[go: up one dir, main page]

WO2021244123A1 - Système et procédé de création de support intelligent en temps réel - Google Patents

Système et procédé de création de support intelligent en temps réel Download PDF

Info

Publication number
WO2021244123A1
WO2021244123A1 PCT/CN2021/085110 CN2021085110W WO2021244123A1 WO 2021244123 A1 WO2021244123 A1 WO 2021244123A1 CN 2021085110 W CN2021085110 W CN 2021085110W WO 2021244123 A1 WO2021244123 A1 WO 2021244123A1
Authority
WO
WIPO (PCT)
Prior art keywords
preview frame
camera preview
camera
interest
overlay
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/CN2021/085110
Other languages
English (en)
Inventor
Anvesh NEELI
Kaushal Prakash SHARMA
Nitin SETIA
Anand CHANDRAVANSHI
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.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
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 Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Publication of WO2021244123A1 publication Critical patent/WO2021244123A1/fr
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
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
    • H04N23/632—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image

Definitions

  • the present invention generally relates to the field of image analysis, and more particularly, to systems and methods for creating real-time intelligent media.
  • a user wants to only capture a small area of a scene, the user is required to capture the entire area first.
  • a typical example of such an issue occurs while live streaming of a cricket match, where the user may want to focus on the ball hitting the wickets in a shot while having the view of the entire match. In order to do this, the user must first capture the entire view of the match and then create a secondary stream on the focused area around the ball and the wickets.
  • the secondary video stores all the plurality of interesting and notable moments of the main video arranged in chronological order.
  • an object of the present invention to provide a system and method of creating real-time intelligent media. It is another object of the invention to implement a single camera solution for capturing a scene when an emphasis on a particular focus. It is also an object of the invention to overcome the need to stop and start recording to capture multiple views of a scene. It is yet another object of the invention to avoid the need of zooming to highlight some parts of the camera preview frame. It is also an object of the present invention to provide better object coverage with intelligent solution to focus on one object.
  • One another object of the present invention is to provide automatic capturing of a media with the desired area of interest in a zoomed view while keeping the same field of view.
  • the present disclosure provides a method and system of creating real-time intelligent media.
  • One aspect of the present invention relates to a method of creating a real-time intelligent media.
  • the said method comprising: receiving, at least one camera preview frame to record a media. Thereafter, a preview resolution of said camera preview frame is divided into at least two blocks.
  • the method then comprises identifying at least one object and an area of interest of said camera preview frame by performing an image analysis, and subsequently, creating an overlay for the camera preview frame, said overlay being based on the identified area of interest and at least one object.
  • the said overlay for the camera preview frame facilitates creation of the real-time intelligent media.
  • the system comprises a camera unit, a processing unit and a display unit.
  • the camera unit is configured to receive at least one camera preview frame.
  • the processing unit connected to said camera unit, is configured to divide the preview resolution of camera preview frame into at least two blocks and identify at least one object and an area of interest of said camera preview frame using image analysis.
  • the processing unit is then configured to create an overlay for the camera preview frame.
  • the invention encompasses that the overlay is based on the identified area of interest and at least one object, wherein said overlay for the camera preview frame facilitates creation of the real-time intelligent media.
  • FIG. 1 illustrates a block diagram of a system [100] for creating real-time intelligent media, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 2 illustrates a block diagram [200] of a camera unit [102] , in accordance with exemplary embodiments of the present disclosure.
  • FIG. 3 illustrates an exemplary method flow diagram [300] , for creating real-time intelligent media, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 4 illustrates an exemplary method of implementation of present invention [400] , for creating real-time intelligent media, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 5 illustrates an exemplary user interface diagram [500] , depicting a gaming event to create a real-time intelligent media of the event, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 6 illustrates an exemplary user interface diagram [600] , depicting a conference event to create a real-time intelligent media of the event, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 7 illustrates an exemplary user interface diagram [700] , depicting a gaming event to create a real-time intelligent media of the event, in accordance with exemplary embodiments of the present disclosure.
  • FIG. 8 illustrates an exemplary user interface diagram [800] , depicting a wildlife scenario to create a real-time intelligent media of the scene, in accordance with exemplary embodiments of the present disclosure.
  • circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail.
  • well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.
  • the present disclosure provides an efficient solution to alleviate problems existing in the prior art and develop a method and system of capturing of real-time intelligent media.
  • the present invention provides a method and system of creating real-time intelligent media.
  • the invention commences when at least one camera preview frame to record a media is received from a user.
