WO2023284469A1

WO2023284469A1 - Video capture information acquisition method, and video capture and processing instruction method

Info

Publication number: WO2023284469A1
Application number: PCT/CN2022/098711
Authority: WO
Inventors: 申子宜
Original assignee: 上海幻电信息科技有限公司
Priority date: 2021-07-15
Filing date: 2022-06-14
Publication date: 2023-01-19
Also published as: CN115701093A

Abstract

Embodiments of the present application provides a video capture information acquisition method. The method comprises: determining a target video for analysis, the target video corresponding to a time axis representing a video progress; analyzing the target video to obtain a plurality of pieces of capture information; and marking the plurality of pieces of capture information on the time axis, each piece of capture information being distributed at a corresponding position of the time axis, respectively. According to the video capture information acquisition method provided in the embodiments of the present application, capture and editing-related capture information of the target video (high-quality video) is deconstructed, and the capture information obtained by deconstruction is distributed on the time axis according to the position of said information in the target video. On the basis of the capture information distributed on the time axis, various capture information that a client needs to use over time when capturing or editing a video, such as, scene layout, character arrangement and capture means, can be indicated.

Description

Method for acquiring video shooting information, and video shooting and processing instruction method

This application declares the priority of the Chinese patent application filed on July 15, 2021 with the application number 202110801309.0 and titled "Method for Acquiring Video Shooting Information, and Method for Video Shooting and Processing Instructions". The entire content of the Chinese patent application is referred to way is incorporated in this application.

technical field

The embodiments of the present application relate to the field of computer technology, and in particular, to a video shooting information acquisition method, system, computer equipment, and computer-readable storage medium, and to a video shooting and processing instruction method.

Background technique

With the lowering of the threshold for video shooting, more and more users have become creators, shooting and creating videos. High-quality video requires a lot of professional and complex shooting methods. However, the inventor realized that for users who have not learned professional shooting techniques, it is difficult to correctly apply the shooting means, resulting in the inability to shoot satisfactory videos and low efficiency.

Contents of the invention

The purpose of the embodiment of the present application is to provide a video shooting information acquisition method, system, computer equipment and computer-readable storage medium, as well as a video shooting and processing instruction method, which are used to solve the following problems: For users who have not learned professional shooting technology , it is difficult to correctly apply the shooting method, resulting in the inability to shoot a satisfactory video and low efficiency.

An aspect of the embodiments of the present application provides a method for acquiring video shooting information, the method including:

Determine the target video for analysis, and the target video corresponds to a time axis representing video progress;

Analyzing the target video to obtain a plurality of shooting information; and

The plurality of shooting information is marked on the time axis, and each shooting information is respectively distributed at a corresponding position of the time axis.

Optionally, the multiple shooting information includes multiple shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtain the field information of each field according to the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is the same as that of each mirror in the field. corresponding to the location distribution.

performing field segmentation on the target video to obtain multiple fields;

analyzing the plurality of fields to obtain a theme for each field;

Obtaining the field information of each field according to the theme of each field and the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the theme of the field and the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is related to that of each mirror in the field. The position distribution of the mirror in the field corresponds to that.

Optionally, the shooting parameters of each mirror include one or more of the following: scene classification, shooting angle, character information, mirror type, mirror movement operation, and scene.

Optionally, it also includes: generating a plurality of storyboard scripts for each field according to the shooting parameters of each mirror in each field;

Wherein, each mirror in each field corresponds to one or more mirror scripts respectively, and the position distribution of multiple mirror scripts in each field on the time axis is the same as that of each mirror in the field. The location distribution within the field corresponds.

An aspect of the embodiments of the present application further provides a system for obtaining video shooting information, the system comprising:

A determination module is used to determine a target video for analysis, and the target video corresponds to a time axis representing video progress;

An analysis module, configured to analyze the target video to obtain a plurality of shooting information; and

A labeling module, configured to label the plurality of shooting information on the time axis, and each shooting information is respectively distributed at a corresponding position on the time axis.

An aspect of the embodiments of the present application further provides a computer device, the computer device includes a memory, a processor, and computer-readable instructions stored in the memory and operable on the processor, the computer can The following steps are implemented when the read instruction is executed by the processor:

Analyzing the target video to obtain a plurality of shooting information; and

An aspect of the embodiments of the present application further provides a computer-readable storage medium, where computer-readable instructions are stored in the computer-readable storage medium, and the computer-readable instructions can be executed by at least one processor, so that The at least one processor performs the following steps:

Analyzing the target video to obtain a plurality of shooting information; and

An aspect of the embodiments of the present application further provides a video shooting and processing instruction method, the method including:

Receive client request information;

Acquiring target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis represents the time sequence of each shooting information; and

returning the target field information to the client to instruct the client to perform video shooting or video processing according to the respective shooting information and marked positions of the respective shooting information on the time axis.

