WO2017071086A1 - 用于视频播放的方法及装置 - Google Patents

用于视频播放的方法及装置 Download PDF

Info

Publication number
WO2017071086A1
WO2017071086A1 PCT/CN2015/099593 CN2015099593W WO2017071086A1 WO 2017071086 A1 WO2017071086 A1 WO 2017071086A1 CN 2015099593 W CN2015099593 W CN 2015099593W WO 2017071086 A1 WO2017071086 A1 WO 2017071086A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
keyword
target object
target
monitoring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2015/099593
Other languages
English (en)
French (fr)
Inventor
张涛
陈志军
龙飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiaomi Inc
Original Assignee
Xiaomi Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiaomi Inc filed Critical Xiaomi Inc
Priority to MX2016005835A priority Critical patent/MX363623B/es
Priority to RU2016118885A priority patent/RU2016118885A/ru
Priority to KR1020167021969A priority patent/KR101798011B1/ko
Priority to JP2016549720A priority patent/JP6419201B2/ja
Publication of WO2017071086A1 publication Critical patent/WO2017071086A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/238—Interfacing the downstream path of the transmission network, e.g. adapting the transmission rate of a video stream to network bandwidth; Processing of multiplex streams
    • H04N21/2387—Stream processing in response to a playback request from an end-user, e.g. for trick-play
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/482—End-user interface for programme selection
    • H04N21/4828—End-user interface for programme selection for searching programme descriptors
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/41—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G06V20/47—Detecting features for summarising video content
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
    • H04L65/60—Network streaming of media packets
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/232—Content retrieval operation locally within server, e.g. reading video streams from disk arrays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/27—Server based end-user applications
    • H04N21/278—Content descriptor database or directory service for end-user access
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47202—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting content on demand, e.g. video on demand
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/658—Transmission by the client directed to the server
    • H04N21/6587—Control parameters, e.g. trick play commands, viewpoint selection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
    • H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8455—Structuring of content, e.g. decomposing content into time segments involving pointers to the content, e.g. pointers to the I-frames of the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the present disclosure relates to the field of Internet technologies, and in particular, to a method and apparatus for video playback.
  • embodiments of the present disclosure provide a method and apparatus for video playback.
  • Methods include:
  • the play request carries target object information, where the target object information includes a target image where the target object is located or a target keyword to which the target object belongs;
  • the determining, according to the target object information, the video segment in which the target object is located in the monitoring video includes:
  • the determining, according to the target object information, the video segment in which the target object is located in the monitoring video includes:
  • the at least one frame of video images is composed of video segments in which the target object is located in the surveillance video.
  • the method further includes:
  • the index library is generated based on the keyword and the monitoring video.
  • the determining, according to the object type, a keyword that the object that is included in the video image belongs to including :
  • the identity is determined as a keyword to which the object included in the video image belongs.
  • the generating the index database based on the keyword and the monitoring video includes:
  • the generating the index database based on the keyword and the monitoring video includes:
  • the keyword and the video image are stored in a correspondence between a keyword and a video image included in the index library.
  • an apparatus for video playback comprising:
  • a receiving module configured to receive a play request, where the play request carries target object information, where the target object information includes a target image where the target object is located or a target keyword to which the target object belongs;
  • a determining module configured to determine, according to the target object information, a video segment in which the target object is located in the monitoring video
  • the sending module is configured to send the video segment to the terminal, so that the terminal plays the video segment.
  • the fixed modules include:
  • a first determining unit configured to: when the target object information includes a target image in which the target object is located, determine a target category to which the target object belongs based on the specified classification model and the target image;
  • a second determining unit configured to determine, according to the target category, a target keyword to which the target object belongs
  • a third determining unit configured to determine, according to the target keyword, a video segment in which the target object is located in the monitoring video.
  • the determining module includes:
  • a first acquiring unit configured to acquire, according to the target keyword and the stored index library corresponding to the target object information, at least one video image of the target object in the monitoring video;
  • a component unit configured to form the at least one frame of the video image into a video segment in which the target object is located in the monitoring video.
  • the first acquiring unit includes:
  • a first acquiring sub-unit configured to: when the correspondence between the keyword and the monitoring time point is stored in the index library, based on the target keyword corresponding to the target object information, from the keyword and the monitoring time Obtaining at least one monitoring time point in the correspondence between the points;
  • a second acquiring subunit configured to acquire at least one frame of the video image from the monitoring video based on the at least one monitoring time point.
  • the first acquiring unit includes:
  • a third obtaining subunit configured to store between the keyword and the video image in the index library At least one frame of the video image is obtained from the correspondence between the keyword and the video image based on the target keyword corresponding to the target object information.
  • the determining The module also includes:
  • a second obtaining unit configured to acquire a monitoring video
  • a fourth determining unit configured to determine, according to the specified classification model, an object category to which the object included in the video image belongs, for each frame video image in the monitoring video;
  • a fifth determining unit configured to determine, according to the object category, a keyword to which the object included in the video image belongs
  • a generating unit configured to generate the index library based on the keyword and the monitoring video.
  • the fifth determining unit includes:
  • a recognition subunit configured to perform face recognition on an object included in the video image when the object category is a human, to obtain a facial feature
  • a fourth acquiring sub-unit configured to obtain a corresponding identity identifier from a correspondence between the stored facial features and the identity identifiers based on the facial features
  • a first determining subunit configured to determine the identity identifier as a keyword to which the object included in the video image belongs.
  • the generating unit includes:
  • a second determining subunit configured to determine, from the monitoring video, a monitoring time point where the video image is located
  • the first storage subunit is configured to store the keyword and the monitoring time point in a correspondence between a keyword included in the index library and a monitoring time point.
  • the generating unit includes:
  • a second storage subunit configured to store the keyword and the video image in a correspondence between a keyword and a video image included in the index library.
  • an apparatus for video playback comprising:
  • a memory configured to store processor executable instructions
  • processor is configured to:
  • the play request carries target object information, where the target object information includes a target image where the target object is located or a target keyword to which the target object belongs;
  • the server receives a play request, where the play request carries the target object information, and the server determines, according to the target object information, the video segment where the target object is located in the monitoring video, and sends the video segment to the terminal to make the terminal.
  • the video segment of the target object may be directly played, and the video segment of the monitoring video other than the target object is not required to be played, thereby preventing the user from manually adjusting the playback of the monitoring video to view the target object.
  • the video is simple, and the video playback efficiency is improved.
  • FIG. 1 is a schematic diagram of an implementation environment involved in a method for video playback, according to an exemplary embodiment
  • FIG. 2 is a flow chart showing a method for video playback, according to an exemplary embodiment
  • FIG. 3 is a flowchart of another method for video playback, according to an exemplary embodiment
  • FIG. 4 is a block diagram of an apparatus for video playback, according to an exemplary embodiment
  • FIG. 5 is a block diagram of a determining module, according to an exemplary embodiment
  • FIG. 6 is a block diagram of another determining module, according to an exemplary embodiment
  • FIG. 7 is a block diagram of a first obtaining unit according to an exemplary embodiment
  • FIG. 8 is a block diagram of still another determining module according to an exemplary embodiment
  • FIG. 9 is a block diagram of a fifth determining unit, according to an exemplary embodiment.
  • FIG. 10 is a block diagram of a generating unit, according to an exemplary embodiment
  • FIG. 11 is a block diagram of another apparatus for video playback, according to an exemplary embodiment.
  • FIG. 1 is a schematic diagram of an implementation environment involved in a method for video playback, according to an exemplary embodiment.
  • the implementation environment may include a server 101, a smart camera device 102, and a terminal 103.
  • the server 101 can be a server, or a server cluster composed of several servers, or a cloud computing service center.
  • the smart camera device 102 can be a smart camera.
  • the terminal 103 can be a mobile phone, a computer, a tablet device, or the like. Service
  • the server 101 and the smart camera device 102 can be connected through a network, and the server 101 and the terminal 103 can also be connected through a network.
  • the server 101 is configured to receive a play request sent by the terminal, acquire a corresponding video based on the play request, and send the video to the terminal.
  • the smart camera device 102 is configured to collect monitoring video within the monitoring area and send the monitoring video to the server.
  • the terminal 103 is configured to receive a video transmitted by the server and play the video.
  • FIG. 2 is a flowchart of a method for video playing according to an exemplary embodiment. As shown in FIG. 2, the method is used in a server, and includes the following steps.
  • step 201 a play request is received, and the play request carries the target object information, and the target object information includes a target image in which the target object is located or a target keyword to which the target object belongs.
  • step 202 based on the target object information, a video segment in which the target object is located in the surveillance video is determined.
  • step 203 the video segment in which the target object is located in the monitoring video is sent to the terminal, so that the terminal plays the video segment.
  • the server receives a play request, where the play request carries the target object information, and the server determines, according to the target object information, the video segment where the target object is located in the monitoring video, and sends the video segment to the terminal to make the terminal.
  • the video segment of the target object may be directly played, and the video segment of the monitoring video other than the target object is not required to be played, thereby preventing the user from manually adjusting the playback of the monitoring video to view the target object.
  • the video is simple, and the video playback efficiency is improved.
  • determining, according to the target object information, a video segment in which the target object is located in the monitoring video includes:
  • the target object information includes the target image in which the target object is located, determining the target category to which the target object belongs based on the specified classification model and the target image;
  • the video segment in which the target object is located in the surveillance video is determined.
  • the server determines the target category to which the target object belongs based on the specified classification model and the target image, and determines the target keyword to which the target object belongs based on the target category, so that the server can quickly determine that the target object is in the monitoring video based on the target keyword.
  • determining, according to the target object information, a video segment in which the target object is located in the monitoring video includes:
  • At least one frame of the video image is formed into a video segment in which the target object is located in the surveillance video.
  • the server can quickly acquire the target object based on the target keyword and the stored index library. At least one frame of video image in the surveillance video improves video acquisition efficiency.
  • acquiring, according to the target keyword corresponding to the target object information and the stored index library, acquiring at least one frame of the video image of the target object in the monitoring video including:
  • At least one monitoring time point is obtained from the correspondence between the keyword and the monitoring time point based on the target keyword corresponding to the target object information;
  • At least one frame of video image is acquired from the surveillance video based on the at least one monitoring time point.
  • the monitoring video includes a monitoring time point corresponding to each video image included in the monitoring video, so the server may determine at least one monitoring time point corresponding to the target keyword, and obtain, from the monitoring video, the at least one monitoring time point. At least one frame of video image improves the accuracy of video image acquisition.
  • acquiring, according to the target keyword corresponding to the target object information and the stored index library, acquiring at least one frame of the video image of the target object in the monitoring video including:
  • the target keyword corresponding to the information acquires at least one frame of the video image from the correspondence between the keyword and the video image.
  • the server directly acquires at least one video image corresponding to the target object based on the target keyword, thereby improving the video image acquisition efficiency.