  • the invention encompasses that the said camera preview frame is associated with an aspect ratio and a field of view.
  • a preview resolution of said camera preview frame is divided into at least two blocks.
  • at least one object and a point or area of interest in the preview frame is identified.
  • an input may be taken from the user to identify the at least one object and a point or area of interest in the preview frame.
  • image analysis of a camera preview frame may be performed to identify the at least one object and point or area of interest in the preview frame.
  • An overlay is then created comprising of the best suited block of the camera preview frame comprising of the identified at least one object and point or area of interest.
  • the camera preview frame is encoded in the aspect ratio wherein the camera preview frame comprises of the overlay created to create a real-time intelligent encoded media having the same field of view.
  • the media generated by the present invention is such that it has the same aspect ratio and field of view of the created media is as of the original preview frame thus preserving the quality and field of view of the media which is otherwise distorted or degraded, or uses post-processing and a second video stream in the prior art solutions.
  • the invention also encompasses detection or identification of point or area of interest dynamically so as to capture changing area of interests as well as multiple areas of interests while recording.
  • a media includes an image, video, graphics, animation or any other form of media that may be obvious to a person skilled in the art.
  • the “camera preview frame” refers to at least one real-time preview of a scene picked up/previewed by the camera sensor unit. Further, the real-time preview of the scene comprises the preview of at least one real-time imaging parameter.
  • the camera preview frame may refer to the preview generated by a camera unit [102] and can be seen on the display unit [106] of a user device when the user opens a camera application.
  • the “imaging parameters” comprises one or more parameters of a scene, an exposure, a face area, an ISO value etc.
  • image analysis refers to determination of one or more imaging parameters and/or identification of at least one face, area of interest, point of interest, object of interest, etc.
  • aspects ratio refers to the ratio of the width to the height of the camera preview frame/image/video.
  • field of view refers to the open observable area/scene the user can see through the camera unit in the camera preview frame.
  • a “processing unit” or “processor” includes one or more processors, wherein processor refers to any logic circuitry for processing instructions.
  • a processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc.
  • the processor may perform signal coding data processing, input/output processing, and/or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor or processing unit is a hardware processor.
  • a “display unit [106] ” or “display” includes one or more computing device for displaying camera preview frame and media generated in accordance with the present invention.
  • the display unit [106] may be an additional hardware coupled to the said electronic device or may be integrated with in the electronic device.
  • the display unit [106] may further include but not limited to CRT display, LED display, ELD display, PDP display, LCD display, OLED display and the like.
  • a user device may be any electrical, electronic, electromechanical and computing device or equipment.
  • the user device may include, but is not limited to, a mobile phone, smart phone, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, wearable device or any other computing device in which a camera can be implemented.
  • the user device contains at least one input means configured to receive an input from the user, a processor and a display unit configured to display at least the camera preview frame, media, etc. to the user.
  • the system [100] comprises, at least one camera unit [102] , at least one processing unit [104] , at least one display unit [106] . All of these components/units are connected to each other, however, the same has not been shown in Fig. 1 for the sake of clarity.
  • the system [100] is configured to provide at least one real-time intelligent media with the help of the said interconnection between the camera unit [102] , the processing unit [104] and the display unit [106] .
  • the invention encompasses that the system [100] may be incorporated into a user device, or any electronic device.
  • the camera unit [102] is configured to receive at least one camera preview frame, said camera preview frame being associated with an aspect ratio and field of view. Further, the camera preview frame comprises real-time data with respect to the current scene in the surrounding environment. The camera preview frame changes in accordance with the movement in the camera unit [102] . A media may then be created from this real-time data/scene of the camera preview frame.
  • the components and functions of the camera unit [102] is further discussed below in reference to Fig. 2.
  • the processing unit [104] is configured to divide the preview resolution of camera preview frame into at least two blocks and to perform an image analysis of the camera preview frame in order to identify at least one object and an area of interest, wherein said image analysis includes identification of at least one of a face in real-time, area of interest, object, real-time imaging parameters and the like associated with the said camera preview frame.
  • the calculation of area/point of interest may be based at least on artificial intelligence, machine learning, scene detection, voice direction, detection of area of interest and the like parameters.
  • the area/point of interest may be identified based on an input received from the user.
  • the invention encompasses that the at least one object and area/point of interest may be determined based on the scene of the camera preview frame.
  • the scene of the camera preview frame may be detected using scene detection mechanism.
