CN111601160A - Method and device for editing video - Google Patents

Abstract

The embodiment of the disclosure discloses a method and a device for editing a video, and relates to the field of artificial intelligence computer vision. One embodiment of the method comprises: identifying a video frame of a video to be processed to obtain a scene segment of the video to be processed; determining content information of a video to be processed according to the scene clip, and extracting a cover image according to the content information; extracting a characteristic segment with a set time length of the scene segment; and combining the cover image and the feature fragment to form a feature video. The embodiment is beneficial to the accuracy and the effectiveness of acquiring the characteristic video.

Description

Method and device for editing video

technical field

Embodiments of the present disclosure relate to the field of artificial intelligence computer vision, and in particular, to a method and apparatus for editing video.

Background technique

With the development of science and technology, various smart devices are used in people's work, study and daily life, which improves the efficiency of people's work and study and the convenience of daily life. Smart devices usually have a video capture function. People can acquire videos related to work and life through smart devices, and upload the videos to a video server to provide them to other users. Moreover, the video itself has the characteristics of rich information and good dissemination, which further promotes the promotion of the video.

After the video is uploaded to the video server, the technicians need to review the video content, and classify and edit the video.

SUMMARY OF THE INVENTION

Embodiments of the present disclosure propose a method and apparatus for editing a video.

In a first aspect, an embodiment of the present disclosure provides a method for editing a video, the method includes: identifying a video frame of a video to be processed, acquiring a scene segment of the video to be processed; The content information of the video is processed, and the cover image is extracted according to the content information; the feature segment of the set time length of the scene segment is extracted; the cover image and the feature segment are combined to form a feature video.

In some embodiments, the identifying the video frame of the video to be processed, and acquiring the scene segment of the video to be processed, includes: performing image recognition on the video frame of the video to be processed, and obtaining a corresponding image of the video to be processed. Scene information, where the scene information is used to represent the scene where the video content is located; the to-be-processed video is divided into scene segments according to the scene information.

In some embodiments, the determining the content information of the video to be processed according to the scene segment includes: identifying an initial object image in the scene segment; counting the number of occurrences of the initial object image in the to-be-processed video and occurrence time, determine target object information according to the number of occurrences and occurrence time; query the attribute information of the target object information, and determine the content information of the video to be processed according to the attribute information, wherein the attribute information includes the following At least one item: the name of the target object, the purpose of the target object.

In some embodiments, the extracting the cover image according to the content information includes: acquiring a feature image in the scene segment, where the feature image is used to characterize the feature of the scene segment; The content information is matched to determine the cover image.

In some embodiments, the combining the cover image and the feature segment to form a feature video includes: in response to the plurality of feature segments, deleting duplicate feature segments.

In some embodiments, the combination of the cover image and the feature segment to form a feature video includes: performing transition processing on adjacent feature segments in the feature video, and the transition process includes at least one of the following: color transition , scene transition, light transition.

In some embodiments, the method further comprises: adding a title to the feature video according to the content information.

In a second aspect, an embodiment of the present disclosure provides an apparatus for editing a video, the apparatus comprising: a scene segment acquiring unit, configured to identify a video frame of a video to be processed, and acquire a scene segment of the video to be processed The cover image acquisition unit is configured to determine the content information of the video to be processed according to the scene segment, and extract the cover image according to the content information; the feature segment extraction unit is configured to extract the set time length of the scene segment. A feature segment; a feature video acquisition unit configured to combine the cover image and the feature segment to form a feature video.

In some embodiments, the scene segment obtaining unit includes: a scene information obtaining subunit, configured to perform image recognition on the video frame of the video to be processed to obtain scene information corresponding to the video to be processed, the scene The information is used to represent the scene where the video content is located; the scene segment dividing subunit is configured to divide the video to be processed into scene segments according to the scene information.

In some embodiments, the cover image acquisition unit includes: an initial object image identification subunit configured to identify an initial object image in the scene segment; a target object information determination subunit configured to count the initial object The number of occurrences and the occurrence time of the image in the video to be processed, and the target object information is determined according to the number of occurrences and the occurrence time; the content information determination subunit is configured to query the attribute information of the target object information, according to the The attribute information determines content information of the video to be processed, wherein the attribute information includes at least one of the following: the name of the target object and the purpose of the target object.