  • the method before acquiring the at least one frame of the video image in the monitoring video, the method further includes:
  • the server generates an index library based on the keyword and the monitoring video, which can facilitate the server to quickly acquire at least one video image of the target object in the monitoring video based on the index library when receiving the playback request, and improve the video image.
  • the efficiency of the acquisition can be performed by the server to quickly acquire at least one video image of the target object in the monitoring video based on the index library when receiving the playback request, and improve the video image.
  • determining, based on the object category, a keyword to which the object included in the video image belongs includes:
  • the identity is determined as a keyword to which the object included in the video image belongs.
  • the server determines the identity of the object as the target keyword of the object, which may facilitate the terminal to acquire at least one video image of the person having the specific identity in the monitoring video, which may be targeted. Get a video segment of a person.
  • generating an index library based on keywords and monitoring video includes:
  • the keywords and the monitoring time points are stored in the correspondence between the keywords included in the index library and the monitoring time points.
  • the server Since the monitoring video includes the monitoring time point corresponding to each frame of the video image, the server stores the keyword and the monitoring time point in the correspondence between the keyword included in the index library and the monitoring time point, which can facilitate the server to be based on the keyword. Obtaining a corresponding monitoring time point, and then acquiring a video image corresponding to the monitoring time point from the monitoring video, thereby improving the accuracy of obtaining the video image.
  • generating an index library based on keywords and monitoring video includes:
  • the keywords and video images are stored in a correspondence between keywords and video images included in the index library.
  • the server stores the keyword and the video image in the correspondence between the keyword and the video image included in the index library, which can facilitate the server to directly obtain the corresponding video image based on the keyword, thereby improving the video image acquisition efficiency.
  • FIG. 3 is a flowchart of a method for video playback according to an exemplary embodiment. As shown in FIG. 3, the method includes the following steps.
  • the server receives a play request, where the play request carries target object information, and the target object information includes a target image where the target object is located or a target keyword to which the target object belongs.
  • the play request may be directly sent by the terminal, of course, the play request It can also be sent by the terminal to other devices, and then sent to the server by other devices, which is not specifically limited in the embodiment of the present disclosure.
  • the terminal when the terminal sends a play request, the terminal may send a play request to the server or other device when receiving the play instruction.
  • the play instruction is configured to obtain a video segment in which the target object is located in the monitoring video, and the play instruction may be triggered by the user, and the user may trigger by a specified operation, which may be a click operation, a slide operation, or a voice operation. Etc., the embodiments of the present disclosure do not specifically limit this.
  • the target image is an image including the target object, and the target image may be a photo of the target object, or the terminal selects a selection instruction when the terminal receives the selection instruction based on the video image of the monitoring video during the playing of the monitoring video.
  • the image of the target object is carried in the image, and the target image may be obtained by other means. The embodiment of the present disclosure does not specifically limit this.
  • the target keyword uniquely corresponds to the target object
  • the target keyword may be the category to which the target object belongs, the identity of the target object, and the like, which are not specifically limited in this embodiment of the present disclosure.
  • step 302 the server determines a video segment in which the target object is located in the surveillance video based on the target object information.
  • the target object information includes the image of the target object or the target keyword to which the target object belongs. Therefore, according to the different content included in the target object information, the server determines, according to the target object information, the video segment in which the target object is located in the monitoring video. There are two ways:
  • the first method is: acquiring at least one video image of the target object in the monitoring video based on the target keyword corresponding to the target object information and the stored index database, and composing the at least one frame of the video image into the target object in the monitoring The video segment in the video.
  • the server can acquire the target.
  • the object is at least one frame of the video image in which the video is located, and the at least one frame of the video image is formed into a video segment in which the target object is located in the surveillance video.
  • the target keyword corresponding to the target object information may be a target keyword included in the target object information, and when the target object includes the target image, the target object information corresponds to The target keyword can be obtained from the target image.
  • the server is based on the target keyword and the stored index database, and when the target object is at least one video image in the monitoring video, when the correspondence between the keyword and the monitoring time point is stored in the index library, the server is based on The target keyword obtains at least one monitoring time point from the correspondence between the keyword and the monitoring time point, and acquires at least one frame of the video image from the monitoring video based on the at least one monitoring time point.
  • the index library stores the correspondence between the keyword and the video image
  • the server acquires at least one frame of the video image from the correspondence between the keyword and the video image based on the target keyword.
  • the monitoring video includes a monitoring time point corresponding to each video image included in the monitoring video. Therefore, when the server is based on the target keyword, the corresponding relationship between the keyword and the monitoring time point, the corresponding target keyword is obtained. After the at least one monitoring time point, the server may acquire at least one video image corresponding to the at least one monitoring time point from the monitoring video based on the at least one monitoring time point.
  • the process of obtaining at least one frame of the video image from the monitoring video may be referred to the related art based on the at least one monitoring time point.
  • the embodiments of the present disclosure are not described in detail herein.
  • the server may be based on the target keyword Yang Lele, from the keywords and monitoring time points shown in Table 1 below.
  • at least one monitoring time point corresponding to Yang Lele is 2015/02/03-21:08:31, 2015/03/05-11:08:11, 2015/08/03-09:05:31, after that, the server can get 2015/02/03-21:08:31, 2015/03/05-11:08:11, 2015/08/ from the surveillance video.
  • the server may be based on the target keyword Yang Lele, from the correspondence between the keyword and the video image shown in Table 2 below.
  • at least one frame of video images corresponding to Yang Lele is obtained as 1. JPEG, 2. JPEG, and 3. JPEG.
  • the server composes the at least one frame of the video image into the video segment in which the target object is located in the monitoring video, reference may be made to the related art, which is not described in detail herein.
  • the server may further generate an index library by using the following steps (1)-(4) before acquiring the at least one video image of the target object in the monitoring video based on the target keyword and the stored index database, including:
  • the server obtains the surveillance video.
  • the server may obtain the monitoring video from the smart camera device.
  • the smart camera device may also send the monitoring video to other devices, so that the server can obtain the monitoring video from other devices.
  • the embodiment does not specifically limit this.
  • the smart camera device is configured to collect the monitoring video in the monitoring area, and the process of the smart camera device collecting the monitoring video in the monitoring area may refer to related technologies, and the embodiments of the present disclosure are not described in detail herein.
  • the smart camera device can communicate with a server or other device through a wired network or a wireless network, and when the smart camera device communicates with a server or other device through a wireless network, the smart camera device can pass the built-in wireless fidelity (English: WIreless-FIdelity (WIFI), Bluetooth or other wireless communication chip to communicate with a server or other device, which is not specifically limited in the embodiment of the present disclosure.
  • WIFI wireless-fidelity
  • Bluetooth Bluetooth
  • the server determines the object class to which the object included in the video image belongs based on the specified classification model.
  • the specified classification model is used to determine the object category corresponding to the image, and the specified classification model can be established in advance.
  • the specified classification model can generally process the image of the preset size to determine the object category to which the object included in the image belongs, and therefore, the server is based on the specified classification model.
  • the server may crop the area where the object is located in the video image of the surveillance video, obtain the object image, and process the size of the object image to a preset size, and then Determining the object based on the specified classification model and the processed object image The object category of the genus.
  • the server cuts the area where the object is located in the video image of the monitoring video, and obtains the circumscribed rectangle of the object from the video image in which the object is located, and determines the circumscribed rectangle as the image.
  • the image area in which the object is in the surveillance video ie the object image.
  • the server may also perform the cropping of the area in which the object is located in other manners to obtain an object image, which is not specifically limited in this embodiment of the present disclosure.
  • the preset size may be preset, for example, the preset size may be 224*224 pixels, 300*300 pixels, and the like, which is not specifically limited in the embodiment of the present disclosure.
  • the server determines a keyword to which the object included in the video image belongs based on the object category to which the object included in the video image belongs.
  • the object category to which the object included in the video image belongs may be a person, may also be a pet, and may also be other objects.
  • the terminal needs to acquire a person with a specific identity. Or the video segment in which the pet is located in the monitoring video. Therefore, the server determines, according to the object category to which the object included in the video image belongs, the operation of the keyword to which the object included in the video image belongs: when the object included in the video image belongs to When the object type is a person, the server performs face recognition on the object to obtain a face feature, and then obtains a corresponding identity identifier from the corresponding relationship between the stored face feature and the identity identifier based on the face feature.
  • the server obtains the pet identifier based on the video image, and obtains the corresponding identity identifier from the stored correspondence between the pet identifier and the identity identifier, and based on the pet identifier, The identity is determined as a keyword to which the object included in the video image belongs.
  • the server can directly determine the object category as the keyword to which the object included in the video image belongs.
  • the server performs face recognition on the object, and the process of obtaining the face feature can refer to related technologies, and the embodiments of the present disclosure are not described in detail herein.
  • the pet identifier is used to uniquely identify the pet, and the pet identifier may be obtained by using a two-dimensional code, a barcode, or other identifiable identifier placed on the pet, which is not specifically limited in this embodiment of the present disclosure. .
  • the server when the object category to which the object included in the video image belongs is a person, the server performs face recognition on the object to obtain a face feature of A, and then, based on the face feature A, a face feature as shown in Table 3 below.
  • the server may determine Yang Lele as the keyword to which the object included in the video image belongs.
  • the server scans the two-dimensional code, the barcode, or other identifiable identifier placed on the pet based on the video image, and obtains the pet identifier as ID1, and then, based on The pet identifier ID1, from the correspondence between the pet identifier and the identity identifier shown in Table 4 below, obtains the identity identifier corresponding to ID1 as the pea, and the server may determine the bean as the object to be included in the video image. Key words.
  • the server may receive the first setting information sent by the terminal, in the first setting information, before the server obtains the corresponding identity identifier from the corresponding relationship between the stored face feature and the identity identifier.
  • the server Carrying the identity of the object and the face image of the object, the server extracts the feature of the face image, obtains the face feature of the object, and stores the face feature and the identity identifier in the face feature and the identity identifier. The correspondence between them.
  • the first setting information sent by the terminal carries the identity identifier and the face image, and the identity identifier is Yang Lele.
  • the server extracts the feature of the face image to obtain the face feature A, and the server can store the A and Yang Lele.
  • the face features and the identity as shown in Table 3.
  • the server may receive, according to the pet identifier, the second setting information sent by the terminal, where the second setting information is carried in the second setting information, before the corresponding identity is obtained from the corresponding relationship between the stored pet identifier and the identity identifier.
  • the identity of the object and the pet identifier of the object, the server the pet identifier and the identity identifier are stored in a correspondence between the pet identifier and the identity identifier.
  • the second setting information sent by the terminal carries the identity identifier and the pet identifier, and the identity identifier is pea, and the pet identifier is ID1, and the server may store the ID1 and the pea in the table 4. The correspondence between the pet identification and the identity identification shown.
  • the server generates an index library based on the keyword and the monitoring video.
