CN112711966B

CN112711966B - Video file processing method and device and electronic equipment

Info

Publication number: CN112711966B
Application number: CN201911018751.5A
Authority: CN
Inventors: 李鹏宇
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-10-24
Filing date: 2019-10-24
Publication date: 2024-03-01
Anticipated expiration: 2039-10-24
Also published as: CN112711966A

Abstract

The application provides a processing method and device of video files and electronic equipment, wherein the processing method of the video files comprises the following steps: obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices; obtaining a target subject from at least one video file of the plurality of video files for the same target object; obtaining video clip data corresponding to the target subject from at least two video files in the plurality of video files aiming at the same target object; a target video file corresponding to the target subject is obtained based on the video clip data corresponding to the target subject. The target video file corresponding to the target main body can be obtained by adopting the mode, and the problems that the short video obtained by the video processing technology in the prior art is not a short video aiming at a single target main body and is unfavorable for multi-angle monitoring of the same target main body at the same time can be solved.

Description

Video file processing method and device and electronic equipment

Technical Field

The present application relates to the field of digital processing, and in particular, to a method and an apparatus for processing a video file, and an electronic device.

Background

With the continuous development of digital technology, real-time monitoring is increasingly used in daily life. The resulting video content is also increasing. As is well known, video content is used primarily for people to query for useful information for monitoring an environment. For example, in intelligent monitoring of a home, video segment information of a target subject or object of interest in a monitored video can be found from video recording content. Or in public environment monitoring, video segment information of the interested target main body or object is found in the video recording content of the real-time monitoring so as to be used for tracking the motion trail information of the interested target main body or object. However, both of the above situations require finding video segments where a target subject or object of interest appears in a large volume of video recording content.

In the prior art, a video segment of an interested target body or object is obtained mainly by concentrating long videos into short videos. Specifically, a video segment corresponding to a target object or object of interest, which will appear in a long video, may be cut off. Since in long videos, there may be more than one video segment corresponding to the object of interest or the object of interest, when there is more than one video segment corresponding to the object of interest or the object of interest, each video segment needs to be searched. It is apparent that the search process may cause inconvenience to the user. Although in some technologies, the video segments corresponding to the target objects or the objects of interest are spliced to obtain a corresponding short video, the short video is simply spliced to different video segments, wherein the spliced video segments also contain a plurality of target objects and are not short videos for a single target object. In addition, the existing long videos are all based on a single camera device, so that the multi-angle monitoring of the same target main body is not facilitated at the same time.

Disclosure of Invention

The application provides a processing method of video files, which aims to solve the problems that short videos obtained by adopting the existing video processing technology are not short videos aiming at a single target main body and are not beneficial to multi-angle monitoring of the same target main body at the same time. The application also provides a processing device of the video file, and electronic equipment and computer media corresponding to the processing device. The application also provides two video file processing methods and devices.

The application provides a processing method of a video file, which comprises the following steps:

obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices;

obtaining a target subject from at least one video file of the plurality of video files for the same target object;

obtaining video clip data corresponding to the target subject from at least two video files in the plurality of video files aiming at the same target object;

and obtaining a target video file corresponding to the target subject based on the video clip data corresponding to the target subject.

Optionally, the obtaining a plurality of video files for the same target object provided by a plurality of video data obtaining devices includes:

Issuing a request to each of the plurality of video data acquisition apparatuses to acquire a plurality of video files for the same target object;

receiving video files for the same target object transmitted by each of the plurality of video data acquisition devices, and determining the video files for the same target object transmitted by each of the plurality of video data acquisition devices as a plurality of video files.

obtaining a plurality of video files provided by a plurality of video data acquisition devices;

classifying the plurality of video files according to the target objects to obtain the corresponding relation between the target objects and the plurality of video files;

and obtaining a plurality of video files aiming at the same target object from the plurality of video files according to the characteristics of the target object and the corresponding relation between the target object and the plurality of video files.

Optionally, the classifying the plurality of video files according to the target object to obtain a corresponding relationship between the target object and the plurality of video files includes:

respectively obtaining different target objects appearing in the plurality of video files;

Respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object;

recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object;

and determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and the plurality of video files.

Optionally, the obtaining the target body from at least one video file of the plurality of video files for the same target object includes:

obtaining the target object from at least one video file in the plurality of video files aiming at the same target object;

obtaining all target subjects in the target object;

and selecting one target subject from all target subjects as the target subject.

Optionally, the obtaining video clip data corresponding to the target subject from at least two video files in the plurality of video files for the same target object includes:

searching video files containing the target subject from at least two video files in the plurality of video files aiming at the same target subject according to the target characteristics of the target subject;

Determining time information of the target subject in the video file containing the target subject;

and obtaining video clip data corresponding to the target main body according to the time information.

Optionally, the searching the video file containing the target subject from at least two video files in the plurality of video files for the same target object according to the target characteristics of the target subject includes:

obtaining a target feature screening threshold of the target subject;

searching video files meeting the target feature screening threshold from at least two video files in the plurality of video files aiming at the same target object; and determining the video file meeting the target feature screening threshold as a video file containing the target main body.

Optionally, the obtaining, based on the video clip data corresponding to the target subject, a target video file corresponding to the target subject includes:

respectively obtaining time information of video clip data corresponding to the target main body;

splicing the video clip data according to the time information of the video clip data and the time sequence to obtain a spliced video file; and determining the spliced video file as a target video file corresponding to the target main body.

respectively obtaining video frames of video clip data corresponding to the target main body;

obtaining time information of the video frame;

splicing the video frames according to the time information of the video frames and the time sequence to obtain a spliced video file; and determining the spliced video file as a target video file corresponding to the target main body.