  • the scene detected may be at least one of a game, conference, party, birthday, wedding concert, stage, wildlife, beach and the like.
  • the point of interest and object may be identified based on the detected scene.
  • the area of interest may include for example, the bat in a cricket match, wedding dress and wedding couple in a marriage scene, dice and mike detection in a conference or award function and decision of location, stage and performer detection (both music and dance) and the like.
  • the invention encompasses that the encoding further comprises adjusting the preview resolution of the camera preview frame to the highest possible resolution with respect to the camera unit [102] . Further, the adjusted the preview resolution of the camera preview frame divided into blocks to perform the image analysis on the preview frame, wherein the said image analysis is done to find at least one object and area of interest and said division in blocks is such that each small box has same aspect ratio as full preview frame/camera preview frame.
  • processing unit [104] is configured to identify a buffer of blocks of the camera preview frame.
  • the identified blocks are best suited blocks comprising of the identified at least object and area of interest.
  • the best suited blocks are then compressed to a minimum recording resolution.
  • the processing unit [104] is also configured to create an overlay for the camera preview frame.
  • the overlay comprises at least one of a, point of interest, identified object and the like imaging parameters with a zoomed view of the at least one of a, point of interest, identified object.
  • the invention encompasses that the overlay comprises of the identified best suited blocks.
  • the processing unit [104] is also configured to encode, at least one real-time intelligent media from the camera preview frame, wherein the encoding is in accordance with created overlay.
  • the processing unit [104] is configured encode the camera preview frame in real-time in accordance with the overlay created, aspect ratio and field of view.
  • the encoding of the camera preview frame in real-time comprises of dynamically superimposing, merging or incorporating the overlay in the real-time media with the same field of view.
  • the invention encompasses that the at least one object and point of interest can be changed during recording of media and multiple point of interests can be encoded dynamically in accordance with the invention.
  • the display unit [106] is configured to display the encoded real-time intelligent media created from the camera preview frame comprising of the overlay created based on at least one of a, point of interest and identified object in a zoomed view, keeping the same field of view.
  • the display unit [106] is configured to display the intelligent media encoded by the processing unit [104] comprising of the overlay.
  • the said display unit [106] may be an additional hardware coupled to the said electronic/user device or may be integrated with in the user/electronic device.
  • the display unit [106] may further include but not limited to CRT display, LED display, ELD display, PDP display, LCD display, OLED display and the like.
  • the system [100] as shown in Fig. 1 may reside in the electronic device/user device.
  • the invention also encompasses that the processing unit [104] of the system [100] resides at a remote server, while the camera unit [102] and the display unit [106] resides in the user device, such that the camera preview frame is captured by the camera unit [102] at the user device and sent to the processing unit [104] at the remote server for processing.
  • FIG. 2 illustrates a block diagram of camera unit [102] , in accordance with exemplary embodiments of the present invention.
  • the said camera unit [102] comprises, at least one camera sensor unit [102a] , at least one camera driver [102b] , at least one camera HAL [102c] , at least one camera framework [102d] at least one camera preview frame unit [102e] .
  • the camera sensor unit [102a] is configured to preview/pick up the scene surrounding the camera unit [102] as raw real-time data.
  • the camera driver [102b] is configured to collect the raw real-time data from the said camera sensor unit [102a] and provide the same to the camera HAL [102c] .
  • the camera HAL [102c] is configured to process the said collected real-time data and provide the same to the camera preview frame unit [102e] .
  • the camera preview frame unit [102e] configured to provide a graphical user interface to the user to provide a preview of the camera preview frame.
  • the invention encompasses that the camera preview frame unit [102e] is configured to display the camera preview frame on the display unit [106] of the system [100] of an electronic/user device.
  • the camera preview frame unit [102e] is further configured to display at least one real-time encoded intelligent media comprising of an overlay in the camera preview frame having the same field of view.
  • the camera sensor unit [102e] also comprises at least one light sensitive processing unit configured to measure and process the imaging parameters of the camera preview frame.
  • the camera framework [102d] is configured to, provide a module to interact with the said camera sensor unit [102a] , said camera driver [102b] , said camera HAL [102c] and the said camera preview frame unit [102e] .
  • the said camera framework [102d] is further configured to store files for input data, processing and the guiding mechanism.
  • FIG. 3 illustrates an exemplary method flow diagram [300] depicting method for creating real-time intelligent media, in accordance with exemplary embodiments of the present disclosure.
  • the invention encompasses that the method begins at step 302 when an at least one camera preview frame to capture a media is received.
  • the camera preview frame being associated with an aspect ratio and a field of view.
  • the camera preview frame may be received when an input is received from the user to open a camera application and select the intelligent recording mode using an input means. For instance, the user may open a camera application on the user interface of the user device. Thereafter, the user may select the intelligent recording mode by clicking on a soft button of an icon on the camera preview frame.