  • the server Since the correspondence between the keyword and the monitoring time point can be stored in the index library, the correspondence between the keyword and the video image can also be stored. Therefore, the server generates an index library based on the keyword and the monitoring video.
  • the server may determine, according to the correspondence between the keyword and the monitoring time point, the monitoring time point of the video image, and store the keyword and the monitoring time point in the monitoring video.
  • the correspondence between the keywords included in the index library and the monitoring time point is stored in the index library
  • the server stores the keyword and the video image in a correspondence between the keyword and the video image included in the index library.
  • the monitoring video includes a monitoring time point corresponding to each video image in the monitoring video. Therefore, when the server determines that a video image of an object exists, the video image may be obtained from the monitoring video to which the video image belongs.
  • the monitoring time point corresponding to the video image after which the server can store the keyword to which the object belongs and the monitoring time point in the correspondence between the keyword included in the index library and the monitoring time point.
  • the keyword to which the object belongs is Yang Lele
  • the server determines from the monitoring video that the monitoring time point of the video image of Yang Lele is 2015/08/03-09:05:31
  • the server can be Yang Lele and 2015/ 08/03-09:05:31 is stored in the correspondence between the keywords as shown in Table 1 and the monitoring time point.
  • the keyword to which the object belongs is Yang Lele
  • the video image of Yang Lele in the surveillance video is 3.JPEG
  • the server can store Yang Lele and 3.JPEG between the keyword and the video image as shown in Table 2. In the correspondence.
  • the second mode when the target object information includes the target image where the target object is located, the server determines the target category to which the target object belongs based on the specified classification model and the target image, and determines the target keyword to which the target object belongs based on the target category, and further Based on the target keyword, determine The video segment in which the target object is in the surveillance video.
  • the server may determine the size of the target image as a preset size based on the specified classification model and the target image, and determine, according to the specified classification model and the processed target image, the target image includes The target category to which the target object belongs.
  • the process of determining the target category to which the target object belongs based on the specified classification model and the processed target image may refer to related technologies, and the embodiments of the present disclosure are not described in detail herein.
  • step (3) the process of determining the target keyword to which the target object belongs based on the target category is similar to the determining process of step (3) in the first mode in step 302.
  • step 303 the server sends the video segment in which the target object is located in the monitoring video to the terminal, so that the terminal plays the video segment.
  • the terminal when the terminal plays the video segment, the terminal can be played not only by the playing module set in the terminal, but also the terminal can also be played by the playing application installed by the terminal.
  • the server acquires a monitoring video, and determines an object category to which the object included in the video image of the monitoring video belongs based on the specified classification model, and further determines a keyword to which the object belongs based on the object category, and The keyword and the monitoring time point corresponding to the keyword or the video image corresponding to the keyword and the keyword are stored in the index library, and then, when the server receives the play request, based on the target object information carried by the play request, Determining the target keyword to which the target object belongs, and obtaining the target based on the target keyword and the stored index library Targeting at least one frame of video image in the monitoring video, and composing the at least one frame of video image into a video segment in which the target object is located in the monitoring video, and then transmitting the video segment to the terminal, so that the terminal can Directly playing the video segment of the target object in the surveillance video, without playing the video segment of the surveillance video other than the target object, thereby preventing the user from manually adjusting the playback of the surveillance video
  • FIG. 4 is a block diagram of an apparatus for video playback, according to an exemplary embodiment.
  • the apparatus includes a receiving module 401, a determining module 402, and a transmitting module 403.
  • the receiving module 401 is configured to receive a play request, where the play request carries information, and the target object information includes a target image where the target object is located or a target keyword to which the target object belongs;
  • the determining module 402 is configured to determine, according to the target object information, a video segment in which the target object is located in the monitoring video;
  • the sending module 403 is configured to send the video segment to the terminal, so that the terminal plays the video segment.
  • the determining module 402 includes:
  • the first determining unit 4021 is configured to: when the target object information includes the target image where the target object is located, determine the target category to which the target object belongs based on the specified classification model and the target image;
  • the second determining unit 4022 is configured to determine, according to the target category, a target keyword to which the target object belongs;
  • the third determining unit 4023 is configured to determine, according to the target keyword, a video segment in which the target object is located in the monitoring video.
  • the determining module 402 includes a first obtaining unit 4024, which is a unit 4025.
  • the first obtaining unit 4024 is configured to acquire, according to the target keyword corresponding to the target object information and the stored index library, the at least one frame video image of the target object in the monitoring video;
  • the component unit 4025 is configured to compose at least one frame of the video image into the target object in the monitoring video.
  • the first obtaining unit 4024 includes a first obtaining subunit 40241 and a second obtaining subunit 40242.
  • the first obtaining sub-unit 40241 is configured to: when the correspondence between the keyword and the monitoring time point is stored in the index library, based on the target keyword corresponding to the target object information, from the correspondence between the keyword and the monitoring time point , obtaining at least one monitoring time point;
  • the second obtaining subunit 40242 is configured to acquire at least one frame of the video image from the monitoring video based on the at least one monitoring time point.
  • the first obtaining unit 4024 includes:
  • the third obtaining subunit is configured to: when the correspondence between the keyword and the video image is stored in the index library, obtain at least the correspondence between the keyword and the video image based on the target keyword corresponding to the target object information One frame of video image.
  • the determining module 402 further includes a second obtaining unit 4026, a fourth determining unit 4027, a fifth determining unit 4028, and a generating unit 4029.
  • the second obtaining unit 4026 is configured to receive the monitoring video sent by the smart camera device
  • the fourth determining unit 4027 is configured to determine, according to the specified classification model, the object category to which the object included in the video image belongs, for each frame video image in the surveillance video;
  • the fifth determining unit 4028 is configured to determine, according to the object category, a keyword to which the object included in the video image belongs;
  • a generating unit 4029 is configured to generate an index library based on the keywords and the monitoring video.
  • the fifth determining unit 4028 includes an identifying subunit 40281, a fourth obtaining subunit 40282, and a first determining subunit 40283.
  • the identification sub-unit 40281 is configured to perform face recognition on the object included in the video image when the object category is a person, to obtain a face feature;
  • a fourth acquisition sub-unit 40282 configured to store facial features and body based on facial features Obtain a corresponding identity in the correspondence between the identifiers
  • the first determining sub-unit 40283 is configured to determine the identity identifier as a keyword to which the object included in the video image belongs.
  • the generating unit 4029 includes a second determining subunit 40291, a first storage subunit 40292.
  • the second determining subunit 40291 is configured to determine, from the monitoring video, a monitoring time point at which the video image is located;
  • the first storage sub-unit 40292 is configured to store the keyword and the monitoring time point in a correspondence between the keyword included in the index library and the monitoring time point.
  • the generating unit 4029 includes:
  • the second storage subunit is configured to store the keyword and the video image in a correspondence between the keyword and the video image included in the index library.
  • the server receives a play request, where the play request carries the target object information, and the server determines, according to the target object information, the video segment where the target object is located in the monitoring video, and sends the video segment to the terminal to make the terminal.
  • the video segment of the target object may be directly played, and the video segment of the monitoring video other than the target object is not required to be played, thereby preventing the user from manually adjusting the playback of the monitoring video to view the target object.
  • the video is simple, and the video playback efficiency is improved.
  • FIG. 11 is a block diagram of an apparatus 1100 for video playback, according to an exemplary embodiment.
  • device 1100 can be provided as a server.
  • apparatus 1100 includes a processing component 1122 that further includes one or more processors, and memory resources represented by memory 1132, configured to store instructions executable by processing component 1122, such as an application.
  • the application stored in the memory 1132 may include one or more of each A module that corresponds to a set of instructions.
  • the device 1100 can also include a power supply component 1126 configured to perform power management of the device 1100, a wired or wireless network interface 1150 configured to connect the device 1100 to the network, and an input/output (I/O) interface 1158.
  • the device 1100 can operate based on an operating system stored in the memory 1132, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • processing component 1122 is configured to execute instructions to perform the video playback method described below, the method comprising:
  • the play request carries the target object information
  • the target object information includes a target image where the target object is located or a target keyword to which the target object belongs.
  • the video segment in which the target object is located in the surveillance video is determined.
  • the video segment in which the target object is located in the monitoring video is sent to the terminal, so that the terminal plays the video segment.
  • determining, according to the target object information, a video segment in which the target object is located in the monitoring video includes:
  • the target object information includes the target image in which the target object is located, determining the target category to which the target object belongs based on the specified classification model and the target image;
  • the video segment in which the target object is located in the surveillance video is determined.
  • determining, according to the target object information, a video segment in which the target object is located in the monitoring video includes:
  • At least one frame of the video image is formed into a video segment in which the target object is located in the surveillance video.
  • the target keyword and the corresponding information corresponding to the target object information obtains at least one video image of the target object in the monitoring video, including:
  • At least one monitoring time point is obtained from the correspondence between the keyword and the monitoring time point based on the target keyword corresponding to the target object information;
  • At least one frame of video image is acquired from the surveillance video based on the at least one monitoring time point.
  • acquiring, according to the target keyword corresponding to the target object information and the stored index library, acquiring at least one frame of the video image of the target object in the monitoring video including:
  • At least one frame of the video image is obtained from the correspondence between the keyword and the video image based on the target keyword corresponding to the target object information.
  • the method before acquiring the at least one frame of the video image in the monitoring video, the method further includes:
  • determining, based on the object category, a keyword to which the object included in the video image belongs includes:
  • the identity is determined as a keyword to which the object included in the video image belongs.
  • generating an index library based on keywords and monitoring video includes:
  • the keywords and the monitoring time points are stored in the correspondence between the keywords included in the index library and the monitoring time points.
  • generating an index library based on keywords and monitoring video includes:
  • the keywords and video images are stored in a correspondence between keywords and video images included in the index library.
  • the server receives a play request, where the play request carries the target object information, and the server determines, according to the target object information, the video segment where the target object is located in the monitoring video, and sends the video segment to the terminal to make the terminal.
  • the video segment of the target object may be directly played, and the video segment of the monitoring video other than the target object is not required to be played, thereby preventing the user from manually adjusting the playback of the monitoring video to view the target object.
  • the video is simple, and the video playback efficiency is improved.
  • the server receives a play request, where the play request carries the target object information, and the server determines, according to the target object information, the video segment where the target object is located in the monitoring video, and sends the video segment to the terminal to make the terminal.
  • the video segment of the target object may be directly played, and the video segment of the monitoring video other than the target object is not required to be played, thereby preventing the user from manually adjusting the playback of the monitoring video to view the target object.
  • the video is simple, and the video playback efficiency is improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Television Signal Processing For Recording (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本公开实施例是关于一种用于视频播放的方法及装置，属于互联网技术领域。所述方法包括：接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；将所述视频段发送给终端，使所述终端播放所述视频段。