In some embodiments, the cover image obtaining unit includes: a feature image obtaining subunit configured to obtain a feature image in the scene segment, the feature image being used to characterize the feature of the scene segment; a cover image determining subunit A unit configured to determine a cover image from matching the feature image with the content information.

In some embodiments, the feature video acquisition unit includes a video deletion subunit configured to delete duplicate feature segments in response to the plurality of feature segments.

In some embodiments, the feature video acquisition unit includes: a transition processing subunit configured to perform transition processing on adjacent feature segments in the feature video, the transition processing including at least one of the following: color transition, Scene transition, light transition.

In some embodiments, the apparatus further includes a title adding unit configured to add a title to the feature video according to the content information.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; a memory on which one or more programs are stored, when the one or more programs are stored by the one or more programs described above When executed by the processor, the above-mentioned one or more processors are caused to execute the method for editing a video of the above-mentioned first aspect.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the method for editing a video of the first aspect above is implemented.

The method and device for editing a video provided by the embodiments of the present disclosure firstly identify the video frame of the video to be processed, and obtain the scene segment of the to-be-processed video; then determine the content information of the to-be-processed video according to the scene segment, Extracting the cover image according to the content information improves the accuracy of the video selected by the user; then extracts the feature segment of the set time length of the scene segment, which is conducive to improving the viewing quality of the feature video; finally, the cover image and the feature The segments are combined to form a feature video. The present application is beneficial to obtain the accuracy and validity of the feature video.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

1 is a schematic diagram according to a first embodiment of the present application;

2 is a schematic diagram according to a second embodiment of the present application;

3 is a schematic diagram according to a third embodiment of the present application;

4 is a schematic diagram according to a fourth embodiment of the present application;

5 is a block diagram of an electronic device used to implement the method for editing a video according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of an electronic device suitable for implementing embodiments of the present disclosure.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

FIG. 1 illustrates an exemplary system architecture 100 of a method for editing a video or an apparatus for editing a video to which embodiments of the present disclosure may be applied.

As shown in FIG. 1 , the system architecture 100 may include terminal devices 101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. Various video client applications may be installed on the terminal devices 101 , 102 and 103 , such as video browser applications, video playback plug-ins, video search applications, video download tools, and video playback clients.

The terminal devices 101, 102, and 103 may be hardware or software. When the terminal devices 101 , 102 , and 103 are hardware, they can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like. When the terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. It may be implemented as multiple software or software modules (for example, used to provide distributed services), or may be implemented as a single software or software module, which is not specifically limited herein.

The server 105 may be a server that provides various services, for example, a server that processes the video to be processed sent from the terminal devices 101 , 102 , and 103 . The server can analyze and process the received video and other data to be processed, and obtain a characteristic video.

It should be noted that the method for editing a video provided by the embodiments of the present disclosure is generally performed by the server 105 , and accordingly, the apparatus for editing a video is generally set in the server 105 .

It should be noted that the server may be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server. When the server is software, it may be implemented as multiple software or software modules (for example, used to provide distributed services), or may be implemented as a single software or software module, which is not specifically limited herein.

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for editing video according to the present disclosure is shown. The method for editing a video includes the following steps:

Step 201: Identify the video frame of the video to be processed, and acquire the scene segment of the video to be processed.

In this embodiment, the execution body of the method for editing a video (for example, the server 105 shown in FIG. 1 ) may receive the video to be processed from the terminal devices 101 , 102 , and 103 through a wired connection or a wireless connection. It should be pointed out that the above wireless connection methods may include but are not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wideband) connection, and other wireless connection methods currently known or developed in the future .

Existing video classification or editing is usually done manually and cannot cope with massive videos. Video reviewers have differences in video review standards and video editing capabilities, resulting in irregular video classification and editing. Manual review of clips usually requires watching the entire content of the video, which takes a lot of time, and the video processing efficiency is low, it is difficult to obtain the key content of the video, and the video content is not prominent enough.

To this end, the execution subject may identify the video frame of the video to be processed, and obtain the video frame content of the video frame. Wherein, the video frame content may include human images, animal images, background images, and the like. After that, the execution body can determine the scene segment according to the video frame content. For example, if the video frame content includes a basketball player and the background image is a basketball court, the execution subject can determine that the video frame corresponds to a basketball scene. Further, the execution subject divides the video to be processed according to the content of the video frame, and obtains the scene segment of playing basketball. In this way, the scene segment of the video to be processed can be obtained, which is beneficial to the accuracy and effectiveness of obtaining the characteristic video.