Optionally, the target field information is field information of a target field in multiple fields; the method further includes pre-acquiring the target field information:

performing field segmentation on the target video to obtain the target field;

performing mirror segmentation on the target field to obtain one or more mirrors;

analyzing each mirror to obtain shooting parameters of each mirror; and

Obtaining the target field information according to the shooting parameters of each mirror;

Wherein, the target field information includes the shooting parameters of each mirror, and the position distribution of the shooting parameters of each mirror on the time axis has the same relationship with the position distribution of each mirror in the target field. Correspondence.

performing field segmentation on the target video to obtain the target field;

analyzing the target field to obtain a theme of the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

Obtain the target field information according to the subject and the shooting parameters of each mirror;

Wherein, the target field information includes the subject and the shooting parameters of each mirror, and the position distribution of the shooting parameters of each mirror on the time axis is related to the position distribution of each mirror in the target field. The location distributions have correspondences.

An aspect of the embodiment of the present application provides a video shooting and processing instruction system, the system includes:

The receiving module is used to receive the request information of the client;

An acquisition module, configured to acquire target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis indicates that each shooting information the chronological order of the information; and

A return module, configured to return the target field information to the client, to instruct the client to perform video shooting or video processing.

An aspect of the embodiments of the present application provides a computer device, the computer device includes a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program Steps for realizing the above-mentioned video shooting and processing instruction method.

An aspect of the embodiments of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program can be executed by at least one processor, so that the at least one The processor executes the steps of the above-mentioned video shooting and processing instruction method.

The video shooting information acquisition method, system, computer equipment, and computer-readable storage medium provided in the embodiments of the present application deconstruct the shooting and editing related shooting information of the target video (high-quality video), and deconstruct the shooting information according to its The positions in the target video are distributed on the time axis. Based on the shooting information distributed on the time axis, the client can be instructed to use various shooting information as time progresses when shooting or editing a video, such as scene layout, character layout, shooting means, etc. In this application, not only can the client be instructed to shoot or edit a video similar to a high-quality video, but also improve the efficiency of shooting or editing.

Description of drawings

FIG. 1 schematically shows an application environment diagram of a method for acquiring video shooting information according to an embodiment of the present application;

FIG. 2 schematically shows a flowchart of a method for acquiring video shooting information according to Embodiment 1 of the present application;

Fig. 3 is the sub-step flowchart of step S202 in Fig. 2;

Fig. 4 is the sub-step flowchart of step S202 in Fig. 2;

FIG. 5 schematically shows a flow chart of newly added steps of the method for acquiring video shooting information according to Embodiment 1 of the present application;

FIG. 6 schematically shows a specific operation example diagram of the video shooting information acquisition method based on Embodiment 1 of the present application;

FIG. 7 schematically shows a flow chart of a video shooting and processing instruction method according to Embodiment 2 of the present application;

FIG. 8 schematically shows a specific operation example diagram based on Embodiment 2 of the present application;

FIG. 9 schematically shows a block diagram of a system for acquiring video shooting information according to Embodiment 3 of the present application;

FIG. 10 schematically shows a block diagram of a system for acquiring video shooting information according to Embodiment 4 of the present application;

FIG. 11 schematically shows a schematic diagram of a hardware architecture of a computer device according to Embodiment 5 of the present application.

detailed description

In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes, and should not be understood as indicating or implying their relative importance or implicitly indicating the indicated technical features quantity. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In addition, the technical solutions of the various embodiments can be combined with each other, but it must be based on the realization of those skilled in the art. When the combination of technical solutions is contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist , nor within the scope of protection required by the present application.

The inventor understands that high-quality video shooting involves information such as scene layout, lens distribution, and mirror movement distribution, and requires professional film and television creation learning, and video creation is based on rich shooting experience. details as follows:

High-quality video includes the following aspects:

(1) Video quality, based on the visual sense, by using professional shooting equipment to record the video in a professional shooting scene;

(2) Shooting content, shooting videos based on professionally designed scripts;

(3) Shooting technology, based on professional shooting skills, screen layout, composition and scene distribution, etc., to shoot.

To sum up, in order to shoot high-quality videos, there must be multiple elements, not only based on high-demand software and hardware, but also video creators need to have professional shooting skills, which virtually raises the threshold for high-quality video creation.

In view of this, this application aims to use video understanding technology to guide users to shoot or edit high-quality videos during the video creation process, for example: screening high-quality videos through intelligent means, and using artificial intelligence related algorithms to build Quantitative analysis of shooting skills related to "high-quality" video. Users can obtain shooting information of similar types of high-quality videos by inputting relevant demand keywords, such as the necessary distribution of elements such as scene switching on the time axis, camera operation, shooting angle, and camera switching under the story line. Therefore, by providing shooting information, users can learn professional shooting techniques for video creation, so as to quickly and specifically perform video creation, lowering the threshold for video creation. details as follows:

First, analyze high-quality videos.