Correspondingly, the application provides a processing device of the video file, which comprises:

a video file acquisition unit configured to acquire a plurality of video files for the same target object provided by a plurality of video data acquisition devices;

a target subject obtaining unit configured to obtain a target subject from at least one video file of the plurality of video files for the same target object;

a video clip data obtaining unit, configured to obtain video clip data corresponding to the target subject from at least two video files in the plurality of video files for the same target object;

and the target video file acquisition unit is used for acquiring a target video file corresponding to the target subject based on the video clip data corresponding to the target subject.

The application also provides a processing method of the video file, which comprises the following steps:

and carrying out video concentration processing on the plurality of video files to obtain at least one target concentrated video file, wherein the target concentrated video file comprises video fragment data of at least two video files in the plurality of video files.

Optionally, the video concentration processing is performed on the plurality of video files to obtain at least one target concentrated video file, including:

Respectively obtaining time information of the plurality of video files;

splicing the video files according to time information of the video files and time sequence to obtain spliced video files; and determining the spliced video file as a target concentrated video file.

Optionally, the method further comprises:

the video concentration processing is performed on the plurality of video files to obtain at least one target concentrated video file, including:

obtaining a concentrated video file corresponding to the target subject based on the video clip data corresponding to the target subject; and determining the concentrated video file corresponding to the target main body as a target concentrated video file.

Correspondingly, the application also provides a processing device of the video file, which comprises the following steps:

And the target concentrated video file acquisition unit is used for carrying out video concentration processing on the plurality of video files to obtain at least one target concentrated video file, wherein the target concentrated video file comprises video fragment data of at least two video files in the plurality of video files.

obtaining an original video file;

obtaining a target subject from the original video file;

obtaining video clip data corresponding to the target subject from the original video file;

and obtaining a concentrated video file corresponding to the target subject based on the video clip data corresponding to the target subject.

Optionally, the obtaining the original video file includes: and obtaining a plurality of video files aiming at the same target object provided by a plurality of video data acquisition devices, and determining the plurality of video files aiming at the same target object as the original video file.

Optionally, the obtaining the target body from the original video file includes:

Obtaining all target subjects in the target object;

Optionally, the obtaining video clip data corresponding to the target subject from the original video file includes:

searching video files containing the target subject from at least two video files in the original video files according to the target characteristics of the target subject;

Optionally, the searching the video file containing the target subject from at least two video files in the original video files according to the target characteristics of the target subject includes:

obtaining a target feature screening threshold of the target subject;

searching video files meeting the target feature screening threshold from at least two video files in the original video files; and determining the video file meeting the target feature screening threshold as a video file containing the target main body.

Optionally, the obtaining, based on the video clip data corresponding to the target subject, a concentrated video file corresponding to the target subject includes:

splicing the video clip data according to the time information of the video clip data and the time sequence to obtain a spliced video file; and determining the spliced video file as a concentrated video file corresponding to the target main body.

obtaining time information of the video frame;

splicing the video frames according to the time information of the video frames and the time sequence to obtain a spliced video file; and determining the spliced video file as a concentrated video file corresponding to the target main body.

the original video file acquisition unit is used for acquiring an original video file;

A target subject acquisition unit configured to acquire a target subject from the original video file;

a video clip data obtaining unit, configured to obtain video clip data corresponding to the target subject from the original video file;

and the concentrated video file acquisition unit is used for acquiring the concentrated video file corresponding to the target main body based on the video clip data corresponding to the target main body.

The application provides an electronic device, comprising:

a processor;

a memory for storing the program of the processing method of the video file, and executing the following steps:

a target video file corresponding to the target subject is obtained based on the video clip data corresponding to the target subject.

The present application provides a computer storage medium storing a program of a processing method of a video file, the program being executed by a processor to perform the steps of:

Compared with the prior art, the application has the following advantages:

the application provides a processing method of a video file, which comprises the following steps: obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices; obtaining a target subject from at least one video file of the plurality of video files for the same target object; obtaining video clip data corresponding to the target subject from at least two video files in the plurality of video files aiming at the same target object; a target video file corresponding to the target subject is obtained based on the video clip data corresponding to the target subject. The method comprises the steps of firstly obtaining a plurality of video files aiming at the same target object provided by a plurality of video data obtaining devices, obtaining video fragment data corresponding to a target main body from at least two video files in the plurality of video files, and finally obtaining the target video file corresponding to the target main body based on the video fragment data. The target video file corresponding to the target main body obtained by adopting the mode can solve the problems that the short video obtained by the video processing technology in the prior art is not a short video aiming at a single target main body and is unfavorable for multi-angle monitoring of the same target main body at the same time.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may also be obtained according to these drawings for a person having ordinary skill in the art.

Fig. 1-a is a schematic diagram of an application scenario embodiment provided in the present application.

Fig. 1 is a flowchart of a method for processing a video file according to a first embodiment of the present application.

Fig. 2 is a schematic diagram of a processing apparatus for video files according to a second embodiment of the present application.

Fig. 3 is a flowchart of a method for processing a video file according to a third embodiment of the present application.

Fig. 4 is a schematic diagram of a processing apparatus for video files according to a fourth embodiment of the present application.