  • Such selection of intelligent recording mode may occur during the capturing/recording of a media, such as an image, or when the user is about to start the capturing/recording.
  • an indication of the selected intelligent recording mode is displayed to the user on the camera preview frame. For instance, an icon ‘auto-record’ may be shown over the camera preview frame after the user opens the camera application.
  • the invention encompasses that the camera preview frame may be received at the processing unit [104] from the camera unit [102] .
  • the camera preview frame provides the at least one preview of a scene displayed by the camera sensor unit [102a] .
  • the camera preview frame comprises of the preview generated by the camera sensor unit [102a] and displayed on the display unit [106] when the camera application is opened.
  • the preview resolution of said camera preview frame is divided into at least two blocks.
  • the said division of preview resolution into blocks is achieved such that the aspect ratio of each small block is same as the aspect ratio of camera preview frame.
  • the camera preview frame may be divided into 4 or 16 blocks. Each block represents a small view that is required to be analysed by the processing unit [104] .
  • image analysis of said camera preview frame is performed to identify at least one object and an area of interest.
  • the invention encompasses that the image analysis of the camera preview frame comprises identifying at least one object and area of interest.
  • At least one object and area of interest is identified using artificial intelligence.
  • the invention encompasses that the identification of at least one object and area of interest is based on the scene in the camera preview frame.
  • the speaker on the stage may be identified as the object and the podium may be identified as the area of interest when the scene in the camera preview frame is of a conference.
  • the batsman and the wickets may be identified as the object of interest and the area of interest when the scene in the camera preview frame is of a cricket match.
  • the lion eating the prey may be identified as the objects of interest when the scene is of a hunt in the jungle.
  • the at least one object and area of interest is identified based on an input recieved from the user.
  • the invention encompasses that the user input on the at least one object and area of interest is given priority over identification using artificial intelligence.
  • the user input of identifying the area of interest and object may be detected when the user attempts to zoom the scene on the camera preview frame to focus on a particular area or object.
  • At step 308 at least one overlay for the camera preview frame is created.
  • the overlay comprises of at least one of identified object and area of interest.
  • the overlay is created by zooming in at least one of identified object and area of interest of the camera preview frame in real-time, wherein the said zooming is achieved with respect to the identified, area of interest, object and/or the other associated parameters of the camera preview frame.
  • the invention encompasses that the overlay comprises of a block of camera preview frame, wherein the block of camera preview frame comprises the best suited block compressed to the minimum recording resolution.
  • the best suited block of camera preview frame is the portion of the camera preview frame comprising at least one of an identified, area of interest, object and the other related parameter of camera preview frame.
  • the camera preview frame is encoded.
  • the camera preview frame is encoded in said aspect ratio.
  • the invention encompasses that the encoded camera preview frame comprises of superimposing, merging or incorporating the overlay created in the same position of the identified at least one object and area of interest.
  • the invention also encompasses that the field of view and the aspect ratio of the camera preview frame remains the same in the encoded real-time media.
  • the encoded intelligent media is displayed at the display unit [106] .
  • the encoded intelligent comprises of the same field of view of the media camera preview frame with the superimposed overlay comprising of a zoomed view of at least one object and area of interest in the same location as the at least one object and area of interest in the camera preview frame.
  • the invention also encompasses storing the encoded real-time intelligent media in a memory at the user device.
  • FIG. 4 refers to an exemplary method of implementation of present invention [400] , for creating real-time intelligent media, in accordance with exemplary embodiments of the present disclosure.
  • a camera preview frame is received, wherein the said camera preview frame is associated with a real-time preview of a scene previewed/picked up by the camera sensor unit [102a] .
  • the said real-time preview of a scene comprises the preview of at least one real-time imaging parameter, area of interest, object and the associated parameters of camera preview frame.
  • camera preview frame may refer to the preview generated by a camera and can be seen on the display unit [106] of a user device when the user opens a camera application.
  • step 404 the capturing/recording of the media is started.
  • a preview resolution is received related to said camera preview frame and the preview resolution is adjusted/set to the maximum possible resolution.
  • the invention encompasses that the preview resolution is divided into NxN blocks, wherein N may be one of, 1, 2, 3, 4........ or so on.
  • the division of the preview resolution is such that each block has the same aspect ratio and field of view as that of the camera preview frame/overall field of view.
  • image analysis is performed on the preview frame, wherein image analysis includes identification of at least one of, face in real-time, area of interest, object, real-time imaging parameters associated with the said camera preview frame and the like associated parameters.