The high-quality video can include: through professional video shooting hardware, high-definition video with excellent picture quality; and through professional video shooting means (layout design): field design, mirror distribution, various scene Other distribution, operation of mirror movement, image stabilizer or post-use image stabilization technology to improve video quality.

Second, through artificial intelligence related algorithms, detect scenes, mirrors, scenes, mirrors, and people in the field, and in the time direction, through points (for scenes, characters, scenes) and segments (for mirrors) The time distribution of each shooting element is counted.

Third, users can determine the personalized shooting theme, and find high-quality videos that match it according to the shooting theme. The user shoots or records a video guided by each shooting element of the matched high-quality video, so as to shoot a similar type of high-quality video. The user can also make fine-tuning on the basis of each shooting element, and shoot or record a video based on the fine-tuning.

Fourth, the user can also search for matching (similar) high-quality video shooting techniques (such as scene selection, camera movement mode) after shooting the video, and edit the video according to the high-quality video shooting techniques so that the high-quality The shooting skills of the video are applied and reflected in the video to efficiently improve the video quality and lower the threshold of creation.

The present application provides a plurality of embodiments to introduce the video shooting information acquisition solution and the video shooting or processing instruction solution, and refer to the following for details.

In the description of the present application, it should be understood that the numerals before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, so they should not be construed as limitations on the present application.

The following is an explanation of the terms used in this application:

Instructions, including controls, guidance and/or prompts.

AI (Artificial Intelligence, artificial intelligence) pull film: use artificial intelligence to detect video content and shooting methods. In this way, the shooting parameters of the video are obtained, such as: shooting skills and related statistical distribution information, such as the content of each shot, scene scheduling, camera movement, scene, editing, sound, picture, rhythm, performance, camera position, etc. .

A mirror, representing a video segment with a temporal start and a temporal end. A feature film generally consists of 400-600 shots.

A field corresponds to a video bridge segment, which can be composed of one or more mirrors.

Scene difference: The distance between the camera and the subject is different, resulting in the difference in the range of the subject in the camera video recorder. Scenes from near to far include: close-up (referring to the human body above the shoulder), close-up (referring to the human body above the chest), middle shot (referring to the human body above the knee), panorama (the entire human body and the surrounding environment), and long-range view (referring to the human body above the knee). environment of the subject).

Mirror movement: the movement mode of the shooting device such as pushing, pulling, shaking, moving, and stilling of the lens during shooting.

Storyboard script refers to various video media such as movies, animations, TV dramas, advertisements, MTV, etc. Before the actual shooting, the composition of the image is explained in the form of a story grid, and the continuous screen is used as a mirror Decompose it as a unit, and mark the camera movement method, duration, dialogue, special effects, etc. In this way, the required shooting content is briefly recorded in the early stage of shooting, so as to remind each storyboard during the shooting process.

Fig. 1 schematically shows a schematic diagram of an environment application according to an embodiment of the present application. As shown in Figure 1:

The computer device 10000 can connect to the client 30000 via the network 20000 .

The computer device 10000 may provide services, such as providing shooting information, to control or prompt the client 30000 to take a shooting action.

Computer equipment 10000 may be located in a data center, such as a single site, or distributed among different geographical locations (e.g., across multiple sites). The computer device 10000 may provide services via one or more networks 20000 . Network 20000 includes various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices and/or the like. Network 20000 may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and the like. Network 20000 may include wireless links, such as cellular links, satellite links, Wi-Fi links, and the like.

Computer device 10000 may be implemented by one or more computing nodes. One or more compute nodes may include virtualized compute instances. Virtualized computing instances may include virtual machines, such as emulations of computer systems, operating systems, servers, and the like. The compute node may load the virtual machine by the compute node based on the virtual image and/or other data defining the specific software (eg, operating system, application-specific, server) used for emulation. As the demand for different types of processing services changes, different virtual machines can be loaded and/or terminated on one or more computing nodes. A hypervisor can be implemented to manage the use of different virtual machines on the same compute node.

Client 30000 may be configured to access computer device 10000 content and services. The client 30000 may include any type of electronic device supporting a photography function, such as a mobile device, a tablet device, a video camera, and the like.

The client 30000 can output shooting information (such as technique quantification information) to the user.

The following will introduce specific technical solutions through multiple embodiments. This scheme can be implemented by the computer device 10000 .

Embodiment one

Fig. 2 schematically shows a flowchart of a method for acquiring video shooting information according to Embodiment 1 of the present application.