Description

用于视频播放的方法及装置
相关申请的交叉引用
本申请基于申请号为201510713118.3、申请日为2015年10月28日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及互联网技术领域，尤其涉及一种用于视频播放的方法及装置。
背景技术
随着摄像头的普及，利用摄像头进行实时监控越来越流行。由于利用摄像头实时监控得到的监控视频具有时间上的连续性，所以，当用户想要查看监控视频中的特定对象的行为时，比如用户想要查看监控视频中婴儿的行为时，用户往往需要在监控视频播放的过程中，手动地对监控视频的播放进度进行调整，使监控视频前进或者后退到特定对象所在的视频画面，从而查看特定对象的行为。而用户手动对监控视频的播放进度进行调整的操作比较繁琐，降低了视频播放效率，因此，亟需一种提高视频播放效率的用于视频播放的方法。
发明内容
为克服相关技术中存在的问题，本公开实施例提供一种用于视频播放的方法及装置。
根据本公开实施例的第一方面，提供一种用于视频播放的方法，所述 方法包括：
接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；
基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
将所述视频段发送给终端，使所述终端播放所述视频段。
结合第一方面，在上述第一方面的第一种可能的实现方式中，所述基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段，包括：
当所述目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和所述目标图像，确定所述目标对象所属的目标类别；
基于所述目标类别，确定所述目标对象所属的目标关键词；
基于所述目标关键词，确定所述目标对象在所述监控视频中所处的视频段。
结合第一方面，在上述第一方面的第二种可能的实现方式中，所述基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段，包括：
基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像；
将所述至少一帧视频图像组成所述目标对象在所述监控视频中所处的视频段。
结合第一方面的第二种可能的实现方式，在上述第一方面的第三种可能的实现方式中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像，包括：
当所述索引库中存储关键词与监控时间点之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
基于所述至少一个监控时间点，从所述监控视频中，获取至少一帧视频图像。
结合第一方面的第二种可能的实现方式，在上述第一方面的第四种可能的实现方式中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像，包括：
当所述索引库中存储关键词与视频图像之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
结合第一方面的第二种可能的实现方式至第一方面的第四种可能的实现方式中任一可能的实现方式，在上述第一方面的第五种可能的实现方式中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中的至少一帧视频图像之前，还包括：
获取监控视频；
对于所述监控视频中每帧视频图像，基于指定分类模型，确定所述视频图像包括的对象所属的对象类别；
基于所述对象类别，确定所述视频图像包括的对象所属的关键词；
基于所述关键词和所述监控视频，生成所述索引库。
结合第一方面的第五种可能的实现方式，在上述第一方面的第六种可能的实现方式中，所述基于所述对象类别，确定所述视频图像包括的对象所属的关键词，包括：
当所述对象类别为人时，对所述视频图像包括的对象进行人脸识别， 得到人脸特征；
基于所述人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
将所述身份标识确定为所述视频图像包括的对象所属的关键词。
结合第一方面的第五种可能的实现方式，在上述第一方面的第七种可能的实现方式中，所述基于所述关键词和所述监控视频，生成所述索引库，包括：
从所述监控视频中，确定所述视频图像所在的监控时间点；
将所述关键词和所述监控时间点存储在所述索引库包括的关键词与监控时间点之间的对应关系中。
结合第一方面的第五种可能的实现方式，在上述第一方面的第八种可能的实现方式中，所述基于所述关键词和所述监控视频，生成所述索引库，包括：
将所述关键词和所述视频图像存储在所述索引库包括的关键词与视频图像之间的对应关系中。
根据本公开实施例的第二方面，提供一种用于视频播放的装置，所述装置包括：
接收模块，配置为接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；
确定模块，配置为基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
发送模块，配置为将所述视频段发送给终端，使所述终端播放所述视频段。
结合第二方面，在上述第二方面的第一种可能的实现方式中，所述确 定模块包括：
第一确定单元，配置为当所述目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和所述目标图像，确定所述目标对象所属的目标类别；
第二确定单元，配置为基于所述目标类别，确定所述目标对象所属的目标关键词；
第三确定单元，配置为基于所述目标关键词，确定所述目标对象在所述监控视频中所处的视频段。
结合第二方面，在上述第二方面的第二种可能的实现方式中，所述确定模块包括：
第一获取单元，配置为基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像；
组成单元，配置为将所述至少一帧视频图像组成所述目标对象在所述监控视频中所处的视频段。
结合第二方面的第二种可能的实现方式，在上述第二方面的第三种可能的实现方式中，所述第一获取单元包括：
第一获取子单元，配置为当所述索引库中存储关键词与监控时间点之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
第二获取子单元，配置为基于所述至少一个监控时间点，从所述监控视频中，获取至少一帧视频图像。
结合第二方面的第二种可能的实现方式，在上述第二方面的第四种可能的实现方式中，所述第一获取单元包括：
第三获取子单元，配置为当所述索引库中存储关键词与视频图像之间 的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
结合第二方面的第二种可能的实现方式至第二方面的第四种可能的实现方式中任一可能的实现方式，在上述第二方面的第五种可能的实现方式中，所述确定模块还包括：
第二获取单元，配置为获取监控视频；
第四确定单元，配置为对于所述监控视频中每帧视频图像，基于指定分类模型，确定所述视频图像包括的对象所属的对象类别；
第五确定单元，配置为基于所述对象类别，确定所述视频图像包括的对象所属的关键词；
生成单元，配置为基于所述关键词和所述监控视频，生成所述索引库。
结合第二方面的第五种可能的实现方式，在上述第二方面的第六种可能的实现方式中，所述第五确定单元包括：
识别子单元，配置为当所述对象类别为人时，对所述视频图像包括的对象进行人脸识别，得到人脸特征；
第四获取子单元，配置为基于所述人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
第一确定子单元，配置为将所述身份标识确定为所述视频图像包括的对象所属的关键词。
结合第二方面的第五种可能的实现方式，在上述第二方面的第七种可能的实现方式中，所述生成单元包括：
第二确定子单元，配置为从所述监控视频中，确定所述视频图像所在的监控时间点；
第一存储子单元，配置为将所述关键词和所述监控时间点存储在所述索引库包括的关键词与监控时间点之间的对应关系中。
结合第二方面的第五种可能的实现方式，在上述第二方面的第八种可能的实现方式中，所述生成单元包括：
第二存储子单元，配置为将所述关键词和所述视频图像存储在所述索引库包括的关键词与视频图像之间的对应关系中。
根据本公开实施例的第三方面，提供一种用于视频播放的装置，所述装置包括：
处理器；
配置为存储处理器可执行指令的存储器；
其中，所述处理器被配置为：
接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；
基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
将所述视频段发送给终端，使所述终端播放所述视频段。
在本公开实施例中，服务器接收播放请求，该播放请求中携带目标对象信息，服务器基于目标对象信息确定目标对象在监控视频中所处的视频段，并将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本发明的实施例，并与说明书一起用于解释本发明的原理。
图1是根据一示例性实施例示出的一种用于视频播放的方法所涉及的实施环境的示意图；
图2是根据一示例性实施例示出的一种用于视频播放的方法的流程图；
图3是根据一示例性实施例示出的另一种用于视频播放的方法的流程图；
图4是根据一示例性实施例示出的一种用于视频播放的装置的框图；
图5是根据一示例性实施例示出的一种确定模块的框图；
图6是根据一示例性实施例示出的另一种确定模块的框图；
图7是根据一示例性实施例示出的一种第一获取单元的框图；
图8是根据一示例性实施例示出的又一种确定模块的框图；
图9是根据一示例性实施例示出的一种第五确定单元的框图；
图10是根据一示例性实施例示出的一种生成单元的框图；
图11是根据一示例性实施例示出的另一种用于视频播放的装置的框图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本发明相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本发明的一些方面相一致的装置和方法的例子。
图1是根据一示例性实施例示出的一种用于视频播放的方法所涉及的实施环境的示意图。如图1所示，该实施环境可以包括：服务器101、智能摄像设备102和终端103。服务器101可以是一台服务器，或者是由若干台服务器组成的服务器集群，或者是一个云计算服务中心，智能摄像设备102可以是智能摄像机，终端103可以是移动电话，计算机，平板设备等。服 务器101和智能摄像设备102之间可以通过网络进行连接，服务器101与终端103之间也可以通过网络进行连接。服务器101配置为接收终端发送的播放请求，基于该播放请求获取对应的视频，并将该视频发送给终端。智能摄像设备102配置为采集监控区域内的监控视频，并将监控视频发送给服务器。终端103配置为接收服务器发送的视频，并播放该视频。
图2是根据一示例性实施例示出的一种用于视频播放的方法的流程图，如图2所示，该方法用于服务器中，包括以下步骤。
在步骤201中，接收播放请求，播放请求中携带目标对象信息，目标对象信息包括目标对象所在的目标图像或者目标对象所属的目标关键词。
在步骤202中，基于目标对象信息，确定目标对象在监控视频中所处的视频段。
在步骤203中，将目标对象在监控视频中所处的视频段发送给终端，使终端播放该视频段。
在本公开实施例中，服务器接收播放请求，该播放请求中携带目标对象信息，服务器基于目标对象信息确定目标对象在监控视频中所处的视频段，并将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。
在本公开的另一实施例中，基于目标对象信息，确定目标对象在监控视频中所处的视频段，包括：
当目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和目标图像，确定目标对象所属的目标类别；
基于目标类别，确定目标对象所属的目标关键词；
基于目标关键词，确定目标对象在监控视频中所处的视频段。
其中，服务器基于指定分类模型和目标图像，确定目标对象所属的目标类别，并基于该目标类别，确定目标对象所属的目标关键词，可以便于服务器基于该目标关键词快速确定目标对象在监控视频中所处的视频段。
在本公开的另一实施例中，基于目标对象信息，确定目标对象在监控视频中所处的视频段，包括：
基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像；
将至少一帧视频图像组成目标对象在监控视频中所处的视频段。
由于终端发送播放请求是为了获取目标对象在监控视频中所处的视频段，而视频段可以由至少一帧视频图像组成，因此，服务器基于目标关键词和存储的索引库，可以快速获取目标对象在监控视频中所处的至少一帧视频图像，提高了视频获取效率。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像，包括：
当索引库中存储关键词与监控时间点之间的对应关系时，基于目标对象信息对应的目标关键词，从关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
基于至少一个监控时间点，从监控视频中，获取至少一帧视频图像。