Fig. 5 is a flowchart of a processing method of a video file according to a fifth embodiment of the present application.

Fig. 6 is a schematic diagram of a processing apparatus for video files according to a sixth embodiment of the present application.

Fig. 7 is a schematic diagram of an electronic device for processing a video file according to a seventh embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and, therefore, the application is not limited to the specific embodiments disclosed below.

The application provides three video file processing methods and devices, electronic equipment and a computer storage medium.

Some embodiments provided herein may be applied to scenarios of interactions between a client, a server, and multiple cameras. Fig. 1-a is a schematic diagram of an application scenario embodiment provided in the present application. The plurality of camera devices collect real-time information of the same target object at the same time, wherein the collected information at least comprises video data information and audio data information. In this scenario, the target object may be identified as being in an animal house in a zoo, and the plurality of imaging devices may be installed in different positions in the animal house, for example, three imaging devices may be installed in three positions in a small image house. Because the three image pickup devices are arranged at different positions, the image pickup area ranges are not completely the same. The camera device can collect video and audio data of the portraits in the portraits area. Although the areas imaged by the three imaging devices are different in scope, there may be a case where the common imaging area is used to collect the same small image from different angles at the same time. In the scene of the embodiment, long videos acquired by shooting by the three shooting devices are sent to a server, and the server respectively identifies target subjects in the three long videos. Here, the target subject may refer to the elephant 1, or may refer to the elephant 2, or may refer to any elephant in the elephant house; but may also be a tool for holding food or other target subject in a small museum. After the target subject is identified, video clips containing the target subject are acquired from at least two videos in the three long videos respectively. After the video clips containing the target subject are acquired, the video clips are recombined according to a certain rule, so that a target video file containing the target subject is acquired. The target video file may be one short video of a combination of all video clips of the elephant 1 taken by three cameras. Or a concentrated video of a combination of all video clips of the elephant 1 photographed by three cameras. For example, in this scenario, if the target object obtained from the three long videos is the elephant 1, all video segments containing the elephant 1 in the three long videos may be cut out, so as to obtain all video segments containing the elephant 1. And then, confirming the time information of the highlight moment of the elephant 1 in all the video clips containing the elephant 1 according to the preset screening conditions, and further intercepting the video clips containing the highlight moment of the elephant 1 according to the time information. And finally, splicing all video clips containing the highlight moment of the elephant 1 to obtain a short video containing the highlight moment of the elephant 1. Further, the server may push short videos containing the elephant 1 highlight to the client. In the same way, the target video files of all the portraits of the portraits can be obtained in turn and sent to its breeder or manager. It should be noted that the application scenario is only one embodiment of the application scenario, and this embodiment of the application scenario is provided to facilitate understanding of the processing method of the video file of the present application, and is not used to limit the processing method of the video file of the present application.

The application provides a method for processing video files, and the following is a specific embodiment.

Fig. 1 is a flowchart of an embodiment of a method for processing a video file according to a first embodiment of the present application. The method comprises the following steps.

Step S101: a plurality of video files for the same target object provided by a plurality of video data acquisition devices are acquired.

When processing a video file using the processing method of a video file of the present embodiment, first, a plurality of video files for the same target object provided by a plurality of video data acquisition apparatuses are obtained. In the present embodiment, the plurality of video data acquisition apparatuses may refer to a plurality of image capturing devices. The same target object may refer to the same imaging environment. There are various ways of obtaining a plurality of video files for the same target object provided by a plurality of video data obtaining apparatuses, one of which is described below.

First, a request to obtain a plurality of video files for the same target object is issued to each of the plurality of video data acquisition apparatuses. It has been pointed out in the above scenario that a plurality of video data acquisition devices may refer to a plurality of camera devices, and the same target object may refer to the environment of a certain small elephant. Thus, in the present embodiment, a request to obtain a plurality of video files for the small image hall may be issued to each of the three image capturing apparatuses that capture the small image hall. Here, two of the three image pickup devices may be installed at both corners of the rear side of the small image hall, and the other one is installed right in front of the small image hall. The mounting positions of the three image pickup devices are formed in a triangular shape as shown in fig. 1-a. Because the acquisition blind area may exist when each camera device acquires the environmental video data information of the small image hall, the adoption of a plurality of camera devices can well avoid the acquisition blind area of the small image hall. At the same time, when a plurality of image pick-up devices pick up images, an image pick-up intersection area exists, which can well collect video data information of a target subject in the small image hall from a plurality of angles. For example, the three image capturing devices can respectively collect video data information of all the portraits of the portraits from three angles, so that multi-angle videos of all the portraits can be obtained.

After a request for obtaining a plurality of video files for the same target object is issued to each of the plurality of video data acquisition apparatuses, the video files for the same target object transmitted by each of the plurality of video data acquisition apparatuses are received, and the video files for the same target object transmitted by each of the plurality of video data acquisition apparatuses are determined as a plurality of video files.

After a request is issued to each of the plurality of cameras to obtain a plurality of video files for the small image library, each of the plurality of cameras may individually retrieve the video files for the small image library upon request. After each camera device respectively calls the video files aiming at the small image library, all the called video files aiming at the small image library are gathered and sent to a server for subsequent processing.

As another way of obtaining a plurality of video files for the same target object provided by a plurality of video data obtaining apparatuses, the following way is also possible.