  • image analysis includes identification of at least one of, face in real-time, area of interest, object, real-time imaging parameters associated with the said camera preview frame and the like associated parameters.
  • the invention encompasses that the image analysis is performed to identify at least one object and area of interest.
  • the at least one object and area of interest may be identified when an input is received from the user using an input means. For example, when recording a cricket match, the user may manually focus the batsman as the area of interest and other related parameters without zooming manually and operating it to record the object when object is in frame.
  • the at least one object and area of interest may be identified automatically using algorithms for machine learning, artificial intelligence, scene detection, voice direction, detection of area of interest and the like parameters.
  • the area of interest may be for example, a batsman in a cricket match, wedding dress and wedding couple, dice and mike detection and decision of location, stage and performer detection (both music and dance) and the like.
  • the said user intervention is taken into consideration on priority over the said automatic identification.
  • the invention encompasses that the at least one object and area of interest may be based on the scene in the camera preview frame.
  • scene detection may comprise detection of at least one of the scene in the camera preview frame such as party, birthday, wedding concert, stage, wildlife, beach and the like.
  • At step 410, at least one overlay is created.
  • the overlay comprises of at least one of identified object and area of interest.
  • the overlay is created by zooming in at least one of identified object and area of interest of the camera preview frame in real-time, wherein the said zooming is achieved with respect to the identified, area of interest, object and/or the other associated parameters of the camera preview frame.
  • the invention encompasses that the overlay comprises of a block of camera preview frame, wherein the block of camera preview frame comprises the best suited block compressed to the minimum recording resolution.
  • the best suited block of camera preview frame is the portion of the camera preview frame comprising at least one of an identified, area of interest, object and the other related parameter of camera preview frame.
  • the final encoded video with overlay is received.
  • the invention encompasses that the real-time intelligent media is encoded with a resolution calculated from area of interest, objects and other parameters in same aspect ratio as that of the camera preview frame.
  • the invention encompasses that the resolution of the camera preview frame is adjusted to the maximum before encoding the media based on said blocks.
  • the encoded media comprises of superimposing/merging of an overlay created with the overall field of view in the place the at least one of the area of interest, object and other imaging parameters related to said camera preview frame.
  • the aspect ratio of each small divided block is similar to the aspect ratio of overall field of view/camera preview frame.
  • an exemplary user interface diagram [500] depicting a game event to create a real-time media of a catch of a ball in a cricket match, in accordance with exemplary embodiments of the present disclosure is shown.
  • the video of the given scene of a cricket match is generated by implementing the present invention.
  • the given exemplary user interface diagram [500] comprises a camera preview frame/overall field of view [502] of the said cricket match, point of interest [504] and encoded said camera preview frame [506] with the overlay [508] .
  • the invention encompasses that the point of interest [504] may be determined using artificial intelligence. Thereafter, the image analysis of the said camera preview frame [502] , is done by first dividing the camera preview frame [502] into small blocks, wherein the said division is achieved considering the point of interest [504] in focus. In this instance, the best suited blocks comprising point of interest and object [504] , i.e. the player crossing the boundary, is identified in accordance with the invention and such best-suited blocks are further used to create an overlay [508] to be superimposed to the real-time image using said single frame.
  • the camera preview frame [502] may be divided into 16 small blocks and thereafter the 6 best suited small blocks comprising point of interest object of interest [504] are further considered to encode the real-time video.
  • the aspect ratio of said small blocks are same as the aspect ratio of full preview of camera preview frame [502] , thus preserving the video quality.
  • the said best suited small blocks are compressed to minimum recording resolution prior to encoding the video in accordance with the single frame of said best suited blocks.
  • the generated final real-time image comprising of an overlay [508] superimposed on the encoded block of said camera preview frame with the same field of view is shown by [506] .
  • FIG. 6 an exemplary user interface diagram [600] , depicting a conference event to create a real-time media of the scene, in accordance with exemplary embodiments of the present disclosure is shown.
  • the media is generated of a conference event by implementing the present invention.
  • the user interface comprises a camera preview frame/overall field of view [602] of the said conference event, point of interest [604] and encoded block of said camera preview frame [606] comprising of the overlay [608] .
  • the camera preview frame/overall field of view [602] is divided into 16 small blocks, in accordance with the invention.
  • the division of camera preview frame [602] is achieved to further assist the image analysis of said camera preview frame [602] , wherein the image analysis is being done as per the point/area of interest [604] .
  • the area of interest in this instance i.e. the person delivering the speech, is identified in accordance with the invention.