Step 202: Determine content information of the video to be processed according to the scene segment, and extract a cover image according to the content information.

After acquiring the scene segment, the execution subject can determine the content information of the video to be processed according to the scene segment, and then select a video frame representing the content of the to-be-processed video from the to-be-processed video as the cover image according to the content information. For example, when the scene segment is playing basketball, the corresponding content information may be: basketball video. After that, the executive body can select a video frame of a basketball or a basketball player from the scene clip as the cover image. The video content of the video to be processed can be visually indicated by the cover image, which improves the accuracy of the video selected by the user.

Step 203, extracting the feature segment of the scene segment with the set time length.

In order to acquire the feature video, the execution body may extract the feature segment of the scene segment with the set time length. The feature segment may represent representative content in the corresponding scene segment. For example, if the scene segment is playing basketball, the corresponding feature segment may be the content of a famous basketball player scoring a goal. For different scene segments, the specific content of the feature segments may be different. In this way, it is beneficial to improve the viewing quality of the feature video.

Step 204, combining the cover image and the feature segment to form a feature video.

After obtaining the cover image and the feature segment, the execution subject can use the cover image as the cover of the feature segment to form a feature video. As can be seen from the above description, the feature video includes feature segments of each scene segment, which can highlight the content of the video to be processed. In this way, the feature video obtained from the to-be-processed video and including the main content of the to-be-processed video is realized, the content of the to-be-processed video is highlighted, the efficiency of acquiring the feature video is improved, and the effectiveness of the feature video is improved.

With continued reference to FIG. 3, a flow 300 of one embodiment of a method for editing a video according to the present disclosure is shown. The method for editing a video includes the following steps:

Step 301: Perform image recognition on video frames of the to-be-processed video to obtain scene information corresponding to the to-be-processed video.

After acquiring the video to be processed, the execution body can perform image recognition on the video frame of the video to be processed to obtain the video frame content of the video frame. The video frame content may include human images, animal images, background images, and the like. After that, the content of the video frame is analyzed to determine scene information. The scene information may be used to represent the scene where the video content is located. For example, if the video frame content includes a basketball player and the background image is a basketball court, the execution subject can determine that the video frame corresponds to a basketball scene. The corresponding scene information can be basketball sports.

Step 302: Divide the to-be-processed video into scene segments according to scene information.

After the scene information is determined, the execution subject can divide the content of the video to be processed according to the scene information to obtain scene segments. In practice, the video to be processed may include one scene segment or multiple scene segments. In this way, the video to be processed is divided according to the scene segments, and the accuracy of identifying the video content to be processed is improved.

Step 303: Determine content information of the video to be processed according to the scene segment, and extract a cover image according to the content information.

In some optional implementation manners of this embodiment, the determining the content information of the video to be processed according to the scene segment may include the following steps:

In the first step, the initial object image in the scene segment is identified.

The executive body may perform image recognition on the video frames included in the scene segment, and determine at least one chef object image included in each video frame. Also taking the above-mentioned basketball scene segment as an example, the initial object images in the video frame of the execution subject recognition scene segment may include: basketball player images, basketball images, basketball court images, basketball hoop images, team logo images, basketball stadium images. images, audience images, etc. The initial object images can be different for different scene segments.

In the second step, count the occurrence times and occurrence times of the initial object image in the to-be-processed video, and determine target object information according to the occurrence times and occurrence times.

Typically, the main content of the video appears the most and for the longest time in the video. To this end, the execution subject may count the occurrence times and the occurrence time of the initial object image in the video to be processed. After that, the target object information is determined according to the number of occurrences and the occurrence time. For example, if the scene segment is playing basketball, in the initial object image, an athlete appears more frequently and appears for the longest time. At this time, the execution subject can determine that the target object information is the name of the athlete. In practice, there may also be a situation in which an initial object image appears the most times, but the appearance time is not the longest. At this time, the execution subject can still mark the initial object image as the target object. And the initial object image with the longest appearance time is also marked as the target object. That is, there may be multiple target objects, and there may also be multiple pieces of corresponding target object information.

In the third step, the attribute information of the target object information is inquired, and the content information of the video to be processed is determined according to the attribute information.