As shown in FIG. 2, the method for obtaining video shooting information may include steps S200-S204, wherein:

In step S200, a target video for analysis is determined, and the target video is corresponding to a time axis representing video progress.

Described target video, can be based on the video manuscript of various video formats, for example: AVI (Audio Video Interleaved, audio video is interleaved) format, H.264/AVC (Advanced Video Coding, advanced video coding), H.265/HEVC (High Efficiency Video Coding, high efficiency video coding) H.265 format, etc.

The target video can be preferably a high-quality video, such as a high-definition video with excellent image quality shot by professional video shooting hardware; and through professional video shooting means (layout design: field design, mirror distribution, various The distribution of different scenes, the operation of mirror movement) or the video quality improved by image stabilization technology in the later stage.

Step S202, analyzing the target video to obtain a plurality of shooting information.

The multiple shooting information may correspond to various shooting elements involved in video shooting or editing. That is, according to the distribution of the various shooting elements in the target video (such as the total time of appearance and duration), the layout of the shooting means (skills) of the target video in the target video can be analyzed shooting information, etc.

The target video can be analyzed in units of "field" and "mirror" to obtain the plurality of shooting information.

(1) Take "field" as a unit to obtain the theme of each field. As an example, the theme of each field can be identified by ECO (Efficient Convolutional Network for Online Video Understanding End-to-End Dense Video Captioning with Masked Transformer, Efficient Convolutional Network for Online Video Understanding).

(2) Taking "mirror" as a unit, obtain the scene, shooting angle, character information, mirror type, mirror movement, and scene of each mirror.

Scene types can include: long shot, panoramic shot, medium shot, close shot, close-up, and close-up.

Scenes can include: indoors and outdoors. The scene can be further refined into offices, squares, coffee shops, etc.

Character information may include: character position, posture (orientation, etc.), identity (man, woman, old man, policeman, lawyer, etc.).

As an example, the above shooting information is calculated, estimated and counted through artificial intelligence related algorithms. Such as:

The scene and movement of each shot can be identified through a unified framework for Shot Type Classification Based on Subject Centric Lens (Unified Framework for Shot Type Classification Based on Subject Centric Lens).

The shooting angle of each mirror can be identified by performing shooting angle detection through Back to the Feature: Learning Robust Camera Localization from Pixels to Pose.

The orientation of each person in each mirror can be detected through fine-grained head pose estimation (Towards Fast, Accurate and Stable 3D Dense Face Alignment Fine-Grained Head Pose Estimation Without Keypoints).

The identity of each person in each mirror can be detected through the face recognition model (Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation Person Search in Videos with One Portrait Through Visual and Temporal Links).

Based on the above exemplary content, the quantity and distribution of each shooting information in the target video can be known.

Step S204, marking the plurality of shooting information on the time axis, and each shooting information is respectively distributed at a corresponding position on the time axis.

That is, each shooting information is displayed in a distributed manner according to the direction of the time axis.

The video shooting information acquisition method provided in this embodiment deconstructs the shooting and editing related shooting information of the target video (high-quality video), and distributes the deconstructed shooting information on the time axis according to its position in the target video. Based on the shooting information distributed on the time axis, the client can be instructed to use various shooting information as time progresses when shooting or editing a video, such as scene layout, character layout, shooting means, etc., to shoot or edit Produce videos similar to high-quality videos and improve shooting or editing efficiency.

As an example, the multiple shooting information includes multiple shooting parameters. As shown in Figure 3, the step S202 may include: step S300, performing field segmentation on the target video to obtain multiple fields; step S302, performing mirror segmentation on the multiple fields respectively, to obtain multiple mirror images , each field includes one or more mirrors; step S304, analyze each mirror in the multiple mirrors to obtain the shooting parameters of each mirror; and step S306, according to each field The shooting parameters of each mirror in the field are obtained to obtain the field information of each field; wherein, the field information of each field includes the shooting parameters of each mirror in the field, and the shooting parameters of each mirror in the field are listed in the The position distribution on the time axis corresponds to the position distribution of each mirror in the field in the field. In this embodiment, the target video is analyzed in units of "field" and "mirror", so as to obtain the shooting parameters of each mirror in different video bridge segments in the target video, which is convenient for storage, classification and user query.

As an example, the multiple shooting information includes multiple shooting parameters. As shown in Figure 4, the step S202 may include: step S400, performing field segmentation on the target video to obtain multiple fields; step S402, performing mirror segmentation on the multiple fields respectively, to obtain multiple mirror images , each field includes one or more mirrors; step S404, analyzing the multiple fields to obtain the subject of each field; step S406, analyzing each mirror in the multiple mirrors, to obtain the shooting parameters of each mirror; and step S408, according to the theme of each field and the shooting parameters of each mirror in each field, obtain the field information of each field; wherein, the The above-mentioned field information of each field includes the theme of the field and the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is related to the position distribution of each mirror in the field in the field. Corresponding to the location distribution within the field. In this embodiment, the target video is analyzed in units of "field" and "mirror", so as to obtain the themes of different video segments in the target video and shooting parameters of each mirror in different video segments , which is convenient for storage, classification and user query based on themes of different bridge sections.