由于监控视频中包括该监控视频包括的每帧视频图像对应的监控时间点，因此，服务器可以确定目标关键词对应的至少一个监控时间点，并从监控视频中，获取该至少一个监控时间点对应的至少一帧视频图像，提高了视频图像的获取准确性。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像，包括：
当索引库中存储关键词与视频图像之间的对应关系时，基于目标对象 信息对应的目标关键词，从关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
其中，服务器基于目标关键词，直接获取目标对象对应的至少一帧视频图像，提高了视频图像获取效率。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中的至少一帧视频图像之前，还包括：
获取监控视频；
对于监控视频中每帧视频图像，基于指定分类模型，确定视频图像包括的对象所属的对象类别；
基于对象类别，确定视频图像包括的对象所属的关键词；
基于关键词和监控视频，生成索引库。
其中，服务器基于关键词和监控视频，生成索引库，可以便于服务器在接收到播放请求时，基于该索引库，快速获取目标对象在监控视频中所处的至少一帧视频图像，提高了视频图像的获取效率。
在本公开的另一实施例中，基于对象类别，确定视频图像包括的对象所属的关键词，包括：
当对象类别为人时，对视频图像包括的对象进行人脸识别，得到人脸特征；
基于人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
将身份标识确定为视频图像包括的对象所属的关键词。
其中，当对象类别为人时，服务器将对象的身份标识确定为该对象所述的目标关键词，可以便于终端获取具有特定身份的人在监控视频中所处的至少一帧视频图像，可以针对性地获取某一个人的视频段。
在本公开的另一实施例中，基于关键词和监控视频，生成索引库，包括：
从监控视频中，确定视频图像所在的监控时间点；
将关键词和监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中。
由于监控视频中包括每帧视频图像对应的监控时间点，因此，服务器将关键词和监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中，可以便于服务器基于关键词，获取对应的监控时间点，进而从监控视频中，获取该监控时间点对应的视频图像，提高了视频图像的获取准确性。
在本公开的另一实施例中，基于关键词和监控视频，生成索引库，包括：
将关键词和视频图像存储在索引库包括的关键词与视频图像之间的对应关系中。
其中，服务器将关键词和视频图像存储在索引库包括的关键词与视频图像之间的对应关系中，可以便于服务器基于关键词，直接获取对应的视频图像，提高了视频图像获取效率。
上述所有可选技术方案，均可按照任意结合形成本公开的可选实施例，本公开实施例对此不再一一赘述。
图3是根据一示例性实施例示出的一种用于视频播放的方法的流程图，如图3所示，该方法包括以下步骤。
在步骤301中，服务器接收播放请求，该播放请求中携带目标对象信息，目标对象信息包括目标对象所在的目标图像或者目标对象所属的目标关键词。
需要说明的是，该播放请求可以由终端直接发送，当然，该播放请求 也可以由终端先发送给其它设备，再由其它设备发送给服务器，本公开实施例对此不做具体限定。
另外，当终端发送播放请求时，该终端可以在接收到播放指令时，向服务器或者其它设备发送播放请求。
需要说明的是，播放指令配置为获取目标对象在监控视频中所处的视频段，且播放指令可以由用户触发，用户可以通过指定操作触发，该指定操作可以为点击操作、滑动操作、语音操作等等，本公开实施例对此不做具体限定。
另外，目标图像为包括目标对象的图像，且该目标图像可以为目标对象的照片，或者是终端在播放监控视频的过程中，当终端基于监控视频的视频图像接收到选择指令时，该选择指令中携带目标对象的图像，当然，目标图像还可以通过其它方式获取得到，本公开实施例对此不做具体限定。
再者，目标关键词与目标对象唯一对应，且目标关键词可以为目标对象所属的类别、目标对象的身份标识等等，本公开实施例对此不做具体限定。
在步骤302中，服务器基于目标对象信息，确定目标对象在监控视频中所处的视频段。
由于目标对象信息中包括目标对象所在的图像或者目标对象所属的目标关键词，因此，根据目标对象信息包括的不同内容，服务器基于目标对象信息，确定目标对象在监控视频中所处的视频段可以有如下两种方式：
第一种方式：基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像，并将该至少一帧视频图像组成目标对象在该监控视频中所处的视频段。
由于终端发送播放请求是为了获取目标对象在监控视频中所处的视频段，而视频段可以由至少一帧视频图像组成，因此，服务器可以获取目标 对象在监控视频中所处的至少一帧视频图像，并将该至少一帧视频图像组成目标对象在监控视频中所处的视频段。
需要说明的是，当目标对象信息包括目标关键词时，目标对象信息对应的目标关键词可以为该目标对象信息中包括的目标关键词，当目标对象信息中包括目标图像时，目标对象信息对应的目标关键词可以通过该目标图像获取得到。
其中，服务器基于目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像时，当索引库中存储关键词与监控时间点之间的对应关系时，服务器基于目标关键词，从该关键词与监控时间点之间的对应关系中，获取至少一个监控时间点，并基于该至少一个监控时间点，从监控视频中，获取至少一帧视频图像。或者，当索引库中存储关键词与视频图像之间的对应关系时，服务器基于目标关键词，从该关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
由于监控视频中包括该监控视频包括的每帧视频图像对应的监控时间点，因此，当服务器基于目标关键词，该关键词与监控时间点之间的对应关系中，获取该目标关键词对应的至少一个监控时间点之后，服务器可以基于该至少一个监控时间点，从该监控视频中，获取该至少一个监控时间点对应的至少一帧视频图像。
其中，服务器基于该至少一个监控时间点，从监控视频中，获取至少一帧视频图像的过程可以参考相关技术，本公开实施例在此不进行详细阐述。
例如，当索引库中存储关键词与监控时间点之间的对应关系时，假设目标关键词为杨乐乐，则服务器可以基于目标关键词杨乐乐，从如下表1所示的关键词与监控时间点之间的对应关系中，获取杨乐乐对应的至少一个监控时间点为2015/02/03-21:08:31、2015/03/05-11:08:11、 2015/08/03-09:05:31，之后，服务器可以从监控视频中，获取2015/02/03-21:08:31、2015/03/05-11:08:11、2015/08/03-09:05:31分别对应的视频图像。
表1
关键词 监控时间点
杨乐乐 2015/02/03-21:08:31、2015/03/05-11:08:11、2015/08/03-09:05:31
郭杰 2015/05/13-21:10:02、2015/05/25-21:03:06、2015/08/11-19:18:26
…… ……
需要说明的是，在本公开实施例中，仅以上述表1所示的关键词与监控时间点之间的对应关系为例进行说明，上述表1并不对本公开实施例构成限定。
再例如，当索引库中存储关键词与视频图像之间的对应关系时，假设目标关键词为杨乐乐，服务器可以基于目标关键词杨乐乐，从如下表2所示关键词与视频图像之间的对应关系中，获取杨乐乐对应的至少一帧视频图像为1.JPEG、2.JPEG、3.JPEG。
表2
关键词 视频图像
杨乐乐 1.JPEG、2.JPEG、3.JPEG
郭杰 1.JPEG、2.JPEG、3.JPEG
…… ……
需要说明的是，在本公开实施例中，仅以上述表2所示的关键词与视频图像之间的对应关系为例进行说明，上述表2并不对本公开实施例构成限定。
其中，服务器将该至少一帧视频图像组成目标对象在监控视频中所处的视频段的过程可以参考相关技术，本发明实施例在此不进行详细阐述。
进一步地，服务器基于目标关键词和存储的索引库，获取目标对象在监控视频中的至少一帧视频图像之前，还可以通过如下步骤(1)-(4)来生成索引库，包括：
(1)服务器获取监控视频。
需要说明的是，服务器可以从智能摄像设备中获取该监控视频，当然，该智能摄像设备也可以将该监控视频发送到其它设备中，以使服务器可以从其它设备中获取该监控视频，本公开实施例对此不做具体限定。
其中，智能摄像设备配置为采集监控区域内的监控视频，且智能摄像设备采集监控区域内的监控视频的过程可以参考相关技术，本公开实施例在此不进行详细阐述。
另外，智能摄像设备可以通过有线网络或者无线网络和服务器或者其它设备进行通信，而当智能摄像设备通过无线网络和服务器或者其它设备进行通信时，智能摄像设备可以通过内置的无线保真(英文：WIreless-FIdelity，简称：WIFI)、蓝牙或者其它无线通信芯片来和服务器或者其它设备进行通信，本公开实施例对此不做具体限定。
(2)对于该监控视频中每帧视频图像，服务器基于指定分类模型，确定该视频图像包括的对象所属的对象类别。
需要说明的是，指定分类模型用于确定图像所对应的对象类别，且指定分类模型可以预先建立。
由于指定分类模型可以预先建立，且为了提高对象类别确定的效率，指定分类模型一般可以对预设尺寸的图像进行处理，以确定该图像包括的对象所属的对象类别，因此，服务器基于指定分类模型，确定该视频图像包括的对象所属的对象类别时，服务器可以在监控视频的视频图像中，对该对象所在的区域进行裁剪，得到对象图像，并将对象图像的尺寸处理为预设尺寸，之后，基于指定分类模型和处理后的对象图像，确定该对象所 属的对象类别。
其中，服务器在监控视频的视频图像中，对该对象所在的区域进行裁剪，得到对象图像时，可以从该对象所在的视频图像中，截取该对象的外接矩形，并将该外接矩形确定为该对象在监控视频中所处的图像区域，即对象图像。当然，服务器也可以以其它方式对该对象所在的区域进行裁剪，得到对象图像，本公开实施例对此不做具体限定。
另外，预设尺寸可以预先设置，如预设尺寸可以为224*224像素、300*300像素等等，本公开实施例对此不做具体限定。
需要说明的是，服务器基于指定分类模型和处理后的对象图像，确定该对象所属的对象类别的过程可以参考相关技术，本公开实施例在此不进行详细阐述。
(3)服务器基于该视频图像包括的对象所属的对象类别，确定该视频图像包括的对象所属的关键词。
由于该视频图像包括的对象所属的对象类别可能为人，也可能为宠物，还可能为其它物体，而当该视频图像包括的对象所属的对象类别为人或宠物时，终端需要获取具有特定身份的人或宠物在监控视频中所处的视频段，因此，服务器基于该视频图像包括的对象所属的对象类别，确定该视频图像包括的对象所属的关键词的操作可以为：当视频图像包括的对象所属的对象类别为人时，服务器对该对象进行人脸识别，得到人脸特征，之后，基于该人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识，并将该身份标识确定为该视频图像包括的对象所属的关键词。当视频图像包括的对象所属的对象类别为宠物时，服务器基于该视频图像，获取宠物标识，并基于该宠物标识，从存储的宠物标识与身份标识的对应关系中，获取对应的身份标识，并将该身份标识确定为该视频图像包括的对象所属的关键词。当视频图像包括的对象所属的对象类别不为 人，也不为宠物时，服务器可以直接将该对象类别确定为该视频图像包括的对象所属的关键词。
需要说明的是，服务器对该对象进行人脸识别，得到人脸特征的过程可以参考相关技术，本公开实施例在此不进行详细阐述。
还需要说明的是，宠物标识用于唯一标识该宠物，且该宠物标识可以通过置于该宠物上的二维码、条形码或者其他可识别标识获取得到，本公开实施例对此不做具体限定。
例如，当视频图像包括的对象所属的对象类别为人时，服务器对该对象进行人脸识别，得到人脸特征为A，之后，基于该人脸特征A，从如下表3所示的人脸特征与身份标识之间的对应关系中，获取A对应的身份标识为杨乐乐，则服务器可以将杨乐乐确定为该视频图像包括的对象所属的关键词。
表3
人脸特征 身份标识
A 杨乐乐
B 郭杰
…… ……
需要说明的是，在本公开实施例中，仅以上述表3所示的人脸特征与身份标识之间的对应关系为例进行说明，上述表3并不对本公开实施例构成限定。
再例如，当视频图像包括的对象所属的对象类别为宠物时，服务器基于该视频图像，扫描置于该宠物上的二维码、条形码或者其他可识别标识，获取宠物标识为ID1，之后，基于该宠物标识ID1，从如下表4所示的宠物标识与身份标识之间的对应关系中，获取ID1对应的身份标识为豆豆，则服务器可以将豆豆确定为该视频图像包括的对象所属的关键词。
表4
宠物标识 身份标识
ID1 豆豆
ID2 欢欢
…… ……
需要说明的是，在本公开实施例中，仅以上述表4所示的宠物标识与身份标识之间的对应关系为例进行说明，上述表4并不对本公开实施例构成限定。
进一步地，服务器基于该人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识之前，服务器可以接收终端发送的第一设置信息，该第一设置信息中携带该对象的身份标识以及该对象的人脸图像，服务器对该人脸图像进行特征提取，得到该对象的人脸特征，并将该人脸特征与该身份标识存储在人脸特征与身份标识之间的对应关系中。
