WO2018095252A1 - 视频录制方法及装置 - Google Patents

视频录制方法及装置 Download PDF

Info

Publication number
WO2018095252A1
WO2018095252A1 PCT/CN2017/111075 CN2017111075W WO2018095252A1 WO 2018095252 A1 WO2018095252 A1 WO 2018095252A1 CN 2017111075 W CN2017111075 W CN 2017111075W WO 2018095252 A1 WO2018095252 A1 WO 2018095252A1
Authority
WO
WIPO (PCT)
Prior art keywords
frame
video
size
frame image
facial feature
Prior art date
Application number
PCT/CN2017/111075
Other languages
English (en)
French (fr)
Inventor
张雅新
李瑞春
曾骁
李明杰
潘柏宇
谢菲
Original Assignee
优酷网络技术（北京）有限公司
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 优酷网络技术（北京）有限公司 filed Critical 优酷网络技术（北京）有限公司
Publication of WO2018095252A1 publication Critical patent/WO2018095252A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships

Definitions

  • the present disclosure relates to the field of image processing, and in particular, to a video recording method and apparatus.
  • the frame selection position of the screen frame is fixed and can only be recorded within a fixed range.
  • the video content that is, the frame selection position and size of the recording screen frame is fixed.
  • the recorded video content may not always be desired by the user, and the user experience is poor.
  • the present disclosure proposes a video recording method and apparatus by applying facial feature recognition technology to a screen recording technology.
  • the position and size of the recording frame can be flexibly set, thereby recording the video desired by the user and improving the user experience.
  • a video recording method including: performing facial feature recognition on a frame-by-frame basis for each frame image of the played video; and determining a recording screen in the frame images according to the facial feature recognition result. Position and size of the frame; and recording the video according to the position and size of the screen frame in the image of each frame.
  • determining the position and size of the video frame in the frame image according to the facial feature recognition result including: determining, according to the facial feature recognition result, Position and initial size of the screen frame in each frame image; selecting one of the determined initial sizes as the reference size; and adjusting the initial size of the screen frame in the frame image to The reference size.
  • the reference size is preset according to the resolution of each frame image of the video.
  • determining the position and size of the video frame in the frame image according to the facial feature recognition result including: first time from the video of the frame image In the case where the facial features of the plurality of objects are identified, at least one of the plurality of objects is selected as the object of interest; in the subsequent frame image of the one-frame image, frame-by-frame determination is made with the target object
  • the similarity of the facial features of each object is respectively a matching facial feature of the corresponding object below a predetermined similarity threshold; and respectively determined according to the facial features of the respective objects in the focused object and the matching facial features of the corresponding objects, respectively The position and size of the screen frame in the one frame image and the subsequent frame image.
  • the video recording method includes: in the subsequent frame image, if there is a frame image that does not have the matching facial feature, respectively, according to each object in the attention object
  • the facial features and the matching facial features of the respective objects determine the position and size of the video frame in the frame image from the one frame image to the frame image without the matching facial features.
  • determining, in the frame image and the subsequent frame, according to a facial feature of each object in the object of interest and a matching facial feature of each corresponding object, respectively Position and size of the screen frame in the image comprising: determining, in the one frame image and the subsequent frame image, according to facial features of each object in the object of interest and matching facial features of each corresponding object, respectively Position and initial size of the screen frame; selecting one of the determined initial sizes as the reference size; and adjusting the initial size in the one frame image and the subsequent frame image to the reference size.
  • the reference size is preset according to the resolution of each frame image of the video.
  • recording the video according to the position and size of the screen frame in the image of each frame includes: loading a preset expression into the Screen box; And recording the video according to the loaded expression and the position and size of the screen frame in the frame images.
  • the facial feature recognition is performed frame by frame on each frame image of the played video, including: performing key region positions of the face in each frame image of the played video. Positioning, wherein the key area location includes at least one of an eyebrow, an eye, a nose, a mouth, an ear, and an area in which the contour of the face is located.
  • a video recording apparatus comprising: a facial feature recognizing unit for performing facial feature recognition on a frame-by-frame basis for each frame image of the played video; a determining unit, and the facial feature recognition a unit connection, configured to determine a position and a size of a screen frame in the frame image according to the facial feature recognition result; and a screen recording unit connected to the determining unit for being used according to the frame image The position and size of the screen frame to record the video.
  • the determining unit includes: a first determining module, configured to determine a position and an initial position of a screen frame in each frame image according to the facial feature recognition result a first selection module, coupled to the first determining module, configured to select one of the determined initial sizes as a reference size; and an adjustment module coupled to the first selection module for The initial size of the screen frame in each of the frame images is adjusted to the reference size.
  • the reference size is preset according to the resolution of each frame image of the video.
  • the determining unit includes: a second selecting module, configured to, when identifying facial features of the plurality of objects from a frame image of the video for the first time Selecting at least one object from the plurality of objects as the object of interest; a second determining module, coupled to the second selecting module, for determining the frame-by-frame and the frame in the subsequent frame image of the one-frame image a matching facial feature of a corresponding object whose similarity of facial features of each object in the object of interest is below a predetermined similarity threshold; and a third determining module connected to the second determining module for respectively following the attention A face feature of each object in the object and a matching face feature of each corresponding object determine a position and a size of the screen frame in the one frame image and the subsequent frame image.
  • the third determining module is further configured to: in the subsequent frame image, if there is a frame image that does not have the matching facial feature, respectively Determining a face feature of each object in the object of interest and a matching face feature of each corresponding object to determine a position of the screen frame in the frame image between the one frame image and the frame image not having the matching face feature And size.
  • the third determining module is configured to: determine, according to a facial feature of each object in the object of interest and a matching facial feature of each corresponding object, respectively Determining a position and an initial size of the screen frame in the frame image and the subsequent frame image; selecting one of the determined initial sizes as the reference size; and placing the image in the frame and the subsequent The initial size in the frame image is adjusted to the reference size.
  • the reference size is preset according to the resolution of each frame image of the video.
  • the recording unit includes: a loading module, configured to load a preset expression into the recording frame; and a recording module, and the loading The module is connected to record the video according to the loaded expression and the position and size of the screen frame in the frame images.
  • the facial feature recognition unit is configured to: locate a key area position of a face in each frame image of the played video, where the key area position At least one of the areas where the eyebrows, eyes, nose, mouth, ears, and facial contours are located.
  • the position and size of the recording frame can be flexibly set, thereby recording the video desired by the user, and improving the user.
  • the facial feature recognition technology to the screen recording technology
  • FIG. 1 illustrates a flow chart of a video recording method according to an embodiment of the present disclosure
  • Figure 2 shows a schematic view of a face that detects a front side
  • Figure 3 shows a schematic view of the detection of a side face
  • FIG. 4 is a schematic view showing the size of a screen frame for determining a face of a front side
  • Figure 5 is a schematic view showing the size of a screen frame for determining a side face
  • FIG. 6 is a flowchart showing a video recording method of another embodiment of the present disclosure.
  • FIG. 7 is a flowchart showing a video recording method of still another embodiment of the present disclosure.
  • FIG. 8 is a schematic diagram showing face tracking recognition and tracking recorded video according to an embodiment of the present disclosure.
  • FIG. 9 is a block diagram showing the structure of a video recording apparatus according to an embodiment of the present disclosure.
  • FIG. 10 illustrates a structural block diagram of a video recording apparatus according to another embodiment of the present disclosure.
  • FIG. 11 is a block diagram showing the structure of a video recording apparatus according to an exemplary embodiment.
  • FIG. 1 illustrates a flow chart of a video recording method in accordance with an embodiment of the present disclosure. As shown in FIG. 1, the method may include the following steps:
  • Step S100 Perform facial feature recognition on a frame-by-frame basis for each frame image of the played video.
  • Step S110 determining a position and a size of a screen frame in each frame image according to the facial feature recognition result
  • Step S120 Record the video according to the position and size of the screen frame in each frame image.
  • the video to be recorded is played in the video player, and then, for example, the screen recording software button is clicked, thereby popping up the screen setting box, and clicking a specific button (for example, a face recording button) in the setting box.
  • the played video may be an online video obtained from the Internet, or may be a local video that has been stored in a local storage, such as a hard disk.
  • face feature recognition may be performed frame by frame to detect whether there is a face (face) in each frame image. And in the case where there is a face, the specific position of the face in the frame image and the outline size of the face are further determined.
  • a key area position of a face in each frame image of the played video may be located, and each key area position is feature-recognized to obtain a facial feature of the face.
  • the key area location includes at least one of an eyebrow, an eye, a nose, a mouth, an ear, and an area in which the facial contour is located, and the facial feature may include a position of the face in the frame image and a contour size thereof.
  • the position of the key region is not limited to the examples listed above, and may be any portion that can reflect the features of the face.
  • detected The resulting face can be either front (as shown in Figure 2) or side (as shown in Figure 3) and can support some degree of occlusion and multi-angle detection.
  • a frame of images there may be faces of multiple objects (eg, people). If there are a plurality of faces, the key region positions of the respective faces are respectively identified to obtain facial features of the respective faces.
  • the information can be stored in the memory as a facial feature recognition result.
  • the screen frame at the time of recording the frame image may be determined according to the obtained facial feature result. Location and size.
  • the position and size of the recording frame can be determined according to the facial feature.
  • the screen frame can at least frame the entire face (as shown in FIGS. 4 and 5).
  • the position and size of the screen frame are determined according to the facial features of the plurality of faces.
  • the screen frame can at least select an area of all of the plurality of faces.
  • the screen frame may be temporarily disappeared, that is, the frame image is not recorded, and then detected again in the subsequent frame image.
  • you reach the face make the recording frame appear and determine its position and size.
  • step S120 when determining the position and size of the screen frame when the frame image is to be recorded in step S110, for example, the start video recording button may be clicked to determine the position of the screen frame according to the determined position. The size is recorded for this video. Thereby, a video clip including facial expressions of various faces is produced.
  • the recorded video can be automatically saved to a common mp4 format and saved to, for example, a folder on the local hard disk.
  • the position and size of the screen frame in each frame image can be determined by identifying the facial features of each frame image in the video and according to the facial feature recognition result, and then according to the Record the video by determining the position and size of the recording frame.
  • the position and size of the screen frame can be flexibly set, thereby recording the video desired by the user and improving the user experience.
  • the size of the screen frame for each frame image may also be different.
  • the size of each frame image obtained is different.
  • the video is recorded by adjusting the size of the screen frame of each frame image to the same size.
  • FIG. 6 shows a flow chart of a video recording method of another embodiment of the present disclosure.
  • the steps in FIG. 6 having the same reference numerals as in FIG. 1 have the same functions, and a detailed description of these steps will be omitted for the sake of brevity.
  • step S110 may include the following steps:
  • Step S210 determining a position and an initial size of the screen frame in each frame image according to the facial feature recognition result
  • Step S220 selecting one of the determined initial sizes as the reference size
  • Step S230 adjusting the initial size in one frame image and subsequent frame image to the reference size.
  • the position of the recording frame for each frame image and the initial size of the recording frame may be first determined according to the facial feature recognition result. Among them, these initial sizes may differ due to the recognized facial feature recognition results. Then, from among the determined initial sizes, one of the appropriate sizes is selected as the reference size, and then the frame of the frame in each frame image is The dimensions are adjusted to the reference size.
  • the reference size is preset according to a resolution of each frame image of the video. And, if the determined initial size is larger than the reference size, for example, the frame image may be scaled down so that the video frame having the reference size can be framed into the frame image when the video is recorded. Facial area.