As an example, the shooting parameters of each mirror include one or more of the following: scene classification, shooting angle, character information, mirror type, mirror movement operation, and scene.

As an example, a graphical storyboard script can be generated for each scene to better prompt the user.

As shown in FIG. 5 , the method for obtaining video shooting information may also include: step S500, generating a plurality of storyboard scripts for each field according to the shooting parameters of each mirror in each field; wherein, Each mirror in each field corresponds to one or more storyboard scripts, and the position distribution of the multiple mirror scripts in each field on the time axis is the same as that of each mirror in the field in the field. corresponding to the location distribution within . details as follows:

(1) Corresponding elements and element vector information can be generated according to character information, etc., and the element vector information includes the size, posture, and relative position of the element in the key frame in the corresponding mirror. The above character information can be divided by character identity, such as children, old people, etc., and can be divided by character occupation, such as policeman and lawyer.

(2) According to the element category of the element, the vector element associated with the element category may be obtained from a vector element material library.

(3) According to the scene in the corresponding mirror, obtain the specified canvas matching the scene from the canvas material library.

(4) According to the element vector information, each vector element is set on a designated canvas to generate a storyboard. For example: according to the size of the element, determine the size of the vector element in the designated canvas; determine the posture of the vector element in the designated canvas according to the posture of the element; Determine the relative position of the vector element in the specified canvas based on the relative position in the reference image.

By identifying the elements in the key frames in the corresponding mirror, and setting the matching vector elements to the specified canvas, the storyboard script in the form of vector graphics is obtained, which makes it more efficient and easy to make storyboard scripts, and effectively improves the user experience. .

Exemplarily, the scene type, shooting angle, character information, mirror type, and mirror operation can be added to the specified canvas in text form.

Exemplarily, the storyboard script can be an editable vector diagram, which can be modified by vectorization according to user needs (habits). The vectorization modification includes at least one of the following: modifying the size of the vector element, modifying the pose of the vector element, modifying the relative position of the vector element in the specified canvas, deleting the vector element or adding a new Vector elements. Here, the user can realize the personalized provision of the storyboard.

Exemplarily, through user habits and portraits, etc., adjust the arrangement of vector elements in the designated canvas to more accurately generate a storyboard script that conforms to the user's drawing habits, and further improve script creation efficiency and user stickiness.

For ease of understanding, an operation example is provided below in conjunction with Figure 6:

S600: Find a high-quality video as a target video.

S602: Divide the target video to obtain multiple fields. As shown in FIG. 6, the target video can be divided into multiple fields.

S604: Divide each field to obtain multiple mirrors. As shown in FIG. 6, one scene is composed of 5 mirrors.

S606: Perform various detections on each mirror to deconstruct and obtain various shooting information, that is, information corresponding to various shooting/editing elements.

Such as mirror movement detection, scene detection, character analysis (character identity analysis, character orientation analysis), shooting angle analysis, etc.

S608. Obtain field information of each field in units of fields.

The field information of each field includes the detection information of each mirror in this field, such as the movement of the mirror, scene, characters, shooting angle, etc.

The above various information is marked on the time axis.

When multiple people need to shoot or edit the same video at the same time, it can be sent to each client in segments according to various information marked on the time axis, respectively instructing different clients to perform different operations to achieve collaboration.

When there is no multi-person, multiple or multi-angle shooting (for example, there is only one creator, or one shooting device, or scenes such as concert recordings that cannot be repeated multiple times), after a single video , the single video can be edited based on the above field information to obtain multiple videos switched between different scenes.

Embodiment two

This embodiment provides a video shooting and processing instruction method, and some technical details and effects can be referred to above.

Fig. 7 schematically shows a flow chart of a video shooting and processing instruction method according to Embodiment 2 of the present application.

As shown in FIG. 7, the video shooting and processing instruction method may include steps S700-S704, wherein:

Step S700, receiving request information from the client.

The request information may include the following:

(1) Text information, including shooting scene, theme, shooting location, scene, etc.;

(2) The video information that has been taken, such as video tags, etc.

Step S702, acquire target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis represents the location of each shooting information Chronologically.

According to the requested information, the most matching video bridge segment (target field) is searched from the database.

The target field has the distribution on the time axis of the shooting information (mirrors, scenes, mirrors, characters, etc.) corresponding to the bridge segment of the video.