例如，终端发送的第一设置信息中携带身份标识和人脸图像，且该身份标识为杨乐乐，服务器对该人脸图像进行特征提取，得到人脸特征为A，则服务器可以将A和杨乐乐存储在如表3所示的人脸特征与身份标识之间的对应关系中。
进一步地，服务器基于该宠物标识，从存储的宠物标识与身份标识之间的对应关系中，获取对应的身份标识之前，服务器可以接收终端发送的第二设置信息，该第二设置信息中携带该对象的身份标识以及该对象的宠物标识，服务器该宠物标识与该身份标识存储在宠物标识与身份标识之间的对应关系中。
例如，终端发送的第二设置信息中携带身份标识和宠物标识，且该身份标识为豆豆，宠物标识为ID1，则服务器可以将ID1和豆豆存储在如表4 所示的宠物标识与身份标识之间的对应关系中。
(4)服务器基于该关键词和该监控视频，生成索引库。
由于索引库中既可以存储关键词与监控时间点之间的对应关系，也可以存储关键词与视频图像之间的对应关系，因此，服务器基于该关键词和该监控视频，生成索引库的操作可以为：当索引库中存储关键词与监控时间点之间的对应关系时，服务器从该监控视频中，确定该视频图像所在的监控时间点，并将该关键词和该监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中。当索引库中存储关键词与视频图像之间的对应关系时，服务器将该关键词和该视频图像存储在索引库包括的关键词与视频图像之间的对应关系中。
由于监控视频中包括该监控视频中每帧视频图像对应的监控时间点，因此，当服务器确定了存在某个对象的视频图像时，可以基于该视频图像，从该视频图像所属的监控视频中获取该视频图像对应的监控时间点，之后，服务器可以将该对象所属的关键词和该监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中。
例如，该对象所属的关键词为杨乐乐，服务器从该监控视频中，确定存在杨乐乐的视频图像所在的监控时间点为2015/08/03-09:05:31，则服务器可以将杨乐乐和2015/08/03-09:05:31存储在如表1所示的关键词与监控时间点之间的对应关系中。
再例如，该对象所属的关键词为杨乐乐，该监控视频中存在杨乐乐的视频图像为3.JPEG，则服务器可以将杨乐乐和3.JPEG存储在如表2所示的关键词与视频图像之间的对应关系中。
第二种方式：当目标对象信息包括目标对象所在的目标图像时，服务器基于指定分类模型和目标图像，确定目标对象所属的目标类别，并基于目标类别，确定目标对象所属的目标关键词，进而基于目标关键词，确定 目标对象在监控视频中所处的视频段。
其中，服务器基于指定分类模型和目标图像，确定目标对象所属的目标类别时，服务器可以将目标图像的尺寸处理为预设尺寸，并基于指定分类模型和处理后的目标图像，确定该目标图像包括的目标对象所属的目标类别。
需要说明的是，服务器基于指定分类模型和处理后的目标图像，确定该目标对象所属目标类别的过程可以参考相关技术，本公开实施例在此不进行详细阐述。
需要说明的是，服务器基于目标类别，确定目标对象所属的目标关键词的过程与步骤302第一种方式中步骤(3)的确定过程类似，本公开实施例对此不再赘述。
还需要说明的是，服务器基于目标关键词，确定目标对象在监控视频中所处的视频段的过程与步骤302第一种方式的确定过程相同，本公开实施例对此不再赘述。
在步骤303中，服务器将目标对象在监控视频中所处的视频段发送给终端，使终端播放该视频段。
需要说明的是，终端播放该视频段时，不仅可以通过终端中设置的播放模块来播放，当然，终端还可以通过自身安装的播放应用程序来播放，本公开实施例对此不做具体限定。
在本公开实施例中，服务器获取监控视频，并基于指定分类模型确定该监控视频的视频图像中包括的对象所属的对象类别，进而基于该对象类别，确定该对象所属的关键词，并将该关键词和该关键词对应的监控时间点或者将该关键词和该关键词对应的视频图像存储在索引库中，之后，服务器在接收到播放请求时，基于该播放请求携带的目标对象信息，确定目标对象所属的目标关键词，并基于该目标关键词和存储的索引库，获取目 标对象在该监控视频中所处的至少一帧视频图像，并将该至少一帧视频图像组成目标对象在该监控视频中所处的视频段，进而将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。
图4是根据一示例性实施例示出的一种用于视频播放的装置的框图。参照图4，该装置包括接收模块401，确定模块402，发送模块403。
接收模块401，配置为接收播放请求，播放请求中携带信息，目标对象信息包括目标对象所在的目标图像或者目标对象所属的目标关键词；
确定模块402，配置为基于目标对象信息，确定目标对象在监控视频中所处的视频段；
发送模块403，配置为将视频段发送给终端，使终端播放视频段。
在本公开的另一实施例中，参照图5，该确定模块402包括：
第一确定单元4021，配置为当目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和目标图像，确定目标对象所属的目标类别；
第二确定单元4022，配置为基于目标类别，确定目标对象所属的目标关键词；
第三确定单元4023，配置为基于目标关键词，确定目标对象在监控视频中所处的视频段。
在本公开的另一实施例中，参照图6，该确定模块402包括第一获取单元4024，组成单元4025。
第一获取单元4024，配置为基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像；
组成单元4025，配置为将至少一帧视频图像组成目标对象在监控视频 中所处的视频段。
在本公开的另一实施例中，参照图7，该第一获取单元4024包括第一获取子单元40241，第二获取子单元40242。
第一获取子单元40241，配置为当索引库中存储关键词与监控时间点之间的对应关系时，基于目标对象信息对应的目标关键词，从关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
第二获取子单元40242，配置为基于至少一个监控时间点，从监控视频中，获取至少一帧视频图像。
在本公开的另一实施例中，该第一获取单元4024包括：
第三获取子单元，配置为当索引库中存储关键词与视频图像之间的对应关系时，基于目标对象信息对应的目标关键词，从关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
在本公开的另一实施例中，参照图8，该确定模块402还包括第二获取单元4026，第四确定单元4027，第五确定单元4028，生成单元4029。
第二获取单元4026，配置为接收智能摄像设备发送的监控视频；
第四确定单元4027，配置为对于监控视频中每帧视频图像，基于指定分类模型，确定视频图像包括的对象所属的对象类别；
第五确定单元4028，配置为基于对象类别，确定视频图像包括的对象所属的关键词；
生成单元4029，配置为基于关键词和监控视频，生成索引库。
在本公开的另一实施例中，参照图9，该第五确定单元4028包括识别子单元40281，第四获取子单元40282，第一确定子单元40283。
识别子单元40281，配置为当对象类别为人时，对视频图像包括的对象进行人脸识别，得到人脸特征；
第四获取子单元40282，配置为基于人脸特征，从存储的人脸特征与身 份标识之间的对应关系中，获取对应的身份标识；
第一确定子单元40283，配置为将身份标识确定为视频图像包括的对象所属的关键词。
在本公开的另一实施例中，参照图10，该生成单元4029包括第二确定子单元40291，第一存储子单元40292。
第二确定子单元40291，配置为从监控视频中，确定视频图像所在的监控时间点；
第一存储子单元40292，配置为将关键词和监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中。
在本公开的另一实施例中，该生成单元4029包括：
第二存储子单元，配置为将关键词和视频图像存储在索引库包括的关键词与视频图像之间的对应关系中。
在本公开实施例中，服务器接收播放请求，该播放请求中携带目标对象信息，服务器基于目标对象信息确定目标对象在监控视频中所处的视频段，并将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图11是根据一示例性实施例示出的一种用于视频播放的装置1100的框图。例如，装置1100可以被提供为一服务器。参照图11，装置1100包括处理组件1122，其进一步包括一个或多个处理器，以及由存储器1132所代表的存储器资源，配置为存储可由处理组件1122的执行的指令，例如应用程序。存储器1132中存储的应用程序可以包括一个或一个以上的每一个 对应于一组指令的模块。
装置1100还可以包括一个电源组件1126被配置为执行装置1100的电源管理，一个有线或无线网络接口1150被配置为将装置1100连接到网络，和一个输入输出(I/O)接口1158。装置1100可以操作基于存储在存储器1132的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM，LinuxTM，FreeBSDTM或类似。
此外，处理组件1122被配置为执行指令，以执行下述视频播放方法，所述方法包括：
接收播放请求，播放请求中携带目标对象信息，目标对象信息包括目标对象所在的目标图像或者目标对象所属的目标关键词。
基于目标对象信息，确定目标对象在监控视频中所处的视频段。
将目标对象在监控视频中所处的视频段发送给终端，使终端播放该视频段。
在本公开的另一实施例中，基于目标对象信息，确定目标对象在监控视频中所处的视频段，包括：
当目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和目标图像，确定目标对象所属的目标类别；
基于目标类别，确定目标对象所属的目标关键词；
基于目标关键词，确定目标对象在监控视频中所处的视频段。
在本公开的另一实施例中，基于目标对象信息，确定目标对象在监控视频中所处的视频段，包括：
基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像；
将至少一帧视频图像组成目标对象在监控视频中所处的视频段。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存 储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像，包括：
当索引库中存储关键词与监控时间点之间的对应关系时，基于目标对象信息对应的目标关键词，从关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
基于至少一个监控时间点，从监控视频中，获取至少一帧视频图像。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中所处的至少一帧视频图像，包括：
当索引库中存储关键词与视频图像之间的对应关系时，基于目标对象信息对应的目标关键词，从关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
在本公开的另一实施例中，基于目标对象信息对应的目标关键词和存储的索引库，获取目标对象在监控视频中的至少一帧视频图像之前，还包括：
获取监控视频；
对于监控视频中每帧视频图像，基于指定分类模型，确定视频图像包括的对象所属的对象类别；
基于对象类别，确定视频图像包括的对象所属的关键词；
基于关键词和监控视频，生成索引库。
在本公开的另一实施例中，基于对象类别，确定视频图像包括的对象所属的关键词，包括：
当对象类别为人时，对视频图像包括的对象进行人脸识别，得到人脸特征；
基于人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
将身份标识确定为视频图像包括的对象所属的关键词。
在本公开的另一实施例中，基于关键词和监控视频，生成索引库，包括：
从监控视频中，确定视频图像所在的监控时间点；
将关键词和监控时间点存储在索引库包括的关键词与监控时间点之间的对应关系中。
在本公开的另一实施例中，基于关键词和监控视频，生成索引库，包括：
将关键词和视频图像存储在索引库包括的关键词与视频图像之间的对应关系中。
在本公开实施例中，服务器接收播放请求，该播放请求中携带目标对象信息，服务器基于目标对象信息确定目标对象在监控视频中所处的视频段，并将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本发明的其它实施方案。本申请旨在涵盖本发明的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本公开实施例未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本发明的真正范围和精神由下面的权利要求指出。
应当理解的是，本发明并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本发明的范围仅由所附的权利要求来限制。
工业实用性
在本公开实施例中，服务器接收播放请求，该播放请求中携带目标对象信息，服务器基于目标对象信息确定目标对象在监控视频中所处的视频段，并将该视频段发送给终端，使终端可以直接播放该监控视频中存在目标对象的视频段，无需播放该监控视频中除该目标对象之外的其他对象所在的视频段，进而避免用户手动对该监控视频的播放进行调整来观看目标对象所处的视频，操作简单，且提高了视频播放效率。