The target object information is usually a description of the target object itself. In most cases, the video is an explanation of the attribute information of the target object. The attribute information may include at least one of the following: the name of the target object, the purpose of the target object, and the occupation of the target object. For different target objects, the attribute information can be different. For example, when the target object is a human, the attribute information may include the name of the target object and the occupation of the target object, but not the usage of the target object. When the target object is a device (for example, a mobile phone), the attribute information may include the name of the target object and the purpose of the target object, but does not include the occupation of the target object. Therefore, the execution subject can determine the content information of the video to be processed according to the attribute information. For example, if the target object information is the name of a basketball player, the attribute information corresponding to the name queried may include the occupation of the target object: basketball. At this time, the execution body can set the content information of the video to be processed as a basketball video.

In some optional implementation manners of this embodiment, the extracting the cover image according to the content information may include the following content:

The first step is to acquire feature images in the scene segment.

For example, when the scene segment is playing basketball, the characteristic images that can be acquired by the execution subject may be an image of an athlete shooting a basketball, an image of a basketball court, an image of an athlete, and the like. When the scene image is football, the characteristic images that can be acquired by the execution subject may be an image of a player shooting a goal, an image of a player dribbling a ball, an image of a football field, and the like. That is, the feature image may be used to characterize the scene segment.

In the second step, the cover image is determined by matching the feature image with the content information.

After obtaining the characteristic image, the execution subject can match the characteristic image with the content information to determine the cover image. For example, the content information is a basketball video, and the characteristic images include an image of a player shooting a basketball, an image of a basketball court, an image of an athlete, and the like. Since the image of the athlete's shot contains the basketball player, basketball and basketball's work information, it can be considered that the image of the athlete's shot has a higher correlation with the basketball video, and the image of the athlete's shot can be determined as the cover image.

Step 304, extracting the feature segment of the scene segment with the set time length.

The content of step 304 is the same as that of step 203, and details are not repeated here.

Step 305, in response to the plurality of feature segments, delete duplicate feature segments.

A video frame of the video to be processed may appear in multiple different scene segments, and multiple scene segments may appear repeatedly in the to-be-processed video. The same scene fragment can be represented by a feature fragment. Therefore, in order to avoid repeated feature segments and improve the effectiveness of the feature video, the executive body can delete the repeated feature segments, and only one of each feature segment is required. At the same time, in order to prevent the file data from being too large and occupying too many resources, the execution body can also adjust the time of each feature segment, so that the video playback time of the finally obtained feature video is within the set time range, and the video The file size is within the set file size.

Step 306: Perform transition processing on adjacent feature segments in the feature video.

Different feature segments correspond to different scenes, and correspondingly, different feature segments also have differences in color, brightness, etc. In order to improve the playback effect of the video, the execution subject may perform transition processing on adjacent feature segments, so that the feature videos have the same or similar visual characteristics during playback. The transition processing may include at least one of the following: color transition, scene transition, and light transition.

With continued reference to FIG. 4, a flow 400 of one embodiment of a method for editing a video according to the present disclosure is shown. The method for editing a video includes the following steps:

Step 401: Identify the video frame of the video to be processed, and acquire the scene segment of the video to be processed.

The content of step 401 is the same as that of step 201, and details are not repeated here.

Step 402: Determine content information of the video to be processed according to the scene segment, and extract a cover image according to the content information.

The content of step 402 is the same as that of step 202, and details are not repeated here.

Step 403, extracting the feature segment of the scene segment with the set time length.

The content of step 403 is the same as that of step 203, and details are not repeated here.

Step 404, combining the cover image and the feature segment to form a feature video.

The content of step 404 is the same as that of step 204, and details are not repeated here.

Step 405: Add a title to the feature video according to the content information.

After the feature video is obtained, in order to further improve the readability of the feature video, the execution body can also add a title to the feature video according to the content information, so that the user can understand the content of the feature video through text. For example, if the content information is a basketball video, and the target object information corresponding to the content information is a certain athlete A, the title may be: "Athlete A's Basketball Highlights" and the like.

Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an apparatus for editing a video. The apparatus embodiment corresponds to the method embodiment shown in FIG. 2 . The device can be specifically applied to various electronic devices.