Step S704, returning the target field information to the client to instruct the client to perform video shooting or video processing according to the respective shooting information and the marked positions of the respective shooting information on the time axis .

The client can guide the user to shoot and edit or automatically shoot and edit according to the field information of the target field. Take automatic editing as an example: the video of the same scene (panorama) is captured, and the shooting information searched is referred to later, and it is edited into a diversified video with multiple scene switching, so as to obtain an effect similar to that of a high-quality video bridge.

The video shooting and processing instruction method provided by this embodiment finds the high-quality video bridge section that meets the user's shooting period according to the theme and content of the user's input of wanting to shoot or edit, and deconstructs the shooting information (field information) obtained by deconstructing the high-quality video bridge section. ) is returned to the client, and the shooting information obtained by the deconstruction is distributed on the time axis. Based on the shooting information distributed on the time axis, the client can be instructed to use various shooting information as time progresses when shooting or editing a video, such as scene layout, character layout, shooting means, editing, etc.

As an example, the target field information is field information of a target field in multiple fields; the method further includes acquiring the target field information in advance:

performing field segmentation on the target video to obtain the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

performing field segmentation on the target video to obtain the target field;

analyzing the target field to obtain a theme of the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

For ease of understanding, an operation example is provided below in conjunction with Figure 8:

S800: The client 30000 receives search content input by a user, and initiates a search request based on the search content.

The search content may include video topics, shooting locations, and the like.

S802: The computer device 10000 searches the database according to the search request.

S804: The computer device 10000 returns to the client 30000 the searched field information (which may include a plurality of shooting information, each shooting information is distributed on the time axis) of the video segment most relevant to the search content.

S806: The client 30000 performs shooting or editing according to each shooting information and the position of each shooting information on the time axis.

S808: The client 30000 generates a video with high-quality shooting means and content according to the shooting or editing results.

Embodiment Three

FIG. 9 schematically shows a block diagram of a video shooting information acquisition system according to Embodiment 3 of the present application. The video shooting information acquisition system can be divided into one or more program modules, and one or more program modules are stored in a storage medium. and executed by one or more processors to complete the embodiments of the present application. The program modules referred to in the embodiments of the present application refer to a series of computer-readable instruction segments capable of accomplishing specific functions. The following description will specifically introduce the functions of the program modules in the embodiments of the present application.

As shown in FIG. 9, the video shooting information acquisition system 900 may include a determination module 910, an analysis module 920, and an annotation module 930, wherein:

Determining module 910, is used for determining the target video that is used for analysis, and described target video is corresponding with the time axis that represents video progress;

An analysis module 920, configured to analyze the target video to obtain a plurality of shooting information; and

The marking module 930 is configured to mark the plurality of shooting information on the time axis, and each shooting information is respectively distributed at a corresponding position on the time axis.

As an example, the multiple shooting information includes multiple shooting parameters; the analyzing module 920 is further configured to:

performing field segmentation on the target video to obtain multiple fields;

analyzing the plurality of fields to obtain a theme for each field;

As an example, the system also includes a script generation module for:

According to the shooting parameters of each mirror in each field, a plurality of shot scripts are respectively generated for each field;

Embodiment four

FIG. 10 schematically shows a block diagram of a video shooting and processing instruction system according to Embodiment 4 of the present application. The video shooting and processing instruction system can be divided into one or more program modules, and one or more program modules are stored in stored in a storage medium and executed by one or more processors to complete the embodiments of the present application. The program modules referred to in the embodiments of the present application refer to a series of computer-readable instruction segments capable of accomplishing specific functions. The following description will specifically introduce the functions of the program modules in the embodiments of the present application.

As shown in Figure 10, the video shooting and processing instruction system 1000 may include a receiving module 1010, an obtaining module 1020 and a returning module 1030, wherein:

A receiving module 1010, configured to receive request information from the client;

The obtaining module 1020 is configured to obtain target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis indicates that each the chronological order of the capture information; and

Returning module 1030, configured to return the target field information to the client to instruct the client to perform video shooting according to the respective shooting information and the marked positions of the respective shooting information on the time axis Or video processing.

Optionally, the target field information is field information of a target field in multiple fields; the system further includes a preset acquisition module, configured to pre-acquire the target field information:

performing field segmentation on the target video to obtain the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

performing field segmentation on the target video to obtain the target field;

analyzing the target field to obtain a theme of the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

Embodiment five

FIG. 11 schematically shows a schematic diagram of a hardware architecture of a computer device 10000 according to Embodiment 5 of the present application. In this embodiment, the computer device 10000 is a device capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions. For example, it may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers) and the like. As shown in FIG. 11 , the computer device 10000 at least includes but is not limited to: a memory 10010 , a processor 10020 , and a network interface 10030 that can communicate with each other through a system bus. in:

The memory 10010 includes at least one type of computer-readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000 , such as a hard disk or memory of the computer device 10000 . In some other embodiments, the memory 10010 can also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, referred to as SMC), a secure digital (Secure Digital (referred to as SD) card, flash memory card (Flash Card) and so on. Certainly, the memory 10010 may also include both an internal storage module of the computer device 10000 and an external storage device thereof. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed in the computer device 10000, such as program codes for methods of acquiring video shooting information, video shooting and processing instruction methods, and the like. In addition, the memory 10010 can also be used to temporarily store various types of data that have been output or will be output.