Claims (19)

  1. 一种用于视频播放的方法，所述方法包括：
    接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；
    基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
    将所述视频段发送给终端，使所述终端播放所述视频段。
  2. 如权利要求1所述的方法，其中，所述基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段，包括：
    当所述目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和所述目标图像，确定所述目标对象所属的目标类别；
    基于所述目标类别，确定所述目标对象所属的目标关键词；
    基于所述目标关键词，确定所述目标对象在所述监控视频中所处的视频段。
  3. 如权利要求1所述的方法，其中，所述基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段，包括：
    基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像；
    将所述至少一帧视频图像组成所述目标对象在所述监控视频中所处的视频段。
  4. 如权利要求3所述的方法，其中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像，包括：
    当所述索引库中存储关键词与监控时间点之间的对应关系时，基于 所述目标对象信息对应的所述目标关键词，从所述关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
    基于所述至少一个监控时间点，从所述监控视频中，获取至少一帧视频图像。
  5. 如权利要求3所述的方法，其中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像，包括：
    当所述索引库中存储关键词与视频图像之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与视频图像之间的对应关系中，获取至少一帧频图像。
  6. 如权利要求3-5任一权利要求所述的方法，其中，所述基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中的至少一帧视频图像之前，还包括：
    获取监控视频；
    对于所述监控视频中每帧视频图像，基于指定分类模型，确定所述视频图像包括的对象所属的对象类别；
    基于所述对象类别，确定所述视频图像包括的对象所属的关键词；
    基于所述关键词和所述监控视频，生成所述索引库。
  7. 如权利要求6所述的方法，其中，所述基于所述对象类别，确定所述视频图像包括的对象所属的关键词，包括：
    当所述对象类别为人时，对所述视频图像包括的对象进行人脸识别，得到人脸特征；
    基于所述人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
    将所述身份标识确定为所述视频图像包括的对象所属的关键词。
  8. 如权利要求6所述的方法，其中，所述基于所述关键词和所述监控视频，生成所述索引库，包括：
    从所述监控视频中，确定所述视频图像所在的监控时间点；
    将所述关键词和所述监控时间点存储在所述索引库包括的关键词与监控时间点之间的对应关系中。
  9. 如权利要求6所述的方法，其中，所述基于所述关键词和所述监控视频，生成所述索引库，包括：
    将所述关键词和所述视频图像存储在所述索引库包括的关键词与视频图像之间的对应关系中。
  10. 一种用于视频播放的装置，所述装置包括：
    接收模块，配置为接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词；
    确定模块，配置为基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
    发送模块，配置为将所述视频段发送给终端，使所述终端播放所述视频段。
  11. 如权利要求10所述的装置，其中，所述确定模块包括：
    第一确定单元，配置为当所述目标对象信息包括目标对象所在的目标图像时，基于指定分类模型和所述目标图像，确定所述目标对象所属的目标类别；
    第二确定单元，配置为基于所述目标类别，确定所述目标对象所属的目标关键词；
    第三确定单元，配置为基于所述目标关键词，确定所述目标对象在所述监控视频中所处的视频段。
  12. 如权利要求10所述的装置，其中，所述确定模块包括：
    第一获取单元，配置为基于所述目标对象信息对应的所述目标关键词和存储的索引库，获取所述目标对象在所述监控视频中所处的至少一帧视频图像；
    组成单元，配置为将所述至少一帧视频图像组成所述目标对象在所述监控视频中所处的视频段。
  13. 如权利要求12所述的装置，其中，所述第一获取单元包括：
    第一获取子单元，配置为当所述索引库中存储关键词与监控时间点之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与监控时间点之间的对应关系中，获取至少一个监控时间点；
    第二获取子单元，配置为基于所述至少一个监控时间点，从所述监控视频中，获取至少一帧视频图像。
  14. 如权利要求12所述的装置，其中，所述第一获取单元包括：
    第三获取子单元，配置为当所述索引库中存储关键词与视频图像之间的对应关系时，基于所述目标对象信息对应的所述目标关键词，从所述关键词与视频图像之间的对应关系中，获取至少一帧视频图像。
  15. 如权利要求12-14任一权利要求所述的装置，其中，所述确定模块还包括：
    第二获取单元，配置为获取监控视频；
    第四确定单元，配置为对于所述监控视频中每帧视频图像，基于指定分类模型，确定所述视频图像包括的对象所属的对象类别；
    第五确定单元，配置为基于所述对象类别，确定所述视频图像包括的对象所属的关键词；
    生成单元，配置为基于所述关键词和所述监控视频，生成所述索引库。
  16. 如权利要求15所述的装置，其中，所述第五确定单元包括：
    识别子单元，配置为当所述对象类别为人时，对所述视频图像包括的对象进行人脸识别，得到人脸特征；
    第四获取子单元，配置为基于所述人脸特征，从存储的人脸特征与身份标识之间的对应关系中，获取对应的身份标识；
    第一确定子单元，配置为将所述身份标识确定为所述视频图像包括的对象所属的关键词。
  17. 如权利要求15所述的装置，其中，所述生成单元包括：
    第二确定子单元，配置为从所述监控视频中，确定所述视频图像所在的监控时间点；
    第一存储子单元，配置为将所述关键词和所述监控时间点存储在所述索引库包括的关键词与监控时间点之间的对应关系中。
  18. 如权利要求15所述的装置，其中，所述生成单元包括：
    第二存储子单元，配置为将所述关键词和所述视频图像存储在所述索引库包括的关键词与视频图像之间的对应关系中。
  19. 一种用于视频播放的装置，所述装置包括：
    处理器；
    配置为存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：
    接收播放请求，所述播放请求中携带目标对象信息，所述目标对象信息包括目标对象所在的目标图像或者所述目标对象所属的目标关键词所属的目标关键词；
    基于所述目标对象信息，确定所述目标对象在监控视频中所处的视频段；
    将所述视频段发送给终端，使所述终端播放所述视频段。
PCT/CN2015/099593 2015-10-28 2015-12-29 用于视频播放的方法及装置 Ceased WO2017071086A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
MX2016005835A MX363623B (es) 2015-10-28 2015-12-29 Metodo y dispositivo para reproducir videos.
RU2016118885A RU2016118885A (ru) 2015-10-28 2015-12-29 Способ и устройство для воспроизведения видео
KR1020167021969A KR101798011B1 (ko) 2015-10-28 2015-12-29 동영상 재생 방법 및 장치
JP2016549720A JP6419201B2 (ja) 2015-10-28 2015-12-29 ビデオ再生のための方法および装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510713118.3A CN105357475A (zh) 2015-10-28 2015-10-28 用于视频播放的方法及装置
CN201510713118.3 2015-10-28