First, a plurality of video files provided by a plurality of video data acquisition devices are acquired. When the imaging device photographs the surrounding environment in the open space, the imaging device may photograph different target objects at different times. For example, the camera device may also be used to capture an elephant library prior to capturing the elephant library environment. Correspondingly, the camera device is only required to be moved to the elephant hall.

And classifying the plurality of video files according to the target objects to obtain the corresponding relation between the target objects and the plurality of video files. When the image pickup device shoots different target objects at different times, if a plurality of video files aiming at the same target object are wanted, firstly, the characteristics of the target object need to be acquired, and then, a plurality of video files aiming at the same target object are acquired from the plurality of video files according to the characteristics of the target object and the corresponding relation between the target object and the plurality of video files. For example, when a plurality of mobile image capturing apparatuses collect information on the surrounding environment at the same time, the correspondence between each target object and a plurality of video files is established in advance, and then a plurality of video files for the same target object can be obtained from the plurality of video files according to the characteristics of the target object and the correspondence between the target object and the plurality of video files. In this embodiment, a video file is generally captured by an image capturing device.

Specifically, the above classification of the plurality of video files according to the target object, to obtain the correspondence between the target object and the plurality of video files may be as follows.

First, different target objects appearing in the plurality of video files are obtained, respectively. For example, some three moving image capturing apparatuses capture the environment of the small image room a for a period of time, and capture the environment of the small image room B for another period of time. If one wants to obtain a long video environment of a small image hall a photographed by three photographing apparatuses, the features of the small image hall a are first acquired. And acquiring the characteristics of the small image library a requires acquiring all target objects appearing in the long video in advance and searching for the characteristics of the small image library a in all the target objects.

And then, respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object. After the characteristics of the target object are acquired, video fragment data of the target object are searched in a plurality of video files. After all the video clip data containing the target object are acquired, the video clip data containing the target object shot by the same shooting equipment is recombined, so that combined video clip data is obtained. And recombining the video segment data of all the appearing target objects according to the target objects in the mode, and respectively obtaining the combined video segment data corresponding to each target object. And finally, determining the corresponding relation between the target object and the combined video clip data corresponding to the target object as the corresponding relation between the target object and the plurality of video files.

Step S102: the target body is obtained from at least one video file of a plurality of video files for the same target object.

After a plurality of video files of the same target object are obtained in step S101, a target body is obtained from at least one video file among the plurality of video files for the same target object.

As one way of obtaining the target subject from at least one of the plurality of video files for the same target object. First, the target object is obtained from at least one video file of the plurality of video files for the same target object. Thereafter, all target subjects in the target object are obtained. And finally, arbitrarily selecting one target subject from all the target subjects as the target subject.

Taking the example of a scene of shooting a small elephant library a, assuming that three cameras are disposed in the small elephant library a, there are three long video files for the small elephant library a. If it is desired to obtain the target subjects in the three long video files, the features of the elephant library a may be extracted first, because all the target subjects in the elephant library a are part of the features of the elephant library a. After the features of elephant library A are acquired, all target subjects of elephant library A are acquired, e.g., all elephant library A is acquired, the elephant's diet tools of elephant library A, etc. After all the target subjects of the elephant library a are acquired, one target subject can be selected from all the target subjects as a study object, that is, one target subject is arbitrarily selected from all the target subjects as the target subject finally. For example, the elephant 1 may be selected as the target subject, or the elephant 2 of the elephant library a may be selected as the target subject. After the target subject is selected, screening video clip data corresponding to the current target subject according to the target subject. After the screening is finished, the next target subject is selected continuously, and then the video clip data corresponding to the next target subject is screened according to the next target subject. In this way, the corresponding video clip data of all target subjects under study are screened out.

Step S103: video clip data corresponding to a target subject is obtained from at least two video files among a plurality of video files for the same target object.

Since the present embodiment obtains video clip data corresponding to a target subject based on a plurality of image capturing apparatuses simultaneously capturing the same target subject, video clip data corresponding to a target subject is obtained from at least two video files among a plurality of video files for the same target subject. As a preferred embodiment of the present application, video clip data corresponding to a target subject is obtained from all video files among a plurality of video files for the same target object.

After the target subject is selected, video clip data corresponding to the target subject is obtained based on at least two video files from among a plurality of video files for the same target object. For example, if the elephant 1 of the elephant library a is selected as the target subject, video clip data corresponding to the elephant 1 is obtained from at least two video files among the plurality of video files for the elephant library a.

Specifically, the obtaining the video clip data corresponding to the target subject from at least two video files in the plurality of video files for the same target object may be as follows.

First, according to the target characteristics of the target subject, searching video files containing the target subject from at least two video files in the plurality of video files aiming at the same target object. Taking the example of searching a plurality of video files of the shooting elephant library A for the video file containing the elephant 1, all the video files containing the elephant 1 in the three video files can be searched according to the target characteristics of the elephant 1. When searching the video file containing the elephant 1, the face recognition technology can be used for searching the video file containing the front face of the elephant 1 in the three video files according to the facial features of the elephant 1. The video files containing the elephant 1 in the three video files can also be searched according to other characteristics of the elephant 1, for example, by utilizing a weight recognition related recognition technology. In a similar manner, video files containing other relevant portions of the elephant 1 may also be found. Of course, other relevant recognition techniques not mentioned in this embodiment may be used to recognize and find all video files containing the elephant 1 in the three video files, and these modifications are all within the scope of the present application. Of course, according to the target characteristics of the target subject, at least two video files containing the target subject are searched from at least two video files in the plurality of video files aiming at the same target subject. Here, it should be noted that not all the videos of the period in which the portraits 1 appear come from at least two video files, but it is necessary that at least one video of the period in which the portraits 1 appear comes from at least two video files. Likewise, other target objects are applicable to this case.