The processor 10020 may be a central processing unit (Central Processing Unit, CPU for short), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 10020 is generally used to control the overall operation of the computer device 10000 , such as performing control and processing related to data interaction or communication with the computer device 10000 . In this embodiment, the processor 10020 is configured to run program codes stored in the memory 10010 or process data.

The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 with an external terminal through a network, and establish a data transmission channel and a communication link between the computer device 10000 and an external terminal. The network can be Intranet, Internet, Global System of Mobile Communication (GSM for short), Wideband Code Division Multiple Access (WCDMA for short), 4G network , 5G network, Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.

It should be noted that FIG. 11 only shows a computer device having components 10010-10030, but it should be understood that implementing all of the illustrated components is not a requirement and that more or fewer components may instead be implemented.

In this embodiment, the video shooting information acquisition method, video shooting and processing instruction method stored in the memory 10010 can also be divided into one or more program modules, and processed by one or more processors (this embodiment is a processing module) device 10020) to complete the embodiment of this application.

Embodiment six

The embodiment of the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the following steps are implemented:

Analyzing the target video to obtain a plurality of shooting information; and

Marking the plurality of shooting information on the time axis, each shooting information is respectively distributed at a corresponding position on the time axis;

Alternatively, the computer readable instructions implement the following steps when executed by the processor:

Receive client request information;

In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory ( ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), Magnetic Memory, Magnetic Disk, Optical Disk, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as a hard disk or a memory of the computer device. In some other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, referred to as SMC), a secure digital ( Secure Digital (referred to as SD) card, flash memory card (Flash Card), etc. Of course, the computer-readable storage medium may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is usually used to store the operating system and various application software installed on the computer device, such as the program codes of the video shooting information acquisition method, video shooting and processing instruction method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computing devices, and they can be concentrated on a single computing device, or distributed among multiple computing devices. Optionally, they may be implemented in program code executable by a computing device, thereby, they may be stored in a storage device to be executed by a computing device, and in some cases, may be implemented in a code different from that described herein The steps shown or described are executed in sequence, or they are fabricated into individual integrated circuit modules, or multiple modules or steps among them are fabricated into a single integrated circuit module for implementation. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structures or equivalent process transformations made by using the description of the application and the accompanying drawings are directly or indirectly used in other related technical fields. , are all included in the patent protection scope of the present application in the same way.

Claims

A method for acquiring video shooting information, wherein the method includes:

Determine the target video for analysis, and the target video corresponds to a time axis representing video progress;

Analyzing the target video to obtain a plurality of shooting information; and

The plurality of shooting information is marked on the time axis, and each shooting information is respectively distributed at a corresponding position of the time axis.
The video shooting information acquisition method according to claim 1, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtain the field information of each field according to the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is the same as that of each mirror in the field. corresponding to the location distribution.
The video shooting information acquisition method according to claim 1 or 2, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing the plurality of fields to obtain a theme for each field;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtaining the field information of each field according to the theme of each field and the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the theme of the field and the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is related to that of each mirror in the field. The position distribution of the mirror in the field corresponds to that.
The video shooting information acquisition method according to claim 2 or 3, wherein the shooting parameters of each mirror include one or more of the following: scene classification, shooting angle, character information, mirror type, mirror movement operation, scene .
The video shooting information acquisition method according to any one of claims 2-4, further comprising:

According to the shooting parameters of each mirror in each field, a plurality of shot scripts are respectively generated for each field;

Wherein, each mirror in each field corresponds to one or more mirror scripts respectively, and the position distribution of multiple mirror scripts in each field on the time axis is the same as that of each mirror in the field. The location distribution within the field corresponds.
A video shooting information acquisition system, wherein the system includes:

A determination module is used to determine a target video for analysis, and the target video corresponds to a time axis representing video progress;

An analysis module, configured to analyze the target video to obtain a plurality of shooting information; and

A labeling module, configured to label the plurality of shooting information on the time axis, and each shooting information is respectively distributed at a corresponding position on the time axis.
A computer device, the computer device comprising a memory, a processor, and computer-readable instructions stored on the memory and operable on the processor, the computer-readable instructions are executed by the processor to implement the following steps :

Determine the target video for analysis, and the target video corresponds to a time axis representing video progress;