As shown in FIG. 5 , the apparatus 500 for editing a video in this embodiment may include: a scene segment acquiring unit 501 , a cover image acquiring unit 502 , a feature segment extracting unit 503 , and a feature video acquiring unit 504 . Wherein, the scene fragment obtaining unit 501 is configured to identify the video frame of the video to be processed, and obtain the scene fragment of the to-be-processed video; the cover image obtaining unit 502 is configured to determine the content of the to-be-processed video according to the scene fragment information, extract the cover image according to the content information; the feature segment extraction unit 503 is configured to extract the feature segment of the set time length of the scene segment; the feature video acquisition unit 504 is configured to extract the cover image and the feature segment The segments are combined to form a feature video.

In some optional implementations of this embodiment, the scene segment acquiring unit 501 may include: a scene information acquiring subunit (not shown in the figure) and a scene segment dividing subunit (not shown in the figure). The scene information acquisition subunit is configured to perform image recognition on the video frame of the video to be processed, and obtain scene information corresponding to the video to be processed, where the scene information is used to represent the scene where the video content is located; the scene fragment A division subunit is configured to divide the video to be processed into scene segments according to the scene information.

In some optional implementations of this embodiment, the cover image acquisition unit 502 may include: an initial object image recognition subunit (not shown in the figure), a target object information determination subunit (not shown in the figure) and content information determination subunit (not shown in the figure). Wherein, the initial object image recognition subunit is configured to recognize the initial object image in the scene segment; the target object information determination subunit is configured to count the number of occurrences of the initial object image in the to-be-processed video and Appearance time, the target object information is determined according to the appearance times and the appearance time; the content information determination subunit is configured to query the attribute information of the target object information, and determine the content information of the to-be-processed video according to the attribute information, Wherein, the attribute information includes at least one of the following: the name of the target object and the purpose of the target object.

In some optional implementations of this embodiment, the cover image obtaining unit 502 may include: a feature image obtaining subunit (not shown in the figure) and a cover image determining subunit (not shown in the figure). Wherein, the characteristic image acquisition subunit is configured to acquire the characteristic image in the scene segment, the characteristic image is used to characterize the characteristics of the scene segment; the cover image determination subunit is configured to obtain the characteristic image from the characteristic image with The content information is matched to determine the cover image.

In some optional implementations of this embodiment, the feature video acquisition unit 504 may include: a video deletion subunit (not shown in the figure), configured to delete duplicates in response to the plurality of feature segments feature segment.

In some optional implementation manners of this embodiment, the feature video obtaining unit 504 may include: a transition processing subunit (not shown in the figure), configured to perform processing on adjacent feature segments in the feature video Transition processing, the transition processing includes at least one of the following: color transition, scene transition, and light transition.

In some optional implementations of this embodiment, the apparatus 500 for editing a video may further include: a title adding unit (not shown in the figure), configured to add a title to the feature video according to the content information .

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 6 , it is a block diagram of an electronic device for a method for editing a video according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 6, the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, each providing some of the necessary operations (eg, as a server array, a group of blade servers, or a multiprocessor system). A processor 601 is taken as an example in FIG. 6 .

The memory 602 is the non-transitory computer-readable storage medium provided by the present application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the method for editing a video provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the method for editing a video provided by the present application.

As a non-transitory computer-readable storage medium, the memory 602 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules ( For example, the scene segment acquisition unit 501, the cover image acquisition unit 502, the feature segment extraction unit 503, and the feature video acquisition unit 504 shown in FIG. 5). The processor 601 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 602, that is, implementing the method for editing video in the above method embodiments.

The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of an electronic device for editing video Wait. Additionally, memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 602 may optionally include memory located remotely from processor 601, which may be connected via a network to an electronic device for editing video. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device for the method of editing a video may further include: an input device 603 and an output device 604 . The processor 601 , the memory 602 , the input device 603 and the output device 604 may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 6 .

The input device 603 can receive input numerical or character information, and generate key signal input related to user settings and function control of electronic equipment for editing video, such as touch screen, keypad, mouse, trackpad, touchpad, pointing stick , one or more mouse buttons, trackballs, joysticks and other input devices. Output devices 604 may include display devices, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical solutions of the embodiments of the present application, the video frame of the video to be processed is first identified, and the scene segment of the to-be-processed video is obtained; then the content information of the to-be-processed video is determined according to the scene segment, and the cover page is extracted according to the content information image, which improves the accuracy of video selection by the user; then extracts the feature segment of the set time length of the scene segment, which is beneficial to improve the viewing quality of the feature video; finally, the cover image and the feature segment are combined to form a feature video. The present application is beneficial to obtain the accuracy and validity of the feature video.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be performed in parallel, sequentially or in different orders, and as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (16)

1. A method for clipping a video, comprising:

identifying a video frame of a video to be processed to obtain a scene segment of the video to be processed;

determining content information of a video to be processed according to the scene clip, and extracting a cover image according to the content information;

extracting a characteristic segment with a set time length of the scene segment;

and combining the cover image and the feature fragment to form a feature video.