  • a single point of interest [604] is shown in the given example, there can be the multiple point of interests [604] and other relevant parameters like specific object/objects or imaging parameters can be taken into consideration.
  • the best suited blocks comprising point of interest [604] are further used as a single frame to encode the real-time video using said single frame.
  • the aspect ratio of the single frame comprising the best-suited blocks is same as that of the preview of camera preview frame [602] .
  • the said camera preview frame [602] is further encoded by superimposing an overlay [608] with a zoomed view of the point of interest [604] , as the speaker, with respect to the single frame of best suited blocks as shown in [606] .
  • the given exemplary user interface diagram [600] indicates a generated final real-time media comprising of encoded block of said camera preview frame [606] comprising of the overlay [608] based on the point of interest [604] having the same field of view.
  • FIG. 7 illustrates an exemplary user interface diagram [700] , depicting a gaming event to create a real-time media of the scene, in accordance with exemplary embodiments of the present disclosure.
  • a media such as an image
  • the exemplary user interface diagram [700] comprises a camera preview frame/overall field of view [702] of the said gaming event, point of interest [704] and encoded block of said camera preview frame [706] comprising of overlay [708] .
  • the camera preview frame [702] indicates overall field view of a gaming event with a specific point of interest [704] .
  • the camera preview frame may be divided into 16 small blocks to further perform the image analysis on said blocks.
  • the division of the camera preview frame [702] may be achieved by diving the said camera preview frame [702] in various combination of different small blocks, wherein the order of said division is NxN.
  • the value of N varies from 1, 2, 3, 4isingso on, considering possible number of small portions/blocks.
  • the division is done in a manner such that the aspect ratio of each said small block should be same as the aspect ratio of preview of said camera preview frame [702] .
  • the point of interest [704] is a player trying to touch another player comprising the said player/point of interest [704] in focus.
  • the user interface at [706] indicates that the said camera preview frame [702] having the same aspect ratio as that of the preview of the camera preview frame [702] , comprises of an overlay [708] wherein the overlay [708] comprises of maybe four small blocks which are the suitable small blocks comprising point of interest [704] , to encode the real-time image with respect to point of interest frames.
  • the four small divided blocks comprising the point of interest [704] have been considered to create an overlay [708] that is superimposed/merged with the camera preview frame having the overall field of view as shown in [706] .
  • the user interface indicates an encoded block of said camera preview frame [706] , wherein the said encoded block of said camera preview frame [706] comprises a zoomed view of the said point of interest [704] i.e. player trying to touch another player in the given user interface as an overlay [708] . Therefore, the real-time media is generated by considering point of interest/player trying to touch another player [704] in focus in the overlay [708] and the said generated image is in same aspect ratio as that of the overall field of view of the original preview [702] .
  • an exemplary user interface diagram [800] depicting a wildlife scenario to create a real-time media of the depicted scene, in accordance with exemplary embodiments of the present disclosure is shown.
  • a video of a wildlife scenario may be generated by implementing the present invention.
  • the exemplary user interface diagram [800] comprises a camera preview frame/overall field of view [802] of the said wildlife scenario, point of interest [804] and encoded block of said camera preview frame [806] comprising of an overlay [808] .
  • the camera preview frame [802] indicates overall field view of a wildlife scene with a specific point of interest [804] .
  • the point of interest [804] is a lion hunting a deer and in order to record a video comprising the said lion/point of interest [804] in focus.
  • the point of interest [804] is difficult to focus while recording a real-time video, therefore in order to record the said real-time video comprising point of interest [804] in focus, said video may be captured using the present invention.
  • the camera preview frame [802] comprising point of interest [804] may being divided into 16 small blocks. Thereafter, image analysis may be performed on the said small blocks with respect to the point of interest [804] .
  • the said small blocks are compressed to a minimum recording resolution and further used as a single frame to encode a real time video, wherein the said single frame comprises small blocks having area of interest in focus (i.e. suitable small blocks) and aspect ratio same as the aspect ratio of preview of camera preview frame [802] .
  • the best suited blocks collectively as a single frame, comprising point of interest [804] are used to create an overlay [808] .
  • the overlay [808] is then superimposed/merged in the encoded the real-time video comprising of the overall field of view. Therefore, in the given user interface, the real-time video is generated by considering point of interest [804] in focus in the overlay [808] and the said generated video is in same aspect ratio and field of view as that of the camera preview frame [802] .
  • the units, interfaces, modules, and/or components depicted in the figures and described herein may be present in the form of a hardware, a software and a combination thereof. Connection/sshown between these units/components/modules/interfaces in the exemplary system architecture may interact with each other through various wired links, wireless links, logical links and/or physical links. Further, the units/components/modules/interfaces may be connected in other possible ways.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Studio Devices (AREA)