And then determining the time information of the target subject in the video file containing the target subject. After searching for a video file containing the target subject from at least two video files in the plurality of video files aiming at the same target object, determining time information of the target subject in the video file containing the target subject from the video file containing the target subject. The time information obtained in this step is used in particular for subsequent steps to intercept video clip data containing the target subject from the long video.

Finally, according to the time information, video clip data corresponding to the target subject is obtained.

And after the time information of the target subject appears in the video file containing the target subject is acquired, acquiring video fragment data corresponding to the target subject according to the time information. Specifically, according to the time information, capturing video clip data corresponding to the time information in the video file containing the target main body, and taking the captured video clip data as the video clip data corresponding to the target main body.

As searching for a video file containing the target subject from at least two video files among the plurality of video files for the same target subject according to the target characteristics of the target subject, the following manner may be adopted.

First, a target feature screening threshold of the target subject is obtained. When the video file containing the elephant 1 is screened, the highlight moment video of the elephant 1 is acquired finally. The target feature screening threshold of the elephant 1 can be preset, for example, the motion feature of the elephant 1 nose can be used as a screening threshold condition, and the video containing the elephant 1 nose motion can be selected from the three video files, so that other video fragments irrelevant to the nose motion can be filtered.

Then, searching video files meeting the target feature screening threshold from at least two video files in the plurality of video files aiming at the same target object; and determining the video file meeting the target feature screening threshold as a video file containing the target main body. Specifically, after a target feature screening threshold of a target subject is obtained, searching for a video file meeting the target feature screening threshold from at least two video files in the plurality of video files aiming at the same target object according to the target feature screening threshold condition.

Step S104: a target video file corresponding to the target subject is obtained based on the video clip data corresponding to the target subject.

After the video clip data corresponding to the target subject is acquired, a target video file corresponding to the target subject is acquired based on all the video clip data corresponding to the target subject. Further, the target video file corresponding to the target subject may be a combination of video clips containing the highlight moment of the target subject or a condensed video containing the highlight moment of the target subject. For example, after obtaining the plurality of video clip data corresponding to the portraits 1, all the video clip data containing the portraits 1 may be spliced according to the corresponding time sequence, and the spliced video may be used as the video clip data corresponding to the portraits 1. Alternatively, the obtained video clip data corresponding to the aspect 1 may be filtered to obtain a video clip combination containing the highlight moment (for example, a nose roll) of aspect 1, and the obtained video clip combination containing the highlight moment of aspect 1 may be used as the target video file. For example, in a zoo scene, all video clips of elephant 1 may be acquired during a day, but after some filtering conditions are set, some video clips may be filtered out. Thus, the obtained filtered video clip may be a video clip corresponding to the highlight moment of the elephant 1 (a video clip of the nose action of the elephant 1) on the day, and after obtaining a plurality of video clips of the highlight moment of the elephant 1, the obtained plurality of video clips are combined, that is, a video clip combination containing the highlight moment of the elephant 1, that is, a target video file of the highlight moment of the elephant 1 is obtained. Further screening may also be the following: if the elephant 1 is acquired at the same time in the three videos, but one video shooting angle is unclear or the picture is unclear, the corresponding video segment can be removed.

As one of the ways of obtaining the target video file corresponding to the target subject based on the video clip data corresponding to the target subject. First, time information of video clip data corresponding to the target subjects is obtained, respectively. Since the acquired video clips corresponding to the target subject may be multi-segmented, it is necessary to acquire time information of video clip data corresponding to the target subject, respectively. For example, in three videos, in each video, the video segments in which the elephant 1 appears are multi-segment and discontinuous, and time information of the multi-segment video segment data needs to be acquired at this time to provide time basis for the subsequent splicing of the video segments.

Then, splicing the video clip data according to the time information of the video clip data and the time sequence to obtain a spliced video file; and determining the spliced video file as a target video file corresponding to the target main body. Specifically, if the video clip data of the portraits 1 are all multi-segment and discontinuous, it is necessary to splice them to obtain the target video file corresponding to the portraits 1. The video clip data are spliced, which is generally to sort the video clip data according to time information, and then splice the sorted video clip data to form a video. If multiple segments of video segment data appear at the same moment, the video segment data at the same moment can be spliced randomly, and then the video segment data at the next moment can be spliced.

As another way of obtaining a target video file corresponding to the target subject based on video clip data corresponding to the target subject. First, video frames of video clip data corresponding to the target subjects are obtained, respectively. The mode is different from the first mode of acquiring the target video file corresponding to the target main body in that: the video clip data is divided into video frames, and in this manner, the video frames may be analogous to the video clip data.

Then, time information of the video frame is obtained. Finally, splicing the video frames according to the time information of the video frames and the time sequence to obtain a spliced video file; and determining the spliced video file as a target video file corresponding to the target main body.