Publications (1)

Publication Number Publication Date
WO2017071086A1 true WO2017071086A1 (zh) 2017-05-04

Family

ID=55333325

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/099593 Ceased WO2017071086A1 (zh) 2015-10-28 2015-12-29 用于视频播放的方法及装置

Country Status (8)

Country Link
US (1) US20170125060A1 (zh)
EP (1) EP3163473A1 (zh)
JP (1) JP6419201B2 (zh)
KR (1) KR101798011B1 (zh)
CN (1) CN105357475A (zh)
MX (1) MX363623B (zh)
RU (1) RU2016118885A (zh)
WO (1) WO2017071086A1 (zh)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105357475A (zh) * 2015-10-28 2016-02-24 小米科技有限责任公司 用于视频播放的方法及装置
CN106162106A (zh) * 2016-08-26 2016-11-23 浙江大华技术股份有限公司 一种视频监控系统中的数据存储方法及装置
CN106709424B (zh) * 2016-11-19 2022-11-11 广东中科人人智能科技有限公司 一种优化的监控视频存储系统
CN108540817B (zh) * 2018-05-08 2021-04-20 成都市喜爱科技有限公司 视频数据处理方法、装置、服务器及计算机可读存储介质
CN108600779B (zh) * 2018-05-18 2021-04-06 新华三信息技术有限公司 一种基于视频内容的目标对象操作方法及装置
CN109873951B (zh) * 2018-06-20 2021-07-13 成都市喜爱科技有限公司 一种视频拍摄及播放的方法、装置、设备及介质
US11627248B2 (en) 2019-02-03 2023-04-11 Chengdu Sioeye Technology Co., Ltd. Shooting method for shooting device, and electronic equipment
WO2020238789A1 (zh) * 2019-05-30 2020-12-03 杭州海康威视数字技术股份有限公司 视频回放
CN112019928B (zh) * 2019-05-30 2022-05-06 杭州海康威视数字技术股份有限公司 一种视频回放方法、装置及电子设备
CN110225282B (zh) * 2019-05-31 2023-05-30 山西仨仁行文化传媒有限公司 一种视频录制控制方法、设备及计算机可读存储介质
CN111190934A (zh) * 2019-12-30 2020-05-22 青岛海尔科技有限公司 数据的推送方法及装置、存储介质和电子装置
CN114095738A (zh) * 2020-07-30 2022-02-25 京东方科技集团股份有限公司 视频及直播处理方法、直播系统、电子设备、终端、介质
CN114598919B (zh) * 2022-03-01 2024-03-01 腾讯科技（深圳）有限公司 视频处理方法、装置、计算机设备和存储介质
US12489953B2 (en) 2023-01-27 2025-12-02 Adeia Guides Inc. Systems and methods for leveraging machine learning to enable user-specific real-time information services for identifiable objects within a video stream
US20240259639A1 (en) * 2023-01-27 2024-08-01 Adeia Guides Inc. Systems and methods for levaraging machine learning to enable user-specific real-time information services for identifiable objects within a video stream

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101299812A (zh) * 2008-06-25 2008-11-05 北京中星微电子有限公司 视频分析和存储方法、系统,及视频检索方法、系统
CN102129474A (zh) * 2011-04-20 2011-07-20 杭州华三通信技术有限公司 一种视频数据检索方法及其装置和系统
CN104754267A (zh) * 2015-03-18 2015-07-01 小米科技有限责任公司 视频片段标注方法、装置及终端
CN105357475A (zh) * 2015-10-28 2016-02-24 小米科技有限责任公司 用于视频播放的方法及装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1148722A4 (en) * 1999-11-15 2005-11-16 Matsushita Electric Industrial Co Ltd METHOD AND APPARATUS FOR VIDEO SEARCH
JP2003046989A (ja) * 2001-07-27 2003-02-14 Mitsubishi Electric Corp 映像監視装置および映像監視システム
JP2005354624A (ja) 2004-06-14 2005-12-22 Canon Inc 動画処理装置、動画処理方法およびコンピュータプログラム
US7760908B2 (en) * 2005-03-31 2010-07-20 Honeywell International Inc. Event packaged video sequence
TWI489394B (zh) * 2008-03-03 2015-06-21 Videoiq Inc 用於追蹤、索引及搜尋之物件匹配
WO2012047662A1 (en) 2010-09-27 2012-04-12 Hulu Llc Method and apparatus for providing user information to improve advertising experience
US8213689B2 (en) * 2008-07-14 2012-07-03 Google Inc. Method and system for automated annotation of persons in video content
CA2776909A1 (en) * 2009-10-07 2011-04-14 Telewatch Inc. Video analytics method and system
JP2012221322A (ja) * 2011-04-11 2012-11-12 Toshiba Corp オーサリング支援装置、オーサリング支援方法およびプログラム
JP2013092941A (ja) * 2011-10-26 2013-05-16 Nippon Telegr & Teleph Corp <Ntt> 画像検索装置、方法、及びプログラム
US9244923B2 (en) * 2012-08-03 2016-01-26 Fuji Xerox Co., Ltd. Hypervideo browsing using links generated based on user-specified content features
CN102867042A (zh) * 2012-09-03 2013-01-09 北京奇虎科技有限公司 多媒体文件搜索方法及装置
CN103916626A (zh) * 2013-01-05 2014-07-09 中兴通讯股份有限公司 一种监控录像信息提供方法、装置及视频监控系统
CN104239309A (zh) * 2013-06-08 2014-12-24 华为技术有限公司 视频分析检索服务端、系统及方法
JP6200306B2 (ja) * 2013-12-09 2017-09-20 株式会社日立製作所 映像検索装置、映像検索方法、および記憶媒体
CN103778204A (zh) * 2014-01-13 2014-05-07 北京奇虎科技有限公司 基于语音分析的视频搜索方法、设备及系统
CN104053048A (zh) * 2014-06-13 2014-09-17 无锡天脉聚源传媒科技有限公司 一种视频定位的方法及装置
CN104036018A (zh) * 2014-06-25 2014-09-10 百度在线网络技术（北京）有限公司 视频获取方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101299812A (zh) * 2008-06-25 2008-11-05 北京中星微电子有限公司 视频分析和存储方法、系统,及视频检索方法、系统
CN102129474A (zh) * 2011-04-20 2011-07-20 杭州华三通信技术有限公司 一种视频数据检索方法及其装置和系统
CN104754267A (zh) * 2015-03-18 2015-07-01 小米科技有限责任公司 视频片段标注方法、装置及终端
CN105357475A (zh) * 2015-10-28 2016-02-24 小米科技有限责任公司 用于视频播放的方法及装置

Also Published As

Publication number Publication date
MX2016005835A (es) 2017-07-20
MX363623B (es) 2019-03-28
US20170125060A1 (en) 2017-05-04
JP6419201B2 (ja) 2018-11-07
CN105357475A (zh) 2016-02-24
JP2018503148A (ja) 2018-02-01
KR101798011B1 (ko) 2017-11-15
RU2016118885A (ru) 2017-11-22
EP3163473A1 (en) 2017-05-03

Similar Documents

Publication Publication Date Title
WO2017071086A1 (zh) 用于视频播放的方法及装置
US11875467B2 (en) Processing method for combining a real-world environment with virtual information according to a video frame difference value to provide an augmented reality scene, terminal device, system, and computer storage medium
US11286310B2 (en) Methods and apparatus for false positive minimization in facial recognition applications
TWI582710B (zh) The method of recognizing the object of moving image and the interactive film establishment method of automatically intercepting target image
WO2016054989A1 (zh) 建立拍照模板数据库、提供拍照推荐信息的方法及装置
US11010596B2 (en) Apparatus and methods for facial recognition systems to identify proximity-based connections
CN108234879B (zh) 一种获取滑动变焦视频的方法和装置
WO2017167060A1 (zh) 一种信息展示方法、装置及系统
TW201941078A (zh) 機器於迴路、圖像至視訊之電腦視覺自助抽樣
WO2014012488A1 (zh) 增强现实的实现方法和装置
US11636710B2 (en) Methods and apparatus for reducing false positives in facial recognition
CN104754234B (zh) 一种拍照方法及装置
US20160182816A1 (en) Preventing photographs of unintended subjects
US20210182536A1 (en) Mediating apparatus and method, and computer-readable recording medium thereof
CN105979363A (zh) 一种身份识别法和装置
CN115053269A (zh) 用于在用户设备上进行面部识别的方法和装置
WO2017166472A1 (zh) 广告数据匹配方法、装置及系统
US9706102B1 (en) Enhanced images associated with display devices
CN105072348B (zh) 一种快速对焦人脸的方法、装置及终端
WO2018133354A1 (zh) 一种信息获取方法及获取设备
CN109960969B (zh) 移动路线生成的方法、装置及系统
WO2015192615A1 (zh) 一种图像文件共享方法、装置和计算机存储介质
CN113591656A (zh) 图像处理方法、系统、装置、设备及计算机存储介质
CN107733874B (zh) 信息处理方法、装置、计算机设备和存储介质
Mukherjee et al. Energy efficient face recognition in mobile-fog environment

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: MX/A/2016/005835

Country of ref document: MX

ENP Entry into the national phase

Ref document number: 2016118885

Country of ref document: RU

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2016549720

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20167021969

Country of ref document: KR

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15907147

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15907147

Country of ref document: EP

Kind code of ref document: A1