping information to obtain the third target video information.

15. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps of the method according to any one of claims 1 to 13.

Images