Abstract

Les modes de réalisation de la présente divulgation concernent des procédés et des systèmes de création de support intelligent en temps réel. L'invention comprend la réception d'au moins un cadre de prévisualisation de caméra pour enregistrer une vidéo, ledit cadre de prévisualisation de caméra étant associé à un rapport d'aspect et à un champ de vision. Par la suite, l'invention comprend en outre la division de la résolution de prévisualisation dudit cadre de prévisualisation de caméra en au moins deux blocs et la réalisation d'une analyse d'image sur ledit cadre de prévisualisation de caméra afin d'identifier au moins un objet et une zone d'intérêt. En outre, la présente invention comprend la création d'une superposition pour le cadre de prévisualisation de caméra sur la base de la zone d'intérêt identifiée et d'au moins un objet. Ensuite, bloc du cadre de prévisualisation de caméra est codé dans ledit rapport d'aspect, ledit bloc de cadre de prévisualisation de caméra comprenant la superposition, afin de créer le support intelligent en temps réel dudit bloc de cadre de prévisualisation de caméra comprenant le même champ de vision.
PCT/CN2021/085110 2020-06-05 2021-04-01 Système et procédé de création de support intelligent en temps réel Ceased WO2021244123A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN202041023583 2020-06-05
IN202041023583 2020-06-05

Publications (1)

Publication Number Publication Date
WO2021244123A1 true WO2021244123A1 (fr) 2021-12-09

Family

ID=78830105

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/085110 Ceased WO2021244123A1 (fr) 2020-06-05 2021-04-01 Système et procédé de création de support intelligent en temps réel