2. The method of claim 1, wherein the identifying the video frame of the video to be processed and obtaining the scene segment of the video to be processed comprises:

performing image recognition on a video frame of the video to be processed to obtain scene information corresponding to the video to be processed, wherein the scene information is used for representing a scene where video content is located;

and dividing the video to be processed into scene segments according to the scene information.

3. The method of claim 2, wherein the determining content information of the video to be processed according to the scene segment comprises:

identifying an initial object image in the scene segment;

counting the occurrence times and the occurrence time of the initial object image in the video to be processed, and determining target object information according to the occurrence times and the occurrence time;

inquiring attribute information of the target object information, and determining content information of the video to be processed according to the attribute information, wherein the attribute information comprises at least one of the following items: name of the target object, purpose of the target object.

4. The method of claim 1, wherein said extracting a cover image from the content information comprises:

acquiring a characteristic image in the scene segment, wherein the characteristic image is used for representing the characteristics of the scene segment;

determining a cover image from matching the feature image with the content information.

5. The method of claim 1, wherein the combining the cover image and feature snippet into a feature video comprises:

deleting the repeated feature segments in response to the feature segments being multiple.

6. The method of claim 1, wherein the combining the cover image and feature snippet into a feature video comprises:

performing transition processing on adjacent feature segments in the feature video, wherein the transition processing comprises at least one of the following steps: color transition, scene transition, light transition.

7. The method of any of claims 1 to 6, wherein the method further comprises:

and adding a title to the characteristic video according to the content information.

8. An apparatus for clipping video, comprising:

the scene segment acquiring unit is configured to identify a video frame of a video to be processed and acquire a scene segment of the video to be processed;

a cover image acquisition unit configured to determine content information of a video to be processed according to the scene segment, and extract a cover image according to the content information;

a feature segment extraction unit configured to extract a feature segment of a set time length of the scene segment;

a feature video acquisition unit configured to combine the cover image and the feature clip to constitute a feature video.

9. The apparatus of claim 8, wherein the scene-slice acquiring unit comprises:

the scene information acquisition subunit is configured to perform image recognition on a video frame of the video to be processed to obtain scene information corresponding to the video to be processed, wherein the scene information is used for representing a scene where video content is located;

and the scene segment dividing unit is configured to divide the video to be processed into scene segments according to the scene information.

10. The apparatus of claim 9, wherein the cover image acquisition unit comprises:

an initial object image identification subunit configured to identify an initial object image in the scene segment;

the target object information determining subunit is configured to count the occurrence times and the occurrence time of the initial object image in the video to be processed, and determine target object information according to the occurrence times and the occurrence time;

a content information determining subunit configured to query attribute information of the target object information, and determine content information of the video to be processed according to the attribute information, wherein the attribute information includes at least one of: name of the target object, purpose of the target object.

11. The apparatus of claim 8, wherein the cover image acquisition unit comprises:

a characteristic image obtaining subunit, configured to obtain a characteristic image in the scene segment, where the characteristic image is used to characterize the characteristics of the scene segment;

a cover image determination subunit configured to determine a cover image from matching the feature image with the content information.

12. The apparatus of claim 8, wherein the feature video acquisition unit comprises:

a video deletion subunit, responsive to the feature segment being multiple, configured to delete a duplicate feature segment.

13. The apparatus of claim 8, wherein the feature video acquisition unit comprises:

a transition processing subunit configured to perform transition processing on adjacent feature segments in the feature video, the transition processing including at least one of: color transition, scene transition, light transition.

14. The apparatus of any one of claims 8 to 13, wherein the apparatus further comprises:

a title adding unit configured to add a title to the feature video according to the content information.

15. An electronic device, comprising:

one or more processors;

a memory having one or more programs stored thereon,

the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.

16. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.

Images