In this embodiment, all the obtained video files including the elephant 1 are taken as short video files of the elephant 1, can be taken as video files of the elephant 1 in a certain day or a certain period, and are sent to a breeder or an administrator of the elephant 1, so that the breeder or the administrator can know the growth history of the elephant 1 in the certain day or the certain period. Meanwhile, the video clips to be fed by the elephant 1 can be screened out by setting screening conditions, for example, when the elephant 1 sends out a starvation action signal or sends out starvation sound, the video clips at the moments are concentrated to obtain a concentrated short video, and a feeder or an administrator can know the rule of the elephant 1 to be fed according to the short video, so that feeding is timely performed. For another example, according to the obtained short video file of the elephant 1, the abnormal sound made by the elephant 1 is analyzed, the video segments corresponding to the abnormal sound are screened out, and concentration is carried out, so that a concentrated shortened video is obtained, whether the elephant is ill or not can be conveniently observed by a breeder or an administrator, and treatment is timely given according to the short video. In addition, when the feeder or the manager feeds on the elephant 1, the expression of the elephant 1 can be captured according to the video clip containing the elephant 1, so as to obtain which foods are interested by the elephant 1. Of course, the above application is illustrated only with the portraits 1, which is equally applicable to other target subjects. The embodiment can be applied to zoo scenes and other observation scenes.

The embodiment obtains the target video files corresponding to the target main body based on the video clip data by firstly obtaining a plurality of video files aiming at the same target object provided by a plurality of video data obtaining devices and obtaining video clip data corresponding to the target main body from at least two video files in the plurality of video files. The target video file corresponding to the target main body can be obtained by adopting the mode, and the problems that the short video obtained by the video processing technology in the prior art is not a short video aiming at a single target main body and is unfavorable for multi-angle monitoring of the same target main body at the same time can be solved.

In the first embodiment, a method for processing a video file is provided, and correspondingly, the application also provides a device for processing the video file. Fig. 2 is a schematic diagram of a video file processing apparatus according to a second embodiment of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

The present embodiment provides a processing apparatus for a video file, including:

A video file acquisition unit 201 for acquiring a plurality of video files for the same target object provided by a plurality of video data acquisition devices;

a target subject obtaining unit 202 for obtaining a target subject from at least one video file of the plurality of video files for the same target object;

a video clip data obtaining unit 203, configured to obtain video clip data corresponding to the target subject from at least two video files in the plurality of video files for the same target object;

a target video file obtaining unit 204, configured to obtain a target video file corresponding to the target subject based on the video clip data corresponding to the target subject.

Optionally, the video file obtaining unit is specifically configured to:

Optionally, the target subject obtaining unit is specifically configured to:

Obtaining all target subjects in the target object;

Optionally, the video clip data acquisition unit is specifically configured to:

obtaining a target feature screening threshold of the target subject;

Optionally, the target video file obtaining unit is specifically configured to:

obtaining time information of the video frame;

In the first embodiment described above, a method for processing a video file is provided. The application also provides another processing method of the video file. Fig. 3 is a flowchart of a method for processing a video file according to a third embodiment of the present application. Since the specific implementation of the method in this embodiment is substantially similar to that of the first embodiment, the description is relatively simple, and reference is made to the partial description of the first embodiment for relevant points.

Fig. 3 is a flowchart of an embodiment of a method for processing a video file according to a third embodiment of the present application. The method comprises the following steps.

Step S301: a plurality of video files for the same target object provided by a plurality of video data acquisition devices are acquired.

As one of the ways of obtaining the plurality of video files for the same target object provided by the plurality of video data obtaining means, the following way may be adopted.

First, a request to obtain a plurality of video files for the same target object is issued to each of the plurality of video data acquisition apparatuses.

Then, video files for the same target object transmitted by each of the plurality of video data acquisition apparatuses are received, and the video files for the same target object transmitted by each of the plurality of video data acquisition apparatuses are determined as a plurality of video files.

As another way of obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition apparatuses, it is also possible to follow the manner described below.

First, a plurality of video files provided by a plurality of video data acquisition devices are acquired.

And classifying the plurality of video files according to the target objects to obtain the corresponding relation between the target objects and the plurality of video files.

Finally, according to the characteristics of the target object and the corresponding relation between the target object and a plurality of video files, a plurality of video files aiming at the same target object are obtained from the plurality of video files.

The classifying the plurality of video files according to the target object to obtain the corresponding relation between the target object and the plurality of video files includes: different target objects appearing in the plurality of video files are obtained respectively. Respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object; and recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object. And determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and the plurality of video files.

Step S302: and carrying out video concentration processing on the plurality of video files to obtain at least one target concentrated video file, wherein the target concentrated video file comprises video fragment data of at least two video files in the plurality of video files.

As one way of performing video concentration processing on the plurality of video files to obtain at least one target concentrated video file, there may be: first, time information of the plurality of video files is obtained, respectively. Then, splicing the video files according to time information of the video files and time sequence to obtain spliced video files; and determining the spliced video file as a target concentrated video file.

Further, in this embodiment, the video concentration processing is performed on the plurality of video files, and the manner of obtaining at least one target concentrated video file may be: first, a target subject is obtained from at least one video file of the plurality of video files for the same target object. Then, video clip data corresponding to the target subject is obtained from at least two video files in the plurality of video files for the same target object. Finally, obtaining a concentrated video file corresponding to the target subject based on the video clip data corresponding to the target subject; and determining the concentrated video file corresponding to the target main body as a target concentrated video file.