Country Status (1)

Country Link
WO (1) WO2021244123A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104796594A (zh) * 2014-01-16 2015-07-22 中兴通讯股份有限公司 一种预览界面特殊效果即时呈现方法及终端设备
WO2018070598A1 (fr) * 2016-10-14 2018-04-19 한국전력공사 Dispositif de surveillance d'activité illégale à l'aide d'une évaluation d'influence de changement d'un code source et procédé associé
CN109218695A (zh) * 2017-06-30 2019-01-15 中国电信股份有限公司 视频图像增强方法、装置、分析系统及存储介质
CN109886108A (zh) * 2019-01-17 2019-06-14 上海大学 一种表单任意区域字符识别与信息录入方法
CN110400626A (zh) * 2019-07-08 2019-11-01 上海联影智能医疗科技有限公司 图像检测方法、装置、计算机设备和存储介质
CN110740689A (zh) * 2017-03-28 2020-01-31 三星麦迪森株式会社 超声诊断装置及其操作方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104796594A (zh) * 2014-01-16 2015-07-22 中兴通讯股份有限公司 一种预览界面特殊效果即时呈现方法及终端设备
WO2018070598A1 (fr) * 2016-10-14 2018-04-19 한국전력공사 Dispositif de surveillance d'activité illégale à l'aide d'une évaluation d'influence de changement d'un code source et procédé associé
CN110740689A (zh) * 2017-03-28 2020-01-31 三星麦迪森株式会社 超声诊断装置及其操作方法
CN109218695A (zh) * 2017-06-30 2019-01-15 中国电信股份有限公司 视频图像增强方法、装置、分析系统及存储介质
CN109886108A (zh) * 2019-01-17 2019-06-14 上海大学 一种表单任意区域字符识别与信息录入方法
CN110400626A (zh) * 2019-07-08 2019-11-01 上海联影智能医疗科技有限公司 图像检测方法、装置、计算机设备和存储介质

Similar Documents

Publication Publication Date Title
JP4539048B2 (ja) 動画像表示システム及びプログラム
US11748870B2 (en) Video quality measurement for virtual cameras in volumetric immersive media
CN107105315A (zh) 直播方法、主播客户端的直播方法、主播客户端及设备
JP2019160318A (ja) 情報処理装置、情報処理方法、及びプログラム
US11438510B2 (en) System and method for editing video contents automatically technical field
CN108989830A (zh) 一种直播方法、装置、电子设备及存储介质
JP2018107793A (ja) 仮想視点画像の生成装置、生成方法及びプログラム
JP2019047431A (ja) 画像処理装置及びその制御方法、画像処理システム
CN101261680A (zh) 图像处理设备、图像处理方法及程序
GB2562488A (en) An apparatus, a method and a computer program for video coding and decoding
WO2023286367A1 (fr) Dispositif de traitement d'informations, procédé de traitement d'informations et programme
US10250803B2 (en) Video generating system and method thereof
CN112183431A (zh) 实时行人数量统计方法、装置、相机和服务器
CN112887620A (zh) 视频拍摄方法、装置及电子设备
WO2021244123A1 (fr) Système et procédé de création de support intelligent en temps réel
JP2015126518A (ja) 撮像装置、画像処理装置、画像処理方法、プログラム
US20240137588A1 (en) Methods and systems for utilizing live embedded tracking data within a live sports video stream
CN112367465A (zh) 图像输出方法、装置及电子设备
CN114520890B (zh) 图像处理方法及装置
CN111415397A (zh) 一种人脸重构、直播方法、装置、设备及存储介质
CN118842928A (zh) 一种多模态视频导播方法及多模态视频导播系统
CN114882422A (zh) 一种视频检测方法、装置、电子设备及存储介质
KR20190122053A (ko) 객체 영상 트랙킹 스트리밍 시스템 및 이를 이용한 스트리밍 방법
CN114092706A (zh) 一种体育全景足球录像方法、系统、存储介质及终端设备
WO2021073336A1 (fr) Système et procédé de création d'une vidéo en temps réel

Legal Events

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

Ref document number: 21817479

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: 21817479

Country of ref document: EP

Kind code of ref document: A1