  • the reference dimension is the largest of the determined initial dimensions.
  • the reference size is not limited thereto, and may be any suitable size as long as the resolution of the frame image recorded by the size can satisfy the resolution of the user's viewing.
  • step S120 video recording is performed using the position of the screen frame of each frame image determined previously and the size of the adjusted screen frame.
  • the size of the frame image recorded for each frame image is uniform, and thus it is possible to solve the problem that the video image when the frame images are spliced is discontinuous and unnatural.
  • each frame image may be first recorded according to the facial feature recognition result identified in step S100, and then the other frame images may be based on the size of the frame image of the appropriate size (for example, the maximum size) recorded.
  • the dimensions are all adjusted to the appropriate size.
  • a method for adjusting the size of other frame images to the appropriate size may be to fill a background or the like at the edges of these other frame images. After the size of the other frame images is changed to an appropriate size by filling the background, the frame images are spliced, which also solves the problem that the video images when the frame images are spliced are discontinuous and unnatural.
  • the facial feature recognition technology can be applied to the screen recording technology, thereby being able to flexibly set the position and size of the screen frame, thereby recording the video desired by the user, and improving the user.
  • the embodiment can adjust the size of the screen frame determined based on the facial feature recognition technology, thereby making the video image discontinuous and unnatural when the video image is spliced.
  • the user may only want to record for the face of one or more of the objects, that is, when recording the video, only the face of the one object or the plurality of objects is recorded, thereby implementing the one. Recording and tracking of objects or facial expressions of the plurality of objects.
  • FIG. 7 shows a flow chart of a video recording method of still another embodiment of the present disclosure.
  • the same steps in FIG. 7 as those in FIG. 1 have the same functions, and a detailed description of these steps will be omitted for the sake of brevity.
  • step S110 may include the following steps:
  • Step S310 in a case where the facial features of the plurality of objects are first recognized from one frame of the video, at least one of the plurality of objects is selected as the object of interest;
  • Step S320 determining a matching facial feature of the corresponding object whose similarity of the facial features of each object in the object of interest is below a predetermined similarity threshold, respectively, in a subsequent frame image of the one frame image;
  • Step S330 determining the position and size of the screen frame in the one-frame image and the subsequent frame image according to the facial features of the objects in the object of interest and the matching facial features of the respective objects, respectively.
  • step S310 when facial feature recognition is performed on each frame image frame by frame, if a face of a plurality of objects is recognized in a certain frame image, the user may be selected from the plurality of objects.
  • One object is the object of interest, and the facial features of the object of interest are stored in the memory.
  • step S330 the position and size of the screen frame of the frame image can be determined based on the facial features of the object of interest.
  • the attention object is used as the screen focus object, thereby tracking a series of facial expression changes of the object of interest.
  • the facial features of the subsequent frame images of the frame image are next identified, and whether the object of interest exists in the subsequent frame images is determined. For example, in a subsequent image, multiple objects are identified, and then the facial features of the multiple objects are respectively The set facial features of the subject of interest are compared to determine the similarity of these facial features to the facial features of the subject of interest.
  • the difference between the feature value of the facial feature of an object and the feature value of the facial feature of the previously set object of interest is small, that is, the similarity between them is less than a preset similarity threshold (in other words, The high similarity of the objects indicates that the object is the object that the user wants to track, that is, the object is the object of interest in the frame image.
  • the facial features of the object are referred to as matching facial features.
  • the frame image may not be recorded.
  • step S320 The processing of the above step S320 is sequentially performed on all subsequent frame images in the video.
  • step S330 the position and size of the screen frame of the corresponding frame image are determined based on the face feature (matching face feature) of the object of interest.
  • the user when the user first recognizes that a certain frame image has faces of a plurality of objects, the user can also select two or more objects as the attention objects from them to record and track each object in the attention object, respectively.
  • the object 1 and the object 2 among the plurality of objects are selected as the attention object 1 and the attention object 2.
  • the facial features of the object of interest 1 and the object of interest 2 are stored in the memory.
  • the position and size of the screen frame for the attention object 1 and the attention object 2 in the frame image can be respectively determined based on the facial features of the attention object 1 and the attention object 2.
  • the attention object 1 and the attention object 2 are respectively used as the screen focus objects, thereby tracking a series of facial expression changes of the attention object 1 and the attention object 2.
  • the facial features of the subsequent frame images of the frame image are next identified, and whether the object of interest 1 and the object of interest 2 are present in the subsequent frame images are determined. For example, in a subsequent image, a plurality of objects are identified, and then facial features of the plurality of objects are respectively compared with previously set facial features of the attention object 1 and the attention object 2 to determine the facial features and the facial features, respectively. The similarity of the facial features of the object 1 and the object of interest 2 is concerned.
  • the similarity between them is smaller than a preset similarity threshold (in other words, this
  • the high similarity of the two objects indicates that the object is the object that the user wants to track, that is, the object is the object of interest 1 in the frame image.
  • the similarity between them is less than the preset similarity threshold (in other words)
  • the similarity between the two objects is high, indicating that the object is the object that the user wants to track, that is, the object is the object of interest 2 in the frame image.
  • the facial feature of the certain object is referred to as a matching facial feature.
  • the frame image may not be recorded.
  • step S320 The processing of the above step S320 is sequentially performed on all subsequent frame images in the video.
  • step S330 for each of the object of interest 1 and the object of interest 2 in the subsequent frame image, the position and size of the screen frame in the subsequent frame image are determined according to their matching face features, respectively.
  • the position and size of the screen frame can be determined for each object separately, and then each object is recorded separately to record and track the facial expression changes of each object.
  • the plurality of object frames can be selected into a recording frame to record and track the plurality of objects as a whole, so as to reflect the scene corresponding to the facial expression.
  • the object can be selected as the object of interest when the user sees the object of interest.
  • the similarity between the facial features of the plurality of faces and the facial features of the attention object are smaller than a preset similarity threshold. For example, the front and side of the same person.
  • an object corresponding to a face having a higher degree of similarity may be selected as the object of interest, for example, a person corresponding to the front face is selected as the object of interest.
  • the subsequent frame image may not be characterized, but according to the The facial features of the object of interest are used to determine the position and size of the screen frame of these frame images.
  • the object of interest is determined in the image of the first frame, and then the subsequent image of the second frame, the image of the third frame, ... are sequentially identified, and when it is found, for example, in the image of the 20th frame, it does not exist.
  • the feature of the first frame image to the 19th frame image is determined by using only the face features of the object of interest in the first frame image to the 19th frame image.
  • the position and size of the screen frame, and the first frame image to the 19th frame image are respectively recorded according to the determined position and size of the screen frame, and the subsequent frame images are not recorded. In this way, it is possible to record only a frame image in a continuous video, thereby obtaining a continuous change in facial expression.
  • the user can stop recording of the video at any frame image according to his or her own needs.
  • a face recording stop button is set in the player, and the face recording can be stopped after the user presses the face recording stop button.
  • the above steps S210-S230 can also be applied to solve the problem of discontinuity and unnaturalness of the video image after video recording.
  • the foregoing step S330 may specifically include the following steps: determining the position of the screen frame in the one frame image and the subsequent frame image according to the facial features of the objects in the object of interest and the matching facial features of the respective objects, respectively. And an initial size; selecting one of the determined initial sizes as the reference size; and adjusting the initial size in the one frame image and the subsequent frame image to the reference size.
  • the face recognized in the video it is also possible to perform an interesting editing operation on the face recognized in the video. For example, in the case where a face of a plurality of objects is detected, if a user does not want to see a face in the video, the face may be tastefully decorated, such as wearing a mask on the face or adding an expression to the face, etc. After that, for example, you can click the save button to save the added expression.
  • the added expression can be applied to all the frame images of the video, and can also be applied to the frame image to which the user desires to apply.
  • the foregoing step S120 may include the following steps: loading a preset expression into the recording frame; and according to the loaded expression and the image in each frame Record the video by the position and size of the recording frame in it.
  • a preset expression may be loaded in all frame images of the video in which the face is recognized, or a preset expression may be loaded in the partial frame image.
  • the preset expressions loaded may be the same or different for each frame image.
  • the fun of video recording can be increased by loading a preset expression during video recording.
  • the facial feature recognition technology can be applied to the screen recording technology, thereby being able to flexibly set the position and size of the screen frame, thereby recording the video desired by the user, and improving the user.
  • the embodiment can adjust the size of the screen frame determined based on the facial feature recognition technology, thereby making the video image discontinuous and unnatural when the video image is spliced.
  • this Embodiments may determine the position and size of the screen frame of each frame image by setting the object of interest in a certain frame image and causing the object of interest to be tracked in the subsequent frame image, and then determining the frame of the frame of each frame image according to the facial features of the object of interest. It is possible to record and track the objects of interest that are of interest to the user.
  • the embodiment can load a preset expression during the video recording process, thereby increasing the interest of the video recording.
  • This embodiment shows a specific application scenario of the present disclosure and corresponding actual operational steps and devices.
  • the screen frame will be selected by default to the face position recognized in the video. If more than two faces appear on the video screen, the screen frame will only select one face by default, and the user can also record according to the user.
  • the face is adjusted to move the screen frame to the face to be recorded, and the screen frame is repositioned according to the feedback data of the face key point (position of the key area of the face inside the video);
  • the screen frame will be tracked and recorded along with the face and side of the face.
  • the video recording ends.
  • the user can finish the recording process in advance;
  • the system will automatically save the recorded video to the common mp4 format and save it to a local folder.
  • the user needs to play the recorded video, he can view it in the local folder.
  • the user can also perform a certain degree of interesting editing and the like.
  • the face (face) recognized in the video can be fun edited, etc. If there is a face in the video that the user does not want to see, the face can be tastefully decorated, such as wearing a face. Add a mask to the face or add an expression to the face. After the addition is complete, click the “Save” button to save the expression.
  • the expression added at this time can be applied to the entire episode video. As long as the face appears in the video, it will bring a mask or an expression. This can reduce the user's plan for the character, and reduce the need for fast forward, increasing the interest of the user when watching the video.
  • the face tracking device can include:
  • a relationship establishing module configured to establish, according to facial feature information of each face (face) in the video sequence frame (each frame image in the video), the feature value of the different face and the ID value of the person corresponding to the face Correspondence between the two to make these feature values are compared in the feature comparator;
  • a search module configured to find a facial feature of a face having the lowest gap value with the focus object of the screen according to the comparison of the feature comparator
  • a storage module for storing the output (identified) facial features
  • a face tracking module for tracking a face with the lowest gap between the video sequence frame and the screen focus object
  • an identification module configured to take a face with the smallest gap value as a focus object of the recording screen when two or more faces appear simultaneously in the video;
  • the screen recording device can include:
  • a monitoring module for monitoring the signal triggered by the screen and the signal sent by the face tracking device to start recording
  • a data storage module for storing the recorded video frame data.
  • FIG. 8 is a schematic diagram showing face tracking recognition and tracking recorded video according to an embodiment of the present disclosure, and the specific process is described in detail below.