In the third embodiment, a method for processing a video file is provided, and correspondingly, the application also provides a device for processing the video file. Fig. 4 is a schematic diagram of a video file processing apparatus according to a fourth embodiment of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

Correspondingly, the embodiment also provides a processing device for the video file, which comprises:

a video file acquisition unit 401 for acquiring a plurality of video files for the same target object provided by a plurality of video data acquisition devices;

a target concentrated video file obtaining unit 402, configured to perform video concentration processing on the plurality of video files, to obtain at least one target concentrated video file, where the target concentrated video file includes video clip data of at least two video files in the plurality of video files.

Optionally, the video file obtaining unit is specifically configured to:

Optionally, the target concentrated video file obtaining unit is specifically configured to:

respectively obtaining time information of the plurality of video files;

Optionally, the video clip data acquisition unit is further included;

the video clip data acquisition unit is specifically configured to:

the target concentrated video file acquisition unit is specifically configured to:

In the first embodiment described above, a method for processing a video file is provided. The application also provides another processing method of the video file. Fig. 5 is a flowchart of a method for processing a video file according to a fifth embodiment of the present application. Since the specific implementation of the method in this embodiment is substantially similar to that of the first embodiment, the description is relatively simple, and reference is made to the partial description of the first embodiment for relevant points.

Fig. 5 is a flowchart of an embodiment of a method for processing a video file according to a fifth embodiment of the present application. The method comprises the following steps.

Step S501: an original video file is obtained.

There are various ways of obtaining the original video file, and as one of them, it can be described as follows. And obtaining a plurality of video files aiming at the same target object provided by a plurality of video data acquisition devices, and determining the plurality of video files aiming at the same target object as the original video file.

Step S502: the target body is obtained from the original video file.

After obtaining the original video file, obtaining a target body from the original video file, wherein the process may include: first, the target object is obtained from at least one video file of the plurality of video files for the same target object. Thereafter, all target subjects in the target object are obtained. Finally, one target subject is arbitrarily selected from the all target subjects as the target subject.

Step S503: video clip data corresponding to the target subject is obtained from the original video file.

As one of the ways of obtaining video clip data corresponding to the target subject from the original video file, first: and searching video files containing the target subject from at least two video files in the original video files according to the target characteristics of the target subject. And then determining the time information of the target subject in the video file containing the target subject. Finally, according to the time information, video clip data corresponding to the target subject is obtained.

The searching the video file containing the target subject from at least two video files in the original video file according to the target characteristics of the target subject comprises the following steps: obtaining a target feature screening threshold of the target subject; searching video files meeting the target feature screening threshold from at least two video files in the original video files; and determining the video file meeting the target feature screening threshold as a video file containing the target main body.

Step S504: a concentrated video file corresponding to the target subject is obtained based on the video clip data corresponding to the target subject.

As one way of obtaining a concentrated video file corresponding to the target subject based on video clip data corresponding to the target subject, first, time information of video clip data corresponding to the target subject is obtained, respectively. Then, splicing the video clip data according to the time information of the video clip data and the time sequence to obtain a spliced video file; and determining the spliced video file as a concentrated video file corresponding to the target main body.

As another way of obtaining a concentrated video file corresponding to the target subject based on video clip data corresponding to the target subject, first, video frames of video clip data corresponding to the target subject are obtained, respectively. Then, time information of the video frame is obtained. Finally, splicing the video frames according to the time information of the video frames and the time sequence to obtain a spliced video file; and determining the spliced video file as a concentrated video file corresponding to the target main body.

In the fifth embodiment, a method for processing a video file is provided, and correspondingly, the application also provides a device for processing a video file. Fig. 6 is a schematic diagram of a video file processing apparatus according to a sixth embodiment of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

an original video file obtaining unit 601, configured to obtain an original video file;

a target subject obtaining unit 602, configured to obtain a target subject from the original video file;

a video clip data obtaining unit 603, configured to obtain video clip data corresponding to the target subject from the original video file;

a concentrated video file obtaining unit 604, configured to obtain a concentrated video file corresponding to the target subject based on the video clip data corresponding to the target subject.

Optionally, the original video file obtaining unit is specifically configured to:

And obtaining a plurality of video files aiming at the same target object provided by a plurality of video data acquisition devices, and determining the plurality of video files aiming at the same target object as the original video file.

Optionally, the target subject obtaining unit is specifically configured to:

obtaining all target subjects in the target object;

Optionally, the video clip data acquisition unit is specifically configured to:

obtaining a target feature screening threshold of the target subject;

Optionally, the concentrated video file obtaining unit is specifically configured to:

obtaining time information of the video frame;

The first embodiment of the application provides a method for processing a video file, and the seventh embodiment of the application provides an electronic device corresponding to the method.

As shown in fig. 7, a schematic diagram of an electronic device for processing a video file according to the present embodiment is shown.

The present embodiment provides an electronic device including:

a processor 701;

the memory 702 is used for storing the program of the processing method of the video file, and performs the following steps:

The first embodiment of the present application provides a method for processing a video file, and the eighth embodiment of the present application provides a computer storage medium corresponding to the method.

The present embodiment provides a computer storage medium storing a program of a processing method of a video file, the program being executed by a processor to perform the steps of:

The third embodiment of the application provides a method for processing a video file, and the ninth embodiment of the application provides an electronic device corresponding to the method. Since the ninth embodiment is the same as the seventh embodiment, please continue to refer to fig. 7, which shows a schematic diagram of an electronic device for processing a video file according to the ninth embodiment of the present application.