Analyzing the target video to obtain a plurality of shooting information; and

The plurality of shooting information is marked on the time axis, and each shooting information is respectively distributed at a corresponding position of the time axis.
The computer device according to claim 7, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtain the field information of each field according to the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is the same as that of each mirror in the field. corresponding to the location distribution.
The computer device according to claim 7 or 8, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing the plurality of fields to obtain a theme for each field;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtaining the field information of each field according to the theme of each field and the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the theme of the field and the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is related to that of each mirror in the field. The position distribution of the mirror in the field corresponds to that.
The computer device according to claim 7 or 8, wherein the shooting parameters of each mirror include one or more of the following: scene classification, shooting angle, character information, mirror type, mirror movement operation, and scene.
The computer device according to any one of claims 8-10, wherein the computer-readable instructions further implement the following steps when executed by the processor:

According to the shooting parameters of each mirror in each field, a plurality of shot scripts are respectively generated for each field;

Wherein, each mirror in each field corresponds to one or more mirror scripts respectively, and the position distribution of multiple mirror scripts in each field on the time axis is the same as that of each mirror in the field. The location distribution within the field corresponds.
A computer-readable storage medium, wherein computer-readable instructions are stored in the computer-readable storage medium, and the computer-readable instructions can be executed by at least one processor, so that the at least one processor performs the following step:

Determine the target video for analysis, and the target video corresponds to a time axis representing video progress;

Analyzing the target video to obtain a plurality of shooting information; and

The plurality of shooting information is marked on the time axis, and each shooting information is respectively distributed at a corresponding position of the time axis.
The computer-readable storage medium according to claim 12, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtain the field information of each field according to the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is the same as that of each mirror in the field. corresponding to the location distribution.
The computer-readable storage medium according to claim 12 or 13, wherein the plurality of shooting information includes a plurality of shooting parameters;

The target video is analyzed to obtain multiple shooting information, including:

performing field segmentation on the target video to obtain multiple fields;

performing mirror segmentation on the plurality of fields respectively to obtain a plurality of mirrors, each field comprising one or more mirrors;

analyzing the plurality of fields to obtain a theme for each field;

analyzing each of the plurality of mirrors to obtain shooting parameters of each of the mirrors; and

Obtaining the field information of each field according to the theme of each field and the shooting parameters of each mirror in each field;

Wherein, the field information of each field includes the theme of the field and the shooting parameters of each mirror in the field, and the position distribution of the shooting parameters of each mirror in the field on the time axis is related to that of each mirror in the field. The position distribution of the mirror in the field corresponds to that.
A video shooting and processing instruction method, wherein the method includes:

Receive client request information;

Acquiring target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis represents the time sequence of each shooting information; and

returning the target field information to the client to instruct the client to perform video shooting or video processing according to the respective shooting information and marked positions of the respective shooting information on the time axis.
The video shooting and processing instruction method according to claim 15, wherein the target field information is field information of a target field in a plurality of fields; the method also includes pre-acquiring the target field information:

performing field segmentation on the target video to obtain the target field;

performing mirror segmentation on the target field to obtain one or more mirrors;

analyzing each mirror to obtain shooting parameters of each mirror; and

Obtaining the target field information according to the shooting parameters of each mirror;

Wherein, the target field information includes the shooting parameters of each mirror, and the position distribution of the shooting parameters of each mirror on the time axis has the same relationship with the position distribution of each mirror in the target field. Correspondence.
The video shooting and processing instruction method according to claim 15 or 16, wherein the target field information is field information of a target field in a plurality of fields; the method also includes pre-acquiring the target field information:

performing field segmentation on the target video to obtain the target field;

performing mirror segmentation on the target field to obtain one or more mirrors;

analyzing the target field to obtain a theme of the target field;

analyzing each mirror to obtain shooting parameters of each mirror; and

Obtain the target field information according to the subject and the shooting parameters of each mirror;

Wherein, the target field information includes the subject and the shooting parameters of each mirror, and the position distribution of the shooting parameters of each mirror on the time axis is related to the position distribution of each mirror in the target field. The location distributions have correspondences.
A video shooting and processing instruction system, wherein the system includes:

The receiving module is used to receive the request information of the client;

An acquisition module, configured to acquire target field information according to the request information, the target field information includes a plurality of shooting information marked on the same time axis, and the position of each shooting information on the time axis indicates that each shooting information the chronological order of the information; and

A return module, configured to return the target field information to the client, to instruct the client to perform video shooting or video processing.
A computer device, the computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor executing the computer program is used to implement any of claims 15 to 17 A step in the video shooting and processing instruction method.
A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and the computer program can be executed by at least one processor, so that the at least one processor executes any of claims 15 to 17. A step in the video shooting and processing instruction method.