  • a face (face) key point detecting method is employed to determine whether a face exists based on a person's facial features. Position the key areas of the face inside the video, including eyebrows, eyes, nose, mouth, facial contours, and more. This detection method supports a certain degree of occlusion and multi-angle faces. By using the face key point detection technology, it is possible to accurately position the face (the front side of the face as shown in FIG. 2 and the side of the face as shown in FIG. 3) (corresponding to "face key point detection” in FIG. 8) ).
  • the plurality of faces appearing in the video picture are memorized by the position information, and the feature values of each face are used to acquire the desired feature values.
  • the face tracking process it is necessary to compare the feature value of the currently detected face with the corresponding feature value of the face previously stored as the screen focus object in the feature comparator to view the gap value. If the currently detected face is compared with the previously stored face similarity less than the preset gap value (similarity threshold) (ie, the similarity is high), the face is determined as the face to be tracked. If two or more faces appear on the video screen and the previously stored face similarity is less than the preset gap value, the face with the smallest similarity difference value is determined as the face to be tracked. And, the key point feature of the face is saved (corresponding to "face comparator", “face feature extraction”, “face recognition”, and “storage” in FIG.
  • an identification module for identifying a facial expression of the video frame and generating a recognition result
  • a sending module configured to send a loading map of the expression effect
  • a loading module for loading a loading map of an expression effect in, for example, each video frame
  • a display module configured to display an emoticon in a face of each video frame during video playback
  • one of the preset expression packs may be selected, and the face in the video frame is matched and recognized, the recognition result is generated, and the loading position of the expression to be loaded in the instant video frame is determined.
  • the parameter points of the face features in each video frame are combined with the expressions. Then, at the time of video recording, each video frame loaded with an expression is recorded. In this way, it is possible to increase the interest of the user when watching the video.
  • the video recording method and the corresponding device can be applied to the screen recording technology by using the facial feature recognition technology, thereby being able to flexibly set the position and size of the screen frame, thereby recording the video desired by the user.
  • the embodiment can set the screen focus object (the object of interest) in a certain frame image, and track the screen focus object in the subsequent frame image, and then determine each according to the facial features of the screen focus object.
  • the position and size of the screen frame of the frame image thereby enabling recording and tracking of the object of interest of interest to the user.
  • the embodiment can load a preset expression during the video recording process, thereby increasing the interest of the video recording.
  • FIG. 9 is a block diagram showing the structure of a video recording apparatus according to an embodiment of the present disclosure.
  • the video recording device 90 may include a facial feature recognition unit 91 for performing a face-by-frame on each frame image of the played video.
  • a feature recognition unit 92 is connected to the facial feature recognition unit 91 for determining a position and a size of a screen frame in each frame image according to the facial feature recognition result; and a screen recording unit 93,
  • the determining unit 92 is connected to record the video according to the position and size of the screen frame in the frame images.
  • the determining unit 92 includes: a first determining module 921, configured to determine a position and an initial size of the screen frame in the frame image according to the facial feature recognition result; a selection module 922, coupled to the first determining module 921, for selecting one of the determined initial sizes as a reference size; and an adjustment module 923 coupled to the first selection module 922 for The initial size of the screen frame in each of the frame images is adjusted to the reference size.
  • the reference size is preset according to a resolution of each frame image of the video.
  • the recording unit 93 may include: a loading module 931 for loading a preset expression into the recording frame; and a recording module 932, and the loading module 931 A connection for recording the video according to the loaded emoticon and the position and size of the video frame in the frame images.
  • the facial feature recognition unit 91 is specifically configured to: locate a key region position of a face in each frame image of the played video, where the key region location includes an eyebrow and an eye At least one of the areas where the nose, mouth, ears, and facial contours are located.
  • the video recording apparatus of the embodiment of the present disclosure may be used to implement the video recording method described in any of the foregoing embodiments of FIG. 1, FIG. 6, and FIG.
  • the specific flow of the video recording method described in FIG. 1, FIG. 6, and FIG. 7 above is detailed in the above-described FIG. 1, FIG. 6, and FIG.
  • the video recording apparatus can apply the facial feature recognition technology to the screen recording technology, thereby being able to flexibly set the position and size of the recording screen frame, thereby recording the video desired by the user, and improving the user.
  • the embodiment can adjust the size of the screen frame determined based on the facial feature recognition technology, thereby making the video image discontinuous and unnatural when the video image is spliced.
  • the embodiment can load a preset expression during the video recording process, thereby increasing the interest of the video recording.
  • FIG. 10 shows a structural block diagram of a video recording apparatus according to another embodiment of the present disclosure.
  • the components in FIG. 10 having the same reference numerals as those in FIG. 9 have the same functions, and a detailed description of these components will be omitted for the sake of brevity.
  • the determining unit 92 may further include: a second selecting module 1001, for In a case where a facial feature of a plurality of objects is recognized in one frame of the video, at least one object is selected as the object of interest from the plurality of objects; and the second determining module 1002 is connected to the second selection module 1001.
  • a matching facial feature of a corresponding object whose similarity to a facial feature of each of the objects of interest is below a predetermined similarity threshold, respectively, is determined frame by frame in a subsequent frame image of the one frame of image; and
  • the third determining module 1003 is connected to the second determining module 1002, and is configured to determine, according to the facial features of the objects in the object of interest and the matching facial features of the corresponding objects, respectively, the image and the image in the frame. The position and size of the screen frame in the subsequent frame image.
  • the third determining module 1003 is further configured to: in the subsequent frame image, if there is a frame image that does not have the matching facial feature, respectively, according to the The facial features of each object and the matching facial features of the respective objects determine the position and size of the video frame in the frame image from the one frame image to the frame image without the matching facial features.
  • the third determining module 1003 may be specifically configured to: determine, according to a facial feature of each object in the object of interest and a matching facial feature of each corresponding object, respectively, in the one a frame image and a position and an initial size of the screen frame in the subsequent frame image; selecting one of the determined initial sizes as a reference size; and the image in the one frame and the subsequent frame The initial size in the adjustment is adjusted to the reference size.
  • the reference size is preset according to a resolution of each frame image of the video.
  • the video recording apparatus of the embodiment of the present disclosure may be used to implement the video recording method described in any of the foregoing embodiments of FIG. 1, FIG. 6, and FIG.
  • the specific flow of the video recording method described in FIG. 1, FIG. 6, and FIG. 7 above is detailed in the above-described FIG. 1, FIG. 6, and FIG.
  • the video recording apparatus can apply the facial feature recognition technology to the screen recording technology, thereby being able to flexibly set the position and size of the recording screen frame, thereby recording the video desired by the user, and improving the user.
  • the embodiment can adjust the size of the screen frame determined based on the facial feature recognition technology, thereby making the video image discontinuous and unnatural when the video image is spliced.
  • the embodiment may set the object of interest in a certain frame image, and cause the object of interest to be tracked in the subsequent frame image, and then determine the position and size of the screen frame of each frame image according to the facial features of the object of interest. Thereby, it is possible to record and track the object of interest that is of interest to the user.
  • the embodiment can load a preset expression during the video recording process, thereby increasing the interest of the video recording.
  • FIG. 11 is a block diagram showing the structure of a video recording apparatus according to an exemplary embodiment.
  • the device 800 is configured to perform the video recording method described in the foregoing embodiments.
  • device 800 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
  • apparatus 800 can include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, And a communication component 816.
  • Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • Processing component 802 can include one or more processors 820 to execute instructions to perform all or part of the steps of the above described methods.
  • processing component 802 can include one or more modules to facilitate interaction between component 802 and other components.
  • processing component 802 can include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operation at device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phone book data, messages, pictures, videos, and the like.
  • the memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM Electrically erasable programmable read only memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • Power component 806 provides power to various components of device 800.
  • Power component 806 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 800.
  • the multimedia component 808 includes a screen between the device 800 and the user that provides an output interface.
  • the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input an audio signal.
  • the audio component 810 includes a microphone (MIC) that is configured to receive an external audio signal when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 804 or transmitted via communication component 816.
  • the audio component 810 also includes a speaker for outputting an audio signal.
  • the I/O interface 812 provides an interface between the processing component 802 and the peripheral interface module, and the peripheral interface module may be Keyboard, click wheel, button, etc. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.
  • Sensor assembly 814 includes one or more sensors for providing device 800 with a status assessment of various aspects.
  • sensor assembly 814 can detect an open/closed state of device 800, relative positioning of components, such as the display and keypad of device 800, and sensor component 814 can also detect a change in position of one component of device 800 or device 800. The presence or absence of user contact with device 800, device 800 orientation or acceleration/deceleration, and temperature variation of device 800.
  • Sensor assembly 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 814 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices.
  • the device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
  • communication component 816 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • the communication component 816 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A gate array
  • controller microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • a non-transitory computer readable storage medium comprising instructions, such as a memory 804 comprising instructions executable by processor 820 of apparatus 800 to perform the above method.
  • the present disclosure can be a system, method, and/or computer program product.
  • the computer program product can comprise a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
  • the computer readable storage medium can be a tangible device that can hold and store the instructions used by the instruction execution device.
  • the computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, with instructions stored thereon A raised structure in the hole card or groove, and any suitable combination of the above.
  • a computer readable storage medium as used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (eg, a light pulse through a fiber optic cable), or through a wire The electrical signal transmitted.
  • the computer readable program instructions described herein can be downloaded from a computer readable storage medium to various computing/processing devices or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in each computing/processing device .
  • Computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages.
  • the computer readable program instructions can be executed entirely on the user's computer, partially on the user's computer, Execution for a stand-alone software package, partly on a user's computer, on a remote computer, or entirely on a remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (eg, using an Internet service provider to access the Internet) connection).
  • the customized electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present disclosure.
  • the computer readable program instructions can be provided to a general purpose computer, a special purpose computer, or a processor of other programmable data processing apparatus to produce a machine such that when executed by a processor of a computer or other programmable data processing apparatus Means for implementing the functions/acts specified in one or more of the blocks of the flowcharts and/or block diagrams.
  • the computer readable program instructions can also be stored in a computer readable storage medium that causes the computer, programmable data processing device, and/or other device to operate in a particular manner, such that the computer readable medium storing the instructions includes An article of manufacture that includes instructions for implementing various aspects of the functions/acts recited in one or more of the flowcharts.
  • the computer readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device to perform a series of operational steps on a computer, other programmable data processing device or other device to produce a computer-implemented process.
  • instructions executed on a computer, other programmable data processing apparatus, or other device implement the functions/acts recited in one or more of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagram can represent a module, a program segment, or a portion of an instruction that includes one or more components for implementing the specified logical functions.
  • Executable instructions can also occur in a different order than those illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

本公开涉及一种视频录制方法及装置，其中该方法包括：对所播放的视频的各帧图像逐帧进行面部特征识别；根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸；以及根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。根据本公开实施例的视频录制方法和装置，通过将面部特征识别技术应用到录屏技术，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。

Description

视频录制方法及装置
交叉引用
本申请主张2016年11月28日提交的中国专利申请号为201611071695.8的优先权，其全部内容通过引用包含于此。
技术领域
本公开涉及图像处理领域，尤其涉及一种视频录制方法及装置。
背景技术
针对PC(Personal Computer，个人计算机)端的在线视频或本地视频，在目前的视频录制(以下还称为“录屏”)技术中，录屏框的框选位置固定并且仅能录制固定范围内的视频内容、即录屏框的框选位置及尺寸固定。由此，导致录制得到的视频内容可能并不总是用户所期望的，用户体验性较差。
发明内容
有鉴于此，本公开提出了一种通过将面部特征识别技术应用到录屏技术的视频录制方法和装置。由此，能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。
根据本公开的一方面，提供了一种视频录制方法，包括：对所播放的视频的各帧图像逐帧进行面部特征识别；根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸；以及根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
对于上述视频录制方法，在一种可能的实现方式中，根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸，包括：根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及初始尺寸；从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及将在所述各帧图像中的录屏框的初始尺寸调整成所述基准尺寸。
对于上述视频录制方法，在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
对于上述视频录制方法，在一种可能的实现方式中，根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸，包括：在首次从所述视频的一帧图像中识别出多个对象的面部特征的情况下，从所述多个对象中选择至少一个对象作为关注对象；在所述一帧图像的后续帧图像中，逐帧确定与所述关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸。
对于上述视频录制方法，在一种可能的实现方式中，还包括：在所述后续帧图像中，如果存在不具有所述匹配面部特征的帧图像，则分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定从所述一帧图像到不具有所述匹配面部特征的帧图像之间的帧图像中的录屏框的位置及尺寸。
对于上述视频录制方法，在一种可能的实现方式中，分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸，包括：分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及初始尺寸；从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及将在所述一帧图像和所述后续帧图像中的初始尺寸调整成所述基准尺寸。
对于上述视频录制方法，在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
对于上述视频录制方法，在一种可能的实现方式中，根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制，包括：将预设的表情加载到所述录屏框中；以 及根据所加载的表情及在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
对于上述视频录制方法，在一种可能的实现方式中，对所播放的视频的各帧图像逐帧进行面部特征识别，包括：对所播放的视频的各帧图像中的面部的关键区域位置进行定位，其中，所述关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个。
根据本公开的另一方面，提供了一种视频录制装置，包括：面部特征识别单元，用于对所播放的视频的各帧图像逐帧进行面部特征识别；确定单元，与所述面部特征识别单元连接，用于根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸；以及录屏单元，与所述确定单元连接，用于根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
对于上述视频录制装置，在一种可能的实现方式中，所述确定单元包括：第一确定模块，用于根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及初始尺寸；第一选择模块，与所述第一确定模块连接，用于从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及调整模块，与所述第一选择模块连接，用于将在所述各帧图像中的录屏框的初始尺寸调整成所述基准尺寸。
对于上述视频录制装置，在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
对于上述视频录制装置，在一种可能的实现方式中，所述确定单元包括：第二选择模块，用于在首次从所述视频的一帧图像中识别出多个对象的面部特征的情况下，从所述多个对象中选择至少一个对象作为关注对象；第二确定模块，与所述第二选择模块连接，用于在所述一帧图像的后续帧图像中，逐帧确定与所述关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及第三确定模块，与所述第二确定模块连接，用于分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸。
对于上述视频录制装置，在一种可能的实现方式中，所述第三确定模块还用于：在所述后续帧图像中，如果存在不具有所述匹配面部特征的帧图像，则分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定从所述一帧图像到不具有所述匹配面部特征的帧图像之间的帧图像中的录屏框的位置及尺寸。
对于上述视频录制装置，在一种可能的实现方式中，所述第三确定模块用于：分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及初始尺寸；从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及将在所述一帧图像和所述后续帧图像中的初始尺寸调整成所述基准尺寸。
对于上述视频录制装置，在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
对于上述视频录制装置，在一种可能的实现方式中，所述录屏单元包括：加载模块，用于将预设的表情加载到所述录屏框中；以及录屏模块，与所述加载模块连接，用于根据所加载的表情及在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
对于上述视频录制装置，在一种可能的实现方式中，所述面部特征识别单元用于：对所播放的视频的各帧图像中的面部的关键区域位置进行定位，其中，所述关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个。
根据本公开实施例的视频录制方法和装置，通过将面部特征识别技术应用到录屏技术，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户 体验。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
包含在说明书中并且构成说明书的一部分的附图与说明书一起示出了本公开的示例性实施例、特征和方面，并且用于解释本公开的原理。
图1示出根据本公开一实施例的视频录制方法的流程图；
图2示出检测到正面的面部的示意图；
图3示出检测到侧面面部的示意图；
图4示出确定正面的面部的录屏框的尺寸的示意图；
图5示出确定侧面的面部的录屏框的尺寸的示意图；
图6示出本公开的另一实施例的视频录制方法的流程图；
图7示出本公开的又一实施例的视频录制方法的流程图；
图8示出本公开一实施例的人脸追踪识别和追踪录制视频的示意图；
图9示出根据本公开一实施例的视频录制装置的结构框图；
图10示出根据本公开的另一实施例的视频录制装置的结构框图；以及
图11是根据一示例性实施例示出的视频录制装置的结构框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
另外，为了更好的说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
图1示出根据本公开一实施例的视频录制方法的流程图。如图1所示，该方法可以包括以下步骤：
步骤S100、对所播放的视频的各帧图像逐帧进行面部特征识别；
步骤S110、根据面部特征识别结果来确定在各帧图像中的录屏框的位置及尺寸；以及
步骤S120、根据在各帧图像中的录屏框的位置及尺寸来对视频进行录制。
具体而言，首先，在视频播放器中播放要进行录屏的视频，然后例如点击录屏软件按钮，由此弹出录屏设置框，并在设置框内点击特定按钮(例如面部录制按钮)。其中，所播放的视频可以是从互联网上获取到的在线视频，也可以是已经存储在本地存储器、例如硬盘上的本地视频。
对于上述步骤S110，针对所播放的视频的各帧图像，可以对其逐帧进行面部特征识别，以检测各帧图像中是否存在人脸(面部)。并且在存在面部的情况下，进一步确定该面部在帧图像中的具体位置以及该面部的轮廓大小。
在一种可能的实现方式中，可以对所播放的视频的各帧图像中的面部的关键区域位置进行定位，并且对各关键区域位置进行特征识别，以得到该面部的面部特征。其中，该关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个，该面部特征可以包括该面部在帧图像中的位置及其轮廓大小。需要说明的是，该关键区域位置不限于以上列举的示例，而只要是能够反映面部特征的部位均可。此外，所检测 出的面部可以是正面(如图2所示)，也可以是侧面(如图3所示)，并且可以支持一定程度的遮挡以及多角度检测。
在一种可能的实现方式中，在一帧图像中，可能存在多个对象(例如人物)的面部。如果存在多个面部，则分别对与各面部的关键区域位置进行识别，以得到各面部的面部特征。
在一种可能的实现方式中，在识别出面部并且得到其面部特征之后，可以将这些信息作为面部特征识别结果而存储在存储器中。
对于上述步骤S110，在通过对各帧图像进行面部特征识别并得到各帧图像的面部特征识别结果之后，可以根据所得到的面部特征结果来确定对各帧图像进行录屏时的录屏框的位置及尺寸。
例如，如果在某一帧图像中检测到一个面部，并且得到了其面部特征(包括该面部在帧图像中的位置及轮廓大小)，则可以根据该面部特征来确定录屏框的位置及尺寸。其中，该录屏框至少能够框选整个面部的区域(如图4、5所示)。又如，如果某一帧图像中检测到多个面部，则根据该多个面部的面部特征来确定录屏框的位置及尺寸。其中，该录屏框至少能够框选全部这多个面部的区域。又如，如果在某一帧图像中未检测到面部，即，该帧图像中不存在面部，则可以使录屏框暂时消失，即不对该帧图像进行录制，等到在后续帧图像中再次检测到面部时，再使录屏框出现，并确定其位置和尺寸。
对于上述步骤S120，在步骤S110中确定了要对各帧图像进行录屏时的录屏框的位置及尺寸时，例如可以点击开始视频录制按钮，以根据所确定出的录屏框的位置及尺寸对该视频进行录制。由此，制作出包括各种面部的面部表情的视频短片。
在录制结束后，例如可以自动将录制的视频保存成通用的mp4格式，并保存至例如本地硬盘上的某一文件夹。当用户需要观看该录制的视频时，点击该mp4格式的文件即可进行观看。
根据本公开实施例的视频录制方法，能够通过对视频中的各帧图像的面部特征进行识别、并根据面部特征识别结果来确定在各帧图像中的录屏框的位置及尺寸，然后根据所确定出的录屏框的位置及尺寸对视频进行录制。这样，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。
在上述实施例的录屏中，由于针对各帧图像所检测出的面部的轮廓大小可能不同，因此针对各帧图像的录屏框的尺寸也可能不同。在利用不同的录屏框尺寸来对各帧图像进行录制时，所得到的各帧图像的尺寸不同。将这样各帧图像拼接成视频时，可能会产生视频图像不连续、不自然的现象。
为了解决上述问题，在本实施例中，采用将各帧图像的录屏框尺寸调整成相同尺寸之后再对视频进行录制。
图6示出本公开的另一实施例的视频录制方法的流程图。图6中标号与图1相同的步骤具有相同的功能，为简明起见，省略对这些步骤的详细说明。
如图6所示，本实施例的视频录制方法与图1所示的视频录制方法的主要区别在于，上述步骤S110可以包括以下步骤：
步骤S210、根据面部特征识别结果来确定在各帧图像中的录屏框的位置及初始尺寸；
步骤S220、从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及
步骤S230、将在一帧图像和后续帧图像中的初始尺寸调整成该基准尺寸。
具体而言，在步骤S100中得到所识别出的面部特征识别结果之后，可以首先根据该面部特征识别结果来确定针对各帧图像的录屏框的位置、以及录屏框的初始尺寸。其中，这些初始尺寸可能由于所识别出的面部特征识别结果的不同而不同。然后，从所确定的各初始尺寸中，选择其中一个适当的尺寸作为基准尺寸，然后将各帧图像中的录屏框的 尺寸均调整成该基准尺寸。其中，在一种可能的实现方式中，所述基准尺寸是根据视频的各帧图像的分辨率而预先设置的。并且，如果所确定出的初始尺寸大于该基准尺寸，则例如可以将该帧图像按比例缩小，以使得利用具有该基准尺寸的录屏框来进行视频录制时能够框选到该帧图像中的面部区域。
在一种可能的实现方式中，该基准尺寸是所确定出的各初始尺寸中的最大尺寸。当然，该基准尺寸不限于此，而可以是任意适当的尺寸，只要利用该尺寸录制出的帧图像的分辨率能够满足用户观看的清晰度即可。
接着，在后续的步骤S120中，利用之前确定的各帧图像的录屏框的位置以及调整后的录屏框的尺寸来进行视频录制。这样，针对各帧图像所录制出的帧图像的尺寸是一致的，因此能够解决在将这些帧图像拼接时的视频图像不连续、不自然的问题。
需要说明的是，解决视频图像不连续、不自然的问题的方法不限于上述实施例，也可以采用其它方法。例如，可以首先根据步骤S100中所识别出的面部特征识别结果对各帧图像进行录制，然后，以所录制出的适当尺寸(例如最大尺寸)的帧图像的尺寸为基准，将其它帧图像的尺寸均调整成该适当尺寸。其中，用于将其它帧图像的尺寸调整成该适当尺寸的方法可以是在这些其它帧图像的边缘填充背景等。在通过填充背景而使其它帧图像的尺寸变成适当尺寸之后，再对这些帧图像进行拼接，这样同样能够解决在将这些帧图像拼接时的视频图像不连续、不自然的问题。
这样，根据本公开实施例的视频录制方法，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。并且，本实施例可以通过调整基于面部特征识别技术所确定出的录屏框的尺寸，由此使得在视频图像拼接时不会产生视频图像不连续、不自然的问题。
如上所述，在一帧图像中，可能识别出多个对象的面部。在这种情况下，用户可能只期望针对其中某一个或多个对象的面部进行录制，即在对该视频进行录制时，仅录制该一个对象或该多个对象的面部，从而实现对该一个对象或该多个对象的面部表情的记录和追踪。
为此，可以利用本实施例的图7所示的视频录制方法的流程图来实现上述目的。
图7示出本公开的又一实施例的视频录制方法的流程图。图7中标号与图1相同的步骤具有相同的功能，为简明起见，省略对这些步骤的详细说明。
如图7所示，本实施例的视频录制方法与图1所示的视频录制方法的主要区别在于，上述步骤S110可以包括以下步骤：
步骤S310、在首次从视频的一帧图像中识别出多个对象的面部特征的情况下，从多个对象中选择至少一个对象作为关注对象；
步骤S320、在一帧图像的后续帧图像中，逐帧确定与关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及
步骤S330、分别根据关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在一帧图像和后续帧图像中的录屏框的位置及尺寸。
首先，针对一个对象的记录和追踪的情况进行说明。
具体而言，在上述步骤S310中，在逐帧对各帧图像进行面部特征识别时，如果在某一帧图像中识别出多个对象的面部，则可以从该多个对象中选择用户感兴趣的一个对象作为关注对象，并且在存储器中存储该关注对象的面部特征。并且，在上述步骤S330中，根据该关注对象的面部特征可以确定该帧图像的录屏框的位置及尺寸。
然后，在对后续帧图像的面部特征识别中，以该关注对象作为录屏焦点对象，从而追踪该关注对象的一系列面部表情变化。具体而言，在上述步骤S320中，接着对该帧图像的后续帧图像的面部特征进行识别，并确定这些后续帧图像中是否存在该关注对象。例如，在某一后续图像中，识别出多个对象，然后将这多个对象的面部特征分别与之前 设定的关注对象的面部特征相比较，以确定这些面部特征与关注对象的面部特征的相似度。如果某一对象的面部特征的特征值与之前设定的关注对象的面部特征的特征值之间的差异小，即它们之间的相似度小于预设的相似度阈值(换句话说，这两个对象的相似度高)，则表示该对象为用户所要追踪的对象、即该对象为该帧图像中的关注对象。这里，将该对象的面部特征称为匹配面部特征。另外，如果某一后续帧图像中不存在该关注对象，则可以不对该帧图像进行录制。
依次对视频中的所有后续帧图像执行上述步骤S320的处理。
这样，可以确认后续帧图像中是否存在该关注对象。并且，在存在该关注对象的情况下，在上述步骤S330中，根据该关注对象的面部特征(匹配面部特征)来确定其对应的帧图像的录屏框的位置及尺寸。
同样，在用户首次识别出某一帧图像具有多个对象的面部时，用户也可以从其中选择两个或更多对象作为关注对象，以分别对关注对象中的各对象进行记录和追踪。
例如，选择多个对象中的对象1和对象2作为关注对象1和关注对象2。并且在存储器中存储该关注对象1和关注对象2的面部特征。并且，在上述步骤S330中，根据该关注对象1和关注对象2的面部特征可以分别确定在该帧图像中针对关注对象1和关注对象2的录屏框的位置及尺寸。
然后，在对后续帧图像的面部特征识别中，分别以该关注对象1和关注对象2作为录屏焦点对象，从而追踪关注对象1和关注对象2的一系列面部表情变化。具体而言，在上述步骤S320中，接着对该帧图像的后续帧图像的面部特征进行识别，并确定这些后续帧图像中是否存在该关注对象1和关注对象2。例如，在某一后续图像中，识别出多个对象，然后将这多个对象的面部特征分别与之前设定的关注对象1和关注对象2的面部特征相比较，以分别确定这些面部特征与关注对象1和关注对象2的面部特征的相似度。如果某一对象的面部特征的特征值与之前设定的关注对象1的面部特征的特征值之间的差异小，即它们之间的相似度小于预设的相似度阈值(换句话说，这两个对象的相似度高)，则表示该对象为用户所要追踪的对象、即该对象为该帧图像中的关注对象1。同理，如果某一对象的面部特征的特征值与之前设定的关注对象2的面部特征的特征值之间的差异小，即它们之间的相似度小于预设的相似度阈值(换句话说，这两个对象的相似度高)，则表示该对象为用户所要追踪的对象、即该对象为该帧图像中的关注对象2。这里，将该某一对象的面部特征称为匹配面部特征。在一种可能的实现方式中，后续帧图像中可能仅存在关注对象1，也可能仅存在关注对象2，还可能同时存在关注对象1和关注对象2。
另外，如果某一后续帧图像中不存在关注对象1和关注对象2，则可以不对该帧图像进行录制。
依次对视频中的所有后续帧图像执行上述步骤S320的处理。
然后，在步骤S330中，针对后续帧图像中的各关注对象1和关注对象2，分别根据其匹配面部特征来确定在后续帧图像中的录屏框的位置及尺寸。
以上以选择两个关注对象为示例来描述了对用户感兴趣的对象的记录和追踪，但是本领域技术人员能够知道，对用户感兴趣的对象的记录和追踪的上述过程同样适用了选择更多的对象。
需要说明的是，如果选择了多个对象，则可以分别针对各对象确定录屏框的位置及尺寸，然后分别对各对象进行录制，以分别对各对象的面部表情变化进行记录和追踪。此外，还可以将这多个对象框选到一个录屏框中，以将这多个对象作为一个整体来进行记录和追踪，这样可以反映面部表情所对应的场景。
这样，在本实施例中，可以不必对所识别出的所有对象的面部进行录制，而仅录制用户期望录制的对象，从而实现对该对象的一系列表情变化的记录和追踪。
在一种可能的实现方式中，可以不必是在首次识别出多个对象的面部特征时选择关 注对象，而可以在用户看到感兴趣的对象时再将该对象选择为关注对象。
在一种可能的实现方式中，在同一帧图像中，可能存在多个面部的面部特征与关注对象的面部特征的相似度均小于预设的相似度阈值的情况。例如，同一人物的正面和侧面。在这种情况下，可以选择与相似度更高(差距值更小)的面部相对应的对象作为关注对象、例如选择与正面相对应的人物作为关注对象。
在一种可能的实现方式中，如果在对后续帧图像的识别中，一旦发现存在不具有上述匹配面部特征的帧图像，则可以不再对后续帧图像进行特征识别，而分别根据到目前为止的关注对象的面部特征来确定这些帧图像的录屏框的位置及尺寸。
例如，在视频中存在100帧图像，在第1帧图像时确定了关注对象，接着依次识别后续的第2帧图像、第3帧图像、……，当在例如第20帧图像时发现不存在该关注对象时，则不再对后续帧图像进行特征识别，而是仅利用第1帧图像～第19帧图像中的关注对象的面部特征来分别确定第1帧图像～第19帧图像的录屏框的位置及尺寸，并且根据所确定出的录屏框的位置及尺寸分别对第1帧图像～第19帧图像进行录制，而不再录制后续的帧图像。这样，可以仅录制一段连续的视频中的帧图像，从而得到面部表情的连续变化。
以上是以一个对象作为关注对象为示例进行了描述，但本公开不限于此，以多个对象作为关注对象的情况同样适用于上述过程。
在一种可能的实现方式中，用户可以根据自身需要在任何帧图像处停止视频的录制。例如，播放器中设置有面部录制停止按钮，用户按下该面部录制停止按钮之后，即可停止面部录制。
此外，在上述步骤S330中确定录屏框的位置及尺寸时，同样可以应用上述步骤S210～S230，以解决视频录制之后视频图像的不连续、不自然的问题。
具体而言，上述步骤S330具体可以包括以下步骤：分别根据关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在一帧图像和后续帧图像中的录屏框的位置及初始尺寸；从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及将在一帧图像和后续帧图像中的初始尺寸调整成该基准尺寸。
此外，在一种可能的实现方式中，在视频录制过程中，还可以对视频内识别到的面部进行趣味编辑等操作。例如，在检测到多个对象的面部的情况下，如果视频内有用户不想看到面部，则可以对面部进行趣味修饰，如给面部戴上面具或对面部进行表情添加等，在表情添加完成之后，例如可以点击保存按钮，以对所添加的表情进行保存。
此时，添加的表情可以应用到视频的全部帧图像中，也可以应用到用户所期望应用到的帧图像中。
此外，在一种可能的实现方式中，在上述任一实施例中，上述步骤S120可以包括以下步骤：将预设的表情加载到录屏框中；以及根据所加载的表情及在各帧图像中的录屏框的位置及尺寸来对视频进行录制。
例如，可以在设置表情添加按钮，点击该按钮后会出现一个包含多个表情的表情包，然后从中选择一个表情加载到录屏框中。然后，在视频录制时，即可根据所加载的表情及在各帧图像中的录屏框的位置及尺寸来对视频进行录制。
在一种可能的实现方式中，可以在视频的识别出了面部的全部帧图像中加载预设的表情，也可以在部分帧图像中加载预设的表情。另外，针对各帧图像，所加载的预设表情可以相同，也可以不同。
这样，通过在视频录制的过程中加载预设的表情，可以增加视频录制中的趣味性。
这样，根据本公开实施例的视频录制方法，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。并且，本实施例可以通过调整基于面部特征识别技术所确定出的录屏框的尺寸，由此使得在视频图像拼接时不会产生视频图像不连续、不自然的问题。此外，本 实施例可以通过在某一帧图像中设定关注对象，并使得在后续帧图像中追踪该关注对象，然后根据关注对象的面部特征来确定各帧图像的录屏框的位置及尺寸，由此能够实现对用户感兴趣的关注对象的记录和追踪。此外，本实施例可以在视频录制过程中加载预设的表情，由此增加视频录制的趣味性。
本实施例示出了本公开的具体应用场景及相应的实际操作步骤和装置等。
首先，用户进行视频录制的大体操作步骤如下：
(1)在用户点击播放视频后，点击录屏软件按钮，系统弹出录屏设置框，设置框内点击“面部录制”按钮；
(2)录屏框会默认框选到视频内识别出的面部位置，如果视频画面上出现超过两个以上的面部时，录屏框仅会默认框选一个面部，用户也可根据自己要录制的面部进行调整，将录屏框移动到需要录制的面部上，录屏框会根据人脸关键点反馈数据进行重新定位(定位视频内面部的关键区域位置)；
(3)在面部框选确定后，即可点击“开始录制”按钮；
(4)录制过程中，录屏框会随着面部的正脸及侧脸进行移动跟踪录制，当人脸移出录屏框后，视频录制即结束，此外，用户也可提前结束录制过程；
(5)当视频内面部动作完成后，录屏框会自动消失，完后录制过程，自动进行保存；
(6)在录制结束后，系统会自动将录制的视频保存成通用的mp4格式，并保存至本地文件夹中。用户需要播放录制的视频时到本地文件夹内查看即可。
在上述步骤的基础上，用户还可以进行一定程度的趣味性编辑等操作。
例如，在录制过程中，可以对视频内识别到的人脸(面部)进行趣味编辑等操作，如果在视频内存在用户不想看到的面部，则可以对该面部进行趣味修饰，如给面部戴上面具或对面部进行表情添加等，添加完成后，点击“保存”按钮，以对该表情添加进行保存。此时添加的表情，可以应用到整集视频内，视频内只要此面部出现，都会带着面具或者表情等。这样可以减少用户对人物的方案，并且减少快进的需求，增加了用户看视频时的趣味性等。
此外，上述步骤可以利用如下的人脸追踪装置和录屏装置来实现。
其中，该人脸追踪装置可以包括：
(1)调用模块、特征(面部特征)比较器；
(2)关系建立模块，用于根据视频序列帧(视频中的各帧图像)中每个人脸(面部)的面部特征信息，建立不同人脸的特征值与人脸对应的人的ID值之间的对应关系，以使这些特征值在特征比较器中进行比较；
(3)查找模块，用于根据特征比较器的比较，查找与录屏焦点对象差距值最低的人脸的面部特征；
(4)存储模块，用于将输出(识别)的人脸特征进行存储；
(5)人脸追踪模块，用于追踪视频序列帧内与录屏焦点对象差距值最低的人脸；
(6)识别模块，用于当视频中同时出现两个以上人脸时，取差距值最小的人脸作为录屏焦点对象；
(7)识别存储器，将视频序列帧内识别的人脸进行存储。
此外，该录屏装置可以包括：
(1)监测模块，用于监测录屏触发的信号和人脸追踪装置发出的信号，开始录制；
(2)收集模块，用于将人脸追踪录制的视频帧进行收集
(3)数据存储模块，用于将录制的视频帧数据进行存储。
图8示出本公开一实施例的人脸追踪识别和追踪录制视频的示意图，具体过程详见以下描述。
(1)在所播放的视频中，逐帧检测视频的各帧图像中的人脸(面部)数和人脸位置信息 (对应图8中的“人脸检测”)。
(2)分析具有人脸特征的模型，与人脸特征模型进行概率匹配(面部特征识别)。
具体而言，采用人脸(面部)关键点检测方法，基于人的脸部特征，判断是否存在人脸。定位视频内面部的关键区域位置，包括眉毛、眼睛、鼻子、嘴巴，脸部轮廓等。该检测方法支持一定程度遮挡以及多角度人脸。通过使用人脸关键点检测技术，可以精确定位人脸(如图2所示的人脸的正面以及如图3所示的人脸的侧面)(对应图8中的“人脸关键点检测”)。
(3)选取一个人脸，并将该人脸设定为录屏焦点对象。设定成功后，后台会记录所选取人脸的关键点特征，并保存在人脸比较器中。该人脸即为后续追踪的主焦点。
然后，将视频画面中出现的多个人脸进行位置信息记忆，利用每个人脸的特征记忆获取所需的特征值。在进行人脸追踪过程中，需要将当前检测到的人脸的特征值与之前在特征比较器中所存储的作为录屏焦点对象的人脸的对应特征值进行比较，以查看差距值。如果当前检测到的人脸与之前所存储的作为比较的人脸相似度小于预设的差距值(相似度阈值)(即相似度高)，则将该人脸确定为所要追踪的人脸。如果视频画面上出现两个及以上的人脸与之前所存储的作为比较的人脸相似度小于预设的差距值，则将相似度差距值最小的人脸确定为所要追踪的人脸。并且，将该人脸的关键点特征进行保存(对应图8中的“人脸比较器”、“人脸特征提取”、“人脸识别”和“存储”)。
(4)接着，确定录屏框选的位置信息，根据人脸的关键点模型进行最外边缘的对角连接，确定出录屏框的位置及尺寸(如图4、5所示)(对应图8中的“录屏框定位”)。
(5)在视频画面上显示录屏框，录屏框位置根据人脸追踪识别过程中所反馈出的关键点特征，对视频进行追踪录制。当追踪的关键点(正面、侧面)特征消失后，结束录制，其中，也可以根据用户需要进行提取结束录制的操作(对应图8中的“录屏框位置对焦”、“录屏框追踪”和“录制视频”)。
(6)将录制出的视频进行视频封装，然后保存在本地文件夹中(对应图8中的“视频封装”和“保存本地”)。
此外，作为在视频录制过程中添加表情等的操作，主要涉及如下模块：
(1)识别模块，用于识别视频帧的人脸表情，生成识别结果；
(2)获取模块，用于获取预设的表情，并选择其中一个进行贴图合成；
(3)确定模快，用于确定表情在视频帧中的加载位置；
(4)发送模块，用于发送表情特效的加载图；
(5)加载模块，用于在例如每个视频帧中进行表情特效的加载图的加载；
(6)显示模块，用于在视频播放中，在例如每个视频帧中的人脸中都显示表情图；
其中，可以选择预设表情包中的一个表情，同时对视频帧中的人脸进行匹配识别，生成识别结果，并且，确定所要加载的表情在即时视频帧中的加载位置。此外，将每个视频帧中的人脸特征的参数点与表情进行合成。然后，在视频录制时，对加载了表情的各视频帧进行录制。这样，可以增加用户观看视频时的趣味性。
这样，根据本公开实施例的视频录制方法及相应装置，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。并且，本实施例可以通过在某一帧图像中设定录屏焦点对象(关注对象)，并使得在后续帧图像中追踪该录屏焦点对象，然后根据录屏焦点对象的面部特征来确定各帧图像的录屏框的位置及尺寸，由此能够实现对用户感兴趣的关注对象的记录和追踪。此外，本实施例可以在视频录制过程中加载预设的表情，由此增加视频录制的趣味性。
图9示出根据本公开一实施例的视频录制装置的结构框图。如图9所示，该视频录制装置90可以包括：面部特征识别单元91，用于对所播放的视频的各帧图像逐帧进行面部 特征识别；确定单元92，与所述面部特征识别单元91连接，用于根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸；以及录屏单元93，与所述确定单元92连接，用于根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
在一种可能的实现方式中，所述确定单元92包括：第一确定模块921，用于根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及初始尺寸；第一选择模块922，与所述第一确定模块921连接，用于从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及调整模块923，与所述第一选择模块922连接，用于将在所述各帧图像中的录屏框的初始尺寸调整成所述基准尺寸。
在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
在一种可能的实现方式中，所述录屏单元93可以包括：加载模块931，用于将预设的表情加载到所述录屏框中；以及录屏模块932，与所述加载模块931连接，用于根据所加载的表情及在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
在一种可能的实现方式中，所述面部特征识别单元91具体用于：对所播放的视频的各帧图像中的面部的关键区域位置进行定位，其中，所述关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个。
本公开实施例的视频录制装置可以用来实现上述图1、图6和图7中任一实施例所述的视频录制方法。上述图1、图6和图7中所述的视频录制方法的具体流程请见上述图1、图6和图7的详细阐述。
这样，根据本公开实施例的视频录制装置，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。并且，本实施例可以通过调整基于面部特征识别技术所确定出的录屏框的尺寸，由此使得在视频图像拼接时不会产生视频图像不连续、不自然的问题。此外，本实施例可以在视频录制过程中加载预设的表情，由此增加视频录制的趣味性。
图10示出根据本公开的另一实施例的视频录制装置的结构框图。图10中标号与图9相同的组件具有相同的功能，为简明起见，省略对这些组件的详细说明。
如图10所示，本实施例的视频录制装置100与图9所示的视频录制装置90的主要区别在于，所述确定单元92还可以包括：第二选择模块1001，用于在首次从所述视频的一帧图像中识别出多个对象的面部特征的情况下，从所述多个对象中选择至少一个对象作为关注对象；第二确定模块1002，与所述第二选择模块1001连接，用用于在所述一帧图像的后续帧图像中，逐帧确定与所述关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及第三确定模块1003，与所述第二确定模块1002连接，用于分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸。
在一种可能的实现方式中，所述第三确定模块1003还用于：在所述后续帧图像中，如果存在不具有所述匹配面部特征的帧图像，则分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定从所述一帧图像到不具有所述匹配面部特征的帧图像之间的帧图像中的录屏框的位置及尺寸。
在一种可能的实现方式中，，所述第三确定模块1003可以具体用于：分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及初始尺寸；从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及将在所述一帧图像和所述后续帧图像中的初始尺寸调整成所述基准尺寸。
在一种可能的实现方式中，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
本公开实施例的视频录制装置可以用来实现上述图1、图6和图7中任一实施例所述的视频录制方法。上述图1、图6和图7中所述的视频录制方法的具体流程请见上述图1、图6和图7的详细阐述。
这样，根据本公开实施例的视频录制装置，可以通过将面部特征识别技术应用到录屏技术中，由此能够灵活设置录屏框的位置及尺寸，从而录制出用户所期望的视频，提高用户体验。并且，本实施例可以通过调整基于面部特征识别技术所确定出的录屏框的尺寸，由此使得在视频图像拼接时不会产生视频图像不连续、不自然的问题。此外，本实施例可以通过在某一帧图像中设定关注对象，并使得在后续帧图像中追踪该关注对象，然后根据关注对象的面部特征来确定各帧图像的录屏框的位置及尺寸，由此能够实现对用户感兴趣的关注对象的记录和追踪。此外，本实施例可以在视频录制过程中加载预设的表情，由此增加视频录制的趣味性。
图11是根据一示例性实施例示出的视频录制装置的结构框图。其中该装置800用于执行上述实施例中所述的视频录制方法。例如，装置800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图11，装置800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制装置800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在装置800的操作。这些数据的示例包括用于在装置800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为装置800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为装置800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述装置800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当装置800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当装置800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是 键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为装置800提供各个方面的状态评估。例如，传感器组件814可以检测到装置800的打开/关闭状态，组件的相对定位，例如所述组件为装置800的显示器和小键盘，传感器组件814还可以检测装置800或装置800一个组件的位置改变，用户与装置800接触的存在或不存在，装置800方位或加速/减速和装置800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于装置800和其他设备之间有线或无线方式的通信。装置800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非易失性计算机可读存储介质，例如包括指令的存储器804，上述指令可由装置800的处理器820执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作 为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (18)

  1. 一种视频录制方法，其特征在于，包括：
    对所播放的视频的各帧图像逐帧进行面部特征识别；
    根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸；以及
    根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
  2. 根据权利要求1所述的视频录制方法，其特征在于，根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸，包括：
    根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及初始尺寸；
    从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及
    将在所述各帧图像中的录屏框的初始尺寸调整成所述基准尺寸。
  3. 根据权利要求2所述的视频录制方法，其特征在于，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
  4. 根据权利要求1所述的视频录制方法，其特征在于，根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及尺寸，包括：
    在首次从所述视频的一帧图像中识别出多个对象的面部特征的情况下，从所述多个对象中选择至少一个对象作为关注对象；
    在所述一帧图像的后续帧图像中，逐帧确定与所述关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及
    分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸。
  5. 根据权利要求4所述的视频录制方法，其特征在于，还包括：
    在所述后续帧图像中，如果存在不具有所述匹配面部特征的帧图像，则分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定从所述一帧图像到不具有所述匹配面部特征的帧图像之间的帧图像中的录屏框的位置及尺寸。
  6. 根据权利要求4所述的视频录制方法，其特征在于，分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸，包括：
    分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及初始尺寸；
    从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及
    将在所述一帧图像和所述后续帧图像中的初始尺寸调整成所述基准尺寸。
  7. 根据权利要求6所述的视频录制方法，其特征在于，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
  8. 根据权利要求1至7中任一项所述的视频录制方法，其特征在于，根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制，包括：
    将预设的表情加载到所述录屏框中；以及
    根据所加载的表情及在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
  9. 根据权利要求1至8中任一项所述的视频录制方法，其特征在于，对所播放的视频的各帧图像逐帧进行面部特征识别，包括：对所播放的视频的各帧图像中的面部的关键区域位置进行定位，
    其中，所述关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个。
  10. 一种视频录制装置，其特征在于，包括：
    面部特征识别单元，用于对所播放的视频的各帧图像逐帧进行面部特征识别；
    确定单元，与所述面部特征识别单元连接，用于根据面部特征识别结果来确定在所 述各帧图像中的录屏框的位置及尺寸；以及
    录屏单元，与所述确定单元连接，用于根据在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
  11. 根据权利要求10所述的视频录制装置，其特征在于，所述确定单元包括：
    第一确定模块，用于根据面部特征识别结果来确定在所述各帧图像中的录屏框的位置及初始尺寸；
    第一选择模块，与所述第一确定模块连接，用于从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及
    调整模块，与所述第一选择模块连接，用于将在所述各帧图像中的录屏框的初始尺寸调整成所述基准尺寸。
  12. 根据权利要求11所述的视频录制装置，其特征在于，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
  13. 根据权利要求10所述的视频录制装置，其特征在于，所述确定单元包括：
    第二选择模块，用于在首次从所述视频的一帧图像中识别出多个对象的面部特征的情况下，从所述多个对象中选择至少一个对象作为关注对象；
    第二确定模块，与所述第二选择模块连接，用于在所述一帧图像的后续帧图像中，逐帧确定与所述关注对象中的各对象的面部特征的相似度分别在预定的相似度阈值以下的对应对象的匹配面部特征；以及
    第三确定模块，与所述第二确定模块连接，用于分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及尺寸。
  14. 根据权利要求13所述的视频录制装置，其特征在于，所述第三确定模块还用于：
    在所述后续帧图像中，如果存在不具有所述匹配面部特征的帧图像，则分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定从所述一帧图像到不具有所述匹配面部特征的帧图像之间的帧图像中的录屏框的位置及尺寸。
  15. 根据权利要求13所述的视频录制装置，其特征在于，所述第三确定模块用于：
    分别根据所述关注对象中的各对象的面部特征和各对应对象的匹配面部特征，来确定在所述一帧图像和所述后续帧图像中的录屏框的位置及初始尺寸；
    从所确定出的各初始尺寸中选择其中一个尺寸作为基准尺寸；以及
    将在所述一帧图像和所述后续帧图像中的初始尺寸调整成所述基准尺寸。
  16. 根据权利要求15所述的视频录制装置，其特征在于，所述基准尺寸是根据所述视频的各帧图像的分辨率而预先设置的。
  17. 根据权利要求10至16中任一项所述的视频录制装置，其特征在于，所述录屏单元包括：
    加载模块，用于将预设的表情加载到所述录屏框中；以及
    录屏模块，与所述加载模块连接，用于根据所加载的表情及在所述各帧图像中的录屏框的位置及尺寸来对所述视频进行录制。
  18. 根据权利要求10至17中任一项所述的视频录制装置，其特征在于，所述面部特征识别单元用于：对所播放的视频的各帧图像中的面部的关键区域位置进行定位，
    其中，所述关键区域位置包括眉毛、眼睛、鼻子、嘴巴、耳朵和脸部轮廓所在区域中的至少一个。
PCT/CN2017/111075 2016-11-28 2017-11-15 视频录制方法及装置 WO2018095252A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611071695.8A CN106791535B (zh) 2016-11-28 2016-11-28 视频录制方法及装置
CN201611071695.8 2016-11-28

Publications (1)

Publication Number Publication Date
WO2018095252A1 true WO2018095252A1 (zh) 2018-05-31

Family

ID=58902567

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/111075 WO2018095252A1 (zh) 2016-11-28 2017-11-15 视频录制方法及装置

Country Status (2)

Country Link
CN (1) CN106791535B (zh)
WO (1) WO2018095252A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615309A (zh) * 2018-09-25 2019-04-12 阿里巴巴集团控股有限公司 一种数据录制方法及装置、一种计算设备及存储介质
CN112307925A (zh) * 2020-10-23 2021-02-02 腾讯科技（深圳）有限公司 图像检测方法、图像显示方法、相关设备及存储介质

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791535B (zh) * 2016-11-28 2020-07-14 阿里巴巴（中国）有限公司 视频录制方法及装置
CN109218612B (zh) * 2018-09-17 2022-04-22 东莞市丰展电子科技有限公司 一种追踪拍摄系统及拍摄方法
CN109982109B (zh) * 2019-04-03 2021-08-03 睿魔智能科技（深圳）有限公司 短视频的生成方法及装置、服务器和存储介质
CN114189646B (zh) * 2020-09-15 2023-03-21 深圳市万普拉斯科技有限公司 终端控制方法、装置、电子设备和存储介质
CN112714253B (zh) * 2020-12-28 2022-08-26 维沃移动通信有限公司 视频录制方法、装置、电子设备和可读存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2664985A2 (en) * 2012-05-18 2013-11-20 Fujitsu Limited Tablet terminal and operation receiving program
CN103679155A (zh) * 2013-12-30 2014-03-26 深圳锐取信息技术股份有限公司 多目标自动跟踪系统及方法
CN104796781A (zh) * 2015-03-31 2015-07-22 小米科技有限责任公司 视频片段提取方法及装置
CN104967802A (zh) * 2015-04-29 2015-10-07 努比亚技术有限公司 移动终端及其屏幕多区域的录制方法和装置
JP2015194997A (ja) * 2014-03-27 2015-11-05 キヤノンマーケティングジャパン株式会社 ユーザインタフェース装置、ユーザインタフェース方法、プログラム及び記憶媒体
CN106028090A (zh) * 2016-05-23 2016-10-12 努比亚技术有限公司 一种移动终端及其视频录制的方法
CN106791535A (zh) * 2016-11-28 2017-05-31 合网络技术（北京）有限公司 视频录制方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009069185A (ja) * 2007-09-10 2009-04-02 Toshiba Corp 映像処理装置及び映像処理方法
CN102693739A (zh) * 2011-03-24 2012-09-26 腾讯科技（深圳）有限公司 视频片段生成方法及系统
US8824750B2 (en) * 2012-03-19 2014-09-02 Next Level Security Systems, Inc. Distributive facial matching and notification system
CN105872438A (zh) * 2015-12-15 2016-08-17 乐视致新电子科技（天津）有限公司 一种视频通话方法、装置及终端
CN106101767A (zh) * 2016-07-28 2016-11-09 维沃移动通信有限公司 一种屏幕录制方法及移动终端

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2664985A2 (en) * 2012-05-18 2013-11-20 Fujitsu Limited Tablet terminal and operation receiving program
CN103679155A (zh) * 2013-12-30 2014-03-26 深圳锐取信息技术股份有限公司 多目标自动跟踪系统及方法
JP2015194997A (ja) * 2014-03-27 2015-11-05 キヤノンマーケティングジャパン株式会社 ユーザインタフェース装置、ユーザインタフェース方法、プログラム及び記憶媒体
CN104796781A (zh) * 2015-03-31 2015-07-22 小米科技有限责任公司 视频片段提取方法及装置
CN104967802A (zh) * 2015-04-29 2015-10-07 努比亚技术有限公司 移动终端及其屏幕多区域的录制方法和装置
CN106028090A (zh) * 2016-05-23 2016-10-12 努比亚技术有限公司 一种移动终端及其视频录制的方法
CN106791535A (zh) * 2016-11-28 2017-05-31 合网络技术（北京）有限公司 视频录制方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615309A (zh) * 2018-09-25 2019-04-12 阿里巴巴集团控股有限公司 一种数据录制方法及装置、一种计算设备及存储介质
CN112307925A (zh) * 2020-10-23 2021-02-02 腾讯科技（深圳）有限公司 图像检测方法、图像显示方法、相关设备及存储介质
CN112307925B (zh) * 2020-10-23 2023-11-28 腾讯科技（深圳）有限公司 图像检测方法、图像显示方法、相关设备及存储介质

Also Published As

Publication number Publication date
CN106791535B (zh) 2020-07-14
CN106791535A (zh) 2017-05-31

Similar Documents

Publication Publication Date Title
WO2018095252A1 (zh) 视频录制方法及装置
JP6405470B2 (ja) 動画撮影方法及びその装置、プログラム、及び記憶媒体
EP3195601B1 (en) Method of providing visual sound image and electronic device implementing the same
CN109257645B (zh) 视频封面生成方法及装置
WO2016029641A1 (zh) 照片获取方法及装置
US10212386B2 (en) Method, device, terminal device, and storage medium for video effect processing
US20190394419A1 (en) Subtitle displaying method and apparatus
EP2998960B1 (en) Method and device for video browsing
CN106559712B (zh) 视频播放处理方法、装置及终端设备
CN105302315A (zh) 图片处理方法及装置
WO2019206243A1 (zh) 一种素材展示方法、终端和计算机存储介质
CN112069952A (zh) 视频片段提取方法、视频片段提取装置及存储介质
US20220084313A1 (en) Video processing methods and apparatuses, electronic devices, storage mediums and computer programs
CN111553864A (zh) 图像修复方法及装置、电子设备和存储介质
CN106534951B (zh) 视频分割方法和装置
WO2017080084A1 (zh) 字体添加方法及装置
US9799376B2 (en) Method and device for video browsing based on keyframe
CN104460185A (zh) 自动对焦方法及装置
CN109963168A (zh) 视频预览方法及装置
US9325776B2 (en) Mixed media communication
CN109495765B (zh) 视频截取方法及装置
CN108174269B (zh) 可视化音频播放方法及装置
CN109756783B (zh) 海报的生成方法及装置
CN110121081A (zh) 视频播放方法及装置
CN112613447A (zh) 关键点检测方法及装置、电子设备和存储介质

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: 17873242

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10.09.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17873242

Country of ref document: EP

Kind code of ref document: A1