The present embodiment provides an electronic device including:

a processor;

A third embodiment of the present application provides a method for processing a video file, and a tenth embodiment of the present application provides a computer storage medium corresponding to the method.

A fifth embodiment of the present application provides a method for processing a video file, and an eleventh embodiment of the present application provides an electronic device corresponding to the method. Since the eleventh embodiment is the same as the seventh embodiment, please continue to refer to fig. 7, which shows a schematic diagram of an electronic device for processing a video file according to the eleventh embodiment of the present application.

The application provides an electronic device, comprising:

a processor;

obtaining an original video file;

obtaining a target subject from the original video file;

A fifth embodiment of the present application provides a method for processing a video file, and a twelfth embodiment of the present application provides a computer storage medium corresponding to the method.

obtaining an original video file;

obtaining a target subject from the original video file;

While the preferred embodiment has been described, it is not intended to limit the invention thereto, and any person skilled in the art may make variations and modifications without departing from the spirit and scope of the present invention, so that the scope of the present invention shall be defined by the claims of the present application.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

1. Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable storage media (non-transitory computer readable storage media), such as modulated data signals and carrier waves.

2. It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Claims

1. A method for processing a video file, comprising:

obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices, including: obtaining a plurality of video files provided by a plurality of video data acquisition devices; respectively obtaining different target objects appearing in the plurality of video files; respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object; recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object; determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and a plurality of video files; obtaining a plurality of video files aiming at the same target object from the plurality of video files according to the characteristics of the target object and the corresponding relation between the target object and the plurality of video files;

2. The method according to claim 1, wherein obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices, comprises:

3. The method of claim 1, wherein obtaining the target body from at least one of the plurality of video files for the same target object comprises:

obtaining all target subjects in the target object;

4. The method of claim 1, wherein the obtaining video clip data corresponding to the target subject from at least two video files of the plurality of video files for the same target object comprises:

5. The method of claim 4, wherein searching for a video file containing the target subject from at least two video files of the plurality of video files for the same target subject based on the target characteristics of the target subject, comprises:

Obtaining a target feature screening threshold of the target subject;

6. The method of claim 1, wherein the obtaining a target video file corresponding to the target subject based on video clip data corresponding to the target subject comprises:

7. The method of claim 1, wherein the obtaining a target video file corresponding to the target subject based on video clip data corresponding to the target subject comprises:

Obtaining time information of the video frame;

8. A video file processing apparatus, comprising:

a video file acquisition unit configured to acquire a plurality of video files for the same target object provided by a plurality of video data acquisition devices; the video file obtaining unit is specifically configured to: obtaining a plurality of video files provided by a plurality of video data acquisition devices; respectively obtaining different target objects appearing in the plurality of video files; respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object; recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object; determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and a plurality of video files; obtaining a plurality of video files aiming at the same target object from the plurality of video files according to the characteristics of the target object and the corresponding relation between the target object and the plurality of video files;

9. A method for processing a video file, comprising:

10. The method of claim 9, wherein obtaining a plurality of video files for the same target object provided by a plurality of video data acquisition devices comprises:

11. The method of claim 9, wherein the video concentrating the plurality of video files to obtain at least one target concentrated video file comprises:

respectively obtaining time information of the plurality of video files;

12. The method as recited in claim 9, further comprising:

13. A video file processing apparatus, comprising:

14. A method for processing a video file, comprising:

obtaining an original video file, comprising: obtaining a plurality of video files provided by a plurality of video data acquisition devices; respectively obtaining different target objects appearing in the plurality of video files; respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object; recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object; determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and a plurality of video files; according to the characteristics of the target object and the corresponding relation between the target object and a plurality of video files, a plurality of video files aiming at the same target object are obtained from the plurality of video files, and the plurality of video files aiming at the same target object are determined to be the original video files;

Obtaining a target subject from the original video file;

15. The method of claim 14, wherein obtaining a target body from the original video file comprises:

obtaining all target subjects in the target object;

16. The method of claim 14, wherein obtaining video clip data corresponding to the target subject from the original video file comprises:

17. The method of claim 16, wherein searching for a video file containing the target subject from at least two video files in the original video file based on the target characteristics of the target subject, comprises:

obtaining a target feature screening threshold of the target subject;

18. The method of claim 14, wherein the obtaining a concentrated video file corresponding to the target subject based on video clip data corresponding to the target subject comprises:

19. The method of claim 14, wherein the obtaining a concentrated video file corresponding to the target subject based on video clip data corresponding to the target subject comprises:

obtaining time information of the video frame;

20. A video file processing apparatus, comprising:

the original video file acquisition unit is used for acquiring an original video file; the original video file obtaining unit is specifically configured to: obtaining a plurality of video files provided by a plurality of video data acquisition devices; respectively obtaining different target objects appearing in the plurality of video files; respectively obtaining video fragment data of the appointed target object in the plurality of video files according to the characteristics of each target object; recombining the video segment data according to the target objects to respectively obtain combined video segment data corresponding to each target object; determining the corresponding relation of the combined video clip data corresponding to the target object as the corresponding relation of the target object and a plurality of video files; according to the characteristics of the target object and the corresponding relation between the target object and a plurality of video files, a plurality of video files aiming at the same target object are obtained from the plurality of video files, and the plurality of video files aiming at the same target object are determined to be the original video files;

21. An electronic device, comprising:

a processor;

22. A computer storage medium storing a program of a processing method of a video file, the program being executed by a processor to perform the steps of: