WO2019071381A1 - 一种录像方法、装置及终端 - Google Patents

一种录像方法、装置及终端 Download PDF

Info

Publication number
WO2019071381A1
WO2019071381A1 PCT/CN2017/105370 CN2017105370W WO2019071381A1 WO 2019071381 A1 WO2019071381 A1 WO 2019071381A1 CN 2017105370 W CN2017105370 W CN 2017105370W WO 2019071381 A1 WO2019071381 A1 WO 2019071381A1
Authority
WO
WIPO (PCT)
Prior art keywords
recording
video
gesture
face
mode
Prior art date
Application number
PCT/CN2017/105370
Other languages
English (en)
French (fr)
Inventor
张学熙
Original Assignee
深圳传音通讯有限公司
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 深圳传音通讯有限公司 filed Critical 深圳传音通讯有限公司
Priority to CN201780095760.7A priority Critical patent/CN111201772A/zh
Priority to PCT/CN2017/105370 priority patent/WO2019071381A1/zh
Publication of WO2019071381A1 publication Critical patent/WO2019071381A1/zh

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
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • 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
    • H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes

Definitions

  • the present application relates to the field of image data processing, and in particular, to a video recording method, apparatus, and terminal.
  • various terminals such as smart phones, PDAs or wearable devices are also equipped with cameras, which can also provide camera and video functions, allowing users to record and share around anytime, anywhere. View.
  • the performance of all aspects of the terminal is constantly improving, which makes the camera and video functions more likely to expand in more directions. At the same time, this also makes the end user's experience requirements for the terminal recording application higher and higher.
  • the video recording application of the terminal can only perform simple recording, and the video screen is not further processed, so that the video image obtained by the video application has a single form, low viewing quality, and poor user experience.
  • the embodiment of the present invention provides a video recording method, device, and terminal, which can increase the diversity of the video images acquired by the video application, improve the viewability of the video image, and improve the user experience.
  • the first aspect provides a video recording method, which may include:
  • the terminal recording mode is switched from the first recording mode to the second recording mode, and the second image data is collected in the second recording mode.
  • the human face in the second video recording image is subjected to beauty processing, and if the second video recording image does not include the human face, The second video frame is beautified.
  • the performing the beauty processing on the face in the second video frame includes:
  • An animation effect adding process is performed on the face in the second video recording screen.
  • the method further includes:
  • the second video frame is beautified.
  • the determining, according to the first image data, whether the first gesture is included in the first video frame comprises:
  • At least one activation mode corresponding to the second recording mode, where the at least one activation mode includes a gesture start, Each of the at least one activation mode corresponds to a user operation instruction;
  • the method further includes:
  • the terminal recording mode is performed by the second The recording mode is switched to the first recording mode.
  • a second aspect provides a video recording apparatus, which can include:
  • a recording unit configured to receive a recording start command, and start a first recording mode according to the recording start command to acquire the first image data to obtain a first recording screen;
  • a gesture recognition unit configured to determine, according to the first image data collected by the recording unit, whether the first video frame includes a first gesture
  • a mode switching unit configured to switch the terminal recording mode from the first recording mode to the second recording mode when the gesture recognition unit recognizes that the first video is included in the first video recording frame;
  • the recording unit is further configured to perform second image data acquisition in the second recording mode to obtain a second video recording screen;
  • a screen processing unit configured to determine whether a face is included in the second video frame, and if the second video frame includes the face, perform beauty processing on the face in the second video frame If the second video screen does not include the human face, the second video screen is beautified.
  • the picture processing unit is configured to:
  • An animation effect adding process is performed on the face in the second video recording screen.
  • the picture processing unit is further configured to:
  • the second video frame includes the human face, and the number of the human faces is equal to or greater than a preset threshold, the second video frame is beautified.
  • the gesture recognition unit is configured to:
  • At least one activation mode corresponding to the second recording mode, where the at least one activation mode includes a gesture start, and each of the at least one activation mode corresponds to a user operation instruction;
  • the gesture recognition unit is further configured to:
  • the mode switching unit is further configured to:
  • the terminal When the gesture recognition unit determines that the second gesture is included in the second video frame, the terminal is The recording mode is switched from the second recording mode to the first recording mode.
  • a third aspect provides a terminal that can include a memory, a processor, and a transceiver;
  • the memory, the processor and the transceiver are connected by a bus;
  • the memory is for storing a set of program codes
  • the processor and the transceiver are configured to invoke program code stored in the memory, and perform the following operations:
  • the transceiver is configured to receive a video start command
  • the processor is configured to start a first recording mode according to the receiving, by the transceiver, the recording start command;
  • the transceiver is further configured to perform collecting of the first video data in the first recording mode initiated by the processor to obtain a first video recording screen;
  • the processor is further configured to determine, according to the first image data collected by the transceiver, whether the first video frame includes a first gesture, and if the first video frame includes the first gesture, And then switching the terminal recording mode from the first recording mode to the second recording mode;
  • the transceiver is further configured to perform second image data acquisition in the second recording mode initiated by the processor to obtain a second video recording screen;
  • the processor is further configured to determine whether the second video frame collected by the transceiver includes a human face, and if the second video frame includes the human face, the second video recording The face is subjected to a beauty treatment, and if the face is not included in the second video frame, the second video frame is beautified.
  • the processor is configured to:
  • the processor is further configured to:
  • the second video frame is beautified.
  • the processor is further configured to:
  • At least one activation mode corresponding to the second recording mode, where the at least one activation mode includes a gesture start, and each of the at least one activation mode corresponds to a user operation instruction;
  • the processor is further configured to:
  • the recording mode is switched from the second recording mode to the first recording mode.
  • the terminal first receives the recording start command, and starts the first recording mode according to the recording start command to perform the first image data acquisition to obtain the first recording screen. And determining, according to the first image data, whether the first video frame includes the first gesture, and if the first video frame includes the first gesture, The terminal recording mode is switched from the first recording mode to the second recording mode, and the second image data is collected in the second recording mode to obtain a second recording screen. Finally, determining whether the second video screen includes a human face, and if the second video screen includes the human face, performing facial processing on the second video screen, if the second video screen does not include The above-mentioned face is subjected to beautification processing on the second video screen.
  • the embodiment of the present application can increase the diversity of the video picture format obtained by the video application, improve the viewability of the video picture, and improve the user experience.
  • FIG. 1 is a schematic flow chart of a video recording method according to an embodiment of the present application.
  • FIG. 2 is a schematic structural diagram of a video recording apparatus according to an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a terminal according to an embodiment of the present application.
  • the terminal provided by the embodiment of the present application may include: a mobile phone, a computer (including a desktop computer and a notebook computer with a camera), a tablet computer, and the like having a recording function.
  • a mobile phone including a desktop computer and a notebook computer with a camera
  • a tablet computer including a desktop computer and a notebook computer with a camera
  • the above devices are merely examples, and are not exhaustive, including but not limited to the above devices.
  • FIG. 1 is a schematic flowchart diagram of an embodiment of a video recording method according to an embodiment of the present application.
  • the method described in the embodiment of the present application can be implemented by using a device having a photographing function, such as a mobile phone or a computer, and the terminal is an execution subject in the embodiment of the present application.
  • the photographing method described in the embodiment of the present application includes the steps of:
  • S101 Receive a recording start command, and start a first recording mode according to the recording start command to perform acquisition of the first image data to obtain a first recording screen.
  • the camera function and the recording function in the terminal are usually integrated into the same target application.
  • the camera in the mobile application has both the recording function and the photographing function. Therefore, before the terminal receives the recording start command, the user may be required to open a target application (such as a camera) in the terminal, and select a function of the target application as a recording function.
  • a target application such as a camera
  • the terminal may obtain a user operation instruction by detecting a click of the user on any area in the main interface of the terminal, and determine, according to the preset instruction set of the terminal, whether the terminal function corresponding to the user operation instruction is a target.
  • the application is open. If the function corresponding to the user operation instruction is the opening of the target application, then It is determined that the user operation instruction is an instruction to open the target application.
  • the instruction set preset by the terminal includes a correspondence between at least one set of user operation instructions and terminal functions.
  • the terminal may determine, according to the instruction set, that the terminal function corresponding to the user operation instruction is to start the camera, and It is determined that the user operation instruction is an application open instruction.
  • the terminal may also obtain a user operation instruction by detecting a pressing (and/or touch) of a physical button (and/or a virtual button) provided by the user to the terminal.
  • the terminal may obtain a user operation instruction by detecting that the user presses the physical volume button in the terminal for a long time, and may determine the terminal function corresponding to the user operation instruction according to the preset instruction set of the terminal.
  • the target application is opened, it is determined that the user operation instruction is an instruction to open the target application.
  • the embodiments of the present application can improve the diversity and interest of the startup mode of the target application, and the applicability is stronger.
  • the prompt information of the user identity information verification may be displayed on the main interface of the terminal, where the prompt information is used to request the user to perform identity information verification.
  • the method for verifying the identity information of the user may include password verification, fingerprint verification, face recognition verification, and iris recognition verification, which are not limited herein.
  • the terminal may display a plurality of function options in the target application interface, and the foregoing function options may include a recording function option, a photographing function option, and the like, which are not limited herein.
  • the terminal obtains different user operation instructions by detecting a click of the user on the function option, and determines whether the terminal function corresponding to the obtained user operation instruction is the selection of the recording function according to the preset instruction set.
  • the preset instruction set is the same instruction set as the preset instruction set, and details are not described herein again.
  • the terminal displays 2 function options in the target application interface, including recording function options and camera function options.
  • a user operation instruction may be acquired, and the terminal function corresponding to the user operation instruction may be determined according to the preset instruction set as the selection of the camera function. If it is detected that the user clicks the recording function option, another user operation instruction may be acquired, and the terminal function corresponding to the user operation instruction may be determined according to the preset instruction set as the selection of the recording function.
  • the terminal determines that the terminal function corresponding to the acquired user operation instruction is the selection of the recording function, the default recording mode of the target application is started, and the first image data is acquired by the terminal camera and the first video is obtained.
  • the above default recording mode can be set to the first recording mode.
  • the terminal may obtain camera type information and photo rotation information before acquiring the first image data. It is determined by the camera type information whether the front camera or the rear camera is used when the terminal performs recording. If the front camera is used, the image data collected by the terminal camera can be mirrored. If the rear camera is used, the image acquisition operation is not required.
  • the video rotation information is used to determine whether the lens is rotated when the user uses the terminal to record. For example, if the user performs horizontal shooting when using the terminal for recording, it can be determined that the user has rotated the lens, and if the user uses the terminal to perform vertical recording when recording, the user does not rotate the lens. If the user rotates the lens, the environment image data collected by the terminal can be rotated, otherwise the rotation operation is not required.
  • the terminal can collect the camera
  • the obtained image data is subjected to one or more processing operations in image acquisition or rotation processing to obtain the first image data described above.
  • the purpose of the above image capturing operation and rotation operation is to make the video image obtained by the recording more suitable for human eyes to view.
  • the camera application After the camera application is opened, it detects and determines whether the user clicks the recording button in the camera application interface. If the determination is yes, the default no-effect recording mode (ie, the first recording mode) of the camera application is turned on, and the mobile phone is used.
  • the front camera or the rear camera collects and processes the environmental image data to obtain the first image data.
  • the image image processing and the rotation processing are performed on the environment image data to obtain a video screen (ie, the first video recording screen) without special effects.
  • the terminal may prompt the user to select a startup mode of the second recording mode different from the first recording mode.
  • the terminal may display multiple startup mode options in the recording function interface, where the startup mode options may include gesture activation, touch activation, and the like, which are not limited herein.
  • the terminal can obtain the option of the user clicking from the recording function interface, and determine the startup mode corresponding to the option clicked by the user as the startup mode of the second recording mode. For example, after acquiring the first video screen, two preset second video mode startup options are provided in the video application interface, including gesture activation and touch activation. The option of detecting the click of the user is detected. If the option clicked by the user is the gesture start option, it is determined that the second recording mode startup mode is the gesture start.
  • the terminal may prompt the user to press (and/or touch) the physical button (and/or the virtual button) provided by the terminal in the recording function interface to select the second recording mode startup mode.
  • the user is prompted to select the second recording mode by long pressing the volume key to start the gesture.
  • the terminal determines the second recording mode startup mode, it is determined whether the startup mode selected by the user is a gesture activation mode. If the activation mode of the second recording mode selected by the user is a gesture start, it is determined by an image processing method whether the first gesture is included in the first recording screen.
  • the first gesture is a special gesture that is easy for the user to implement and easy for the terminal to recognize. For example, open your fingers and make a fist, or use your index finger to draw a closed circle in the air, or use your fingers to make a V-shaped gesture.
  • the above image processing method may include image feature extraction, human body gesture recognition, image stitching, and the like, which are not limited herein.
  • the terminal extracts each frame image in the first video frame in the preset time period, and performs feature extraction on each frame image to detect whether a specific gesture exists in the image. If it is detected that the multi-frame image contains a specific gesture, it is determined that there is a specific gesture in the first video frame.
  • the position of the human finger is extracted from the multi-frame image, and the multi-frame image is image-spliced, and whether the position of the finger constitutes a specific gesture action is determined according to the splicing result. If the determination is yes, it is determined that there is a specific gesture in the first video recording screen.
  • a first video frame segment having a duration of 5 s in the first video frame is extracted and decomposed into image frames, and feature extraction is performed on each frame image to detect whether a V-shaped gesture exists in the image. If it is determined that the multi-frame image in each of the frame images has a V-shaped gesture, it is determined that there is a specific gesture in the first video recording, and the specific gesture is the first gesture.
  • the terminal recording mode is switched from the first recording mode to the second recording mode, and the second image data is collected in the second recording mode to obtain a second recording screen.
  • the terminal determines that the first video frame includes the first gesture, and then switches the terminal recording mode from the first recording mode without the special effect to the second recording mode, and in the second recording mode.
  • the second image data is collected by the terminal camera to obtain a second video frame.
  • the environment image data collected by the terminal camera is processed to obtain second image data, and the second image data is obtained by performing splicing processing on the second image data.
  • the target application channel is switched to a default program stream that does not contain a third-party algorithm such as beauty, image beautification, etc., to include beauty, image beautification in the background.
  • the function program stream of the third-party algorithm is used to perform second image data acquisition by the terminal camera in the second recording mode to obtain the second video image.
  • the environment image data collected by the terminal camera may be preprocessed according to the terminal device information to obtain the second image data, and then the second video image is obtained by splicing the second image data, and the second video is recorded.
  • the recording mode of the terminal is triggered by the gesture, the operation is more convenient, the switching efficiency of the terminal recording mode is higher, the interest of the terminal recording is improved, and the user experience of the terminal is improved.
  • step S104 Determine whether the second video screen includes a human face. If the determination is yes, execute step S105; otherwise, execute step S106.
  • the terminal may process the second image data by using an image processing method to determine whether the second video frame includes a human face. If there is a face on the second video screen, the face is subjected to a beauty treatment, and if the second video screen does not include a face, the second video screen is beautified.
  • the terminal may process the second image data by using an image processing method to determine whether the second video frame includes a human face. If there is a face on the second video screen, the face is subjected to a beauty treatment, and if the second video screen does not include a face, the second video screen is beautified.
  • the terminal extracts each frame image in the second video frame in the preset time period, and determines whether there is a human face in each frame image by using a face recognition algorithm, and further determines if a face exists in the image.
  • the face is subjected to a beauty treatment by a corresponding image processing method.
  • the above-mentioned beauty treatment may include one or more of face-lifting treatment, skin-beautifying treatment, facial features enhancement processing, or animation effect addition processing.
  • the above-mentioned beauty treatment is only an example, not an exhaustive one, and is not limited herein.
  • the above-described skin treatment includes color enhancement processing of the skin of a human face using image enhancement technology to achieve an effect of brightening the skin.
  • image enhancement processing is used to enlarge the eyes in the face, and the nose in the face is improved, and finally the effect of the facial features is enhanced.
  • the image enhancement processing is performed on each of the frame images, and the beautification processing may include a filter effect addition, a picture sharpening, and the like, which is not limited herein.
  • image processing technology is used to adjust the color of each frame image, so that the color of each frame image tends to be warm, and the image warming function is realized, and finally the warming effect of the video image is realized.
  • the second screen is beautified, otherwise Make a face treatment on the face contained in the second video screen.
  • the above-mentioned beauty treatment and the above-mentioned beautification treatment are the same as above, and will not be described here.
  • the second video screen has a special display effect, improves the viewability of the video screen, and improves the user experience of the terminal.
  • the terminal may detect whether the second video recording is present.
  • the method for determining whether the first gesture has a second gesture is the same as the method for determining whether the first gesture is included in the first recording screen in the foregoing step S102, and details are not described herein again. If the terminal detects that the second gesture exists in the second video recording mode, the current recording mode of the terminal is switched from the second recording mode to the first recording mode, so that the terminal recording can be performed in the normal mode, thereby saving power consumption of the terminal. It also improves the variety of switching modes of the terminal recording mode, and the operation is more flexible.
  • the implementation manner of the method for switching the recording mode of the terminal is the same as the implementation of the method for switching the recording mode in step S103, and details are not described herein again.
  • the terminal first receives the recording start command, and starts the first recording mode according to the recording start command to perform the first image data acquisition to obtain the first recording screen. And determining, according to the first image data, whether the first video frame includes the first gesture, and if the first video signal includes the first gesture, switching the terminal recording mode from the first recording mode to the second recording And acquiring the second image data in the second recording mode to obtain the second video image. Finally, determining whether the second video screen includes a human face, and if the second video screen includes the human face, performing facial processing on the second video screen, if the second video screen does not include The above-mentioned face is subjected to beautification processing on the second video screen.
  • the embodiment of the present application can increase the diversity of the video picture format obtained by the video application, improve the viewability of the video picture, and improve the user experience.
  • FIG. 2 is a schematic structural diagram of a video recording apparatus according to an embodiment of the present application.
  • the image processing apparatus described in this embodiment of the present application includes:
  • the recording unit 10 is configured to receive a recording start command, and start the first recording mode according to the recording start command to acquire the first image data to obtain the first recording screen.
  • the gesture recognition unit 20 is configured to determine, according to the first image data collected by the recording unit, whether the first video is included in the first video recording.
  • the mode switching unit 30 is configured to switch the terminal recording mode from the first recording mode to the second recording mode when the gesture recognition unit recognizes that the first video is included in the first video recording mode.
  • the recording unit 10 is further configured to perform second image data acquisition in the second recording mode to obtain a second video recording.
  • the screen processing unit 40 is configured to determine whether the second video screen includes a human face, and if the second video recording screen includes the human face, perform beauty on the human face in the second video recording screen. Processing, if the second video screen does not include the human face, the second video screen is beautified.
  • the gesture recognition unit 20 is configured to:
  • At least one activation mode corresponding to the second recording mode where the at least one startup mode includes a gesture start, and each of the at least one startup mode corresponds to a user operation instruction
  • Obtaining a user operation instruction if the obtained startup mode corresponding to the user operation instruction is a gesture start, detecting whether the first gesture is included in the first video recording.
  • the gesture recognition unit 20 is further configured to:
  • the mode switching unit 30 is further configured to:
  • the terminal is The end recording mode is switched from the second recording mode to the first recording mode.
  • the image processing unit 40 is configured to:
  • An animation effect adding process is performed on the face in the second recording screen.
  • the picture processing unit 40 is further configured to:
  • the second video frame acquired by the video recording unit 10 includes the human face, and the number of the human faces is equal to or greater than a preset threshold, the second video frame is beautified.
  • the recording unit 10 can obtain a user operation instruction by detecting a user click on any area in the main interface of the terminal, and determine, according to the instruction set preset by the terminal, whether the terminal function corresponding to the user operation instruction is a target.
  • the application is open. If the function corresponding to the user operation instruction is the opening of the target application, it is determined that the user operation instruction is an open command of the target application.
  • the instruction set preset by the terminal includes a correspondence between at least one set of user operation instructions and terminal functions.
  • the terminal function corresponding to the user operation instruction may be determined according to the instruction set to start the camera. And can determine that the user operation instruction is an application open instruction.
  • the recording unit 10 can also obtain a user operation instruction by detecting a pressing (and/or touch) of a physical button (and/or a virtual button) provided by the user to the terminal.
  • a user operation instruction by detecting that the user presses the volume button in the terminal for a long time, and can determine the terminal corresponding to the user operation instruction according to the preset instruction set of the terminal. The function is turned on for the target application, and it is determined that the user operation instruction turns on the instruction for the target application.
  • the prompt information of the user identity information verification may be displayed on the terminal main interface, where the prompt information is used to request the user to perform identity information verification.
  • the method for verifying the identity information of the user may include password verification, fingerprint verification, face recognition verification, and iris recognition verification, which are not limited herein.
  • the above target application is opened.
  • the video recording unit 10 prompts the user to perform identity information verification in the terminal main interface, and the identity information verification mode may be fingerprint verification. After detecting that the user's fingerprint recognition result is true, the above target application is opened.
  • the recording unit 10 may prompt the user to select the application function of the target application.
  • a plurality of function options may be displayed in the target application interface, and the function options may include a recording function option, a photographing function option, and the like, which are not limited herein.
  • the recording unit 10 obtains different user operation commands by detecting a click of the function option by the user, and determines, according to the preset instruction set, whether the terminal function corresponding to the user operation instruction is a selection of a recording function, wherein the preset The instruction set is the same instruction set as the above-mentioned preset instruction set, and will not be described here.
  • the above-described recording unit 10 displays two function options on the target application interface, including a recording function option and a photographing function option. If it is detected that the user clicks the camera function option, a user operation instruction may be acquired, and the terminal function corresponding to the user operation instruction may be determined according to the preset instruction set as the selection of the camera function. If it is detected that the user clicks the recording function option, another user operation instruction different from the above user operation instruction may be acquired, and The terminal function corresponding to the user operation instruction is determined according to the preset instruction set as the selection of the recording function.
  • the recording unit 10 determines that the terminal function corresponding to the acquired user operation instruction is the selection of the recording function, the recording unit 10 starts the default recording mode of the target application, and collects the first image data through the terminal camera to obtain the first recording. Picture.
  • the above default recording mode can be set to the first recording mode.
  • the video recording unit 10 may acquire camera type information and camera rotation information before acquiring the first image data. It is determined by the camera type information whether the front camera or the rear camera is used when the terminal performs recording. If the front camera is used, the image data collected by the terminal camera can be mirrored. If the rear camera is used, the image acquisition operation is not required.
  • the video rotation information is used to determine whether the lens is rotated when the user uses the terminal to record. For example, if the user performs horizontal shooting when using the terminal for recording, it can be determined that the user has rotated the lens, and if the user uses the terminal to perform vertical recording when recording, the user does not rotate the lens. If the user rotates the lens, the environment image data collected by the terminal can be rotated, otherwise the rotation operation is not required.
  • the recording unit 10 can perform one or more processing operations of image acquisition or rotation processing on the image data collected by the camera to obtain the first image data. The purpose of the above image capturing operation and rotation operation is to make the video image obtained by the recording more suitable for human eyes to view.
  • the recording unit 10 detects and determines whether the user clicks the recording button in the camera application interface. If the determination is yes, the default no-effect recording mode of the camera application is turned on, and the front of the mobile phone is used.
  • the camera or the rear camera collects and processes the environmental image data.
  • the image data is mirrored and processed and rotated to obtain a video screen without special effects.
  • the gesture recognition unit 20 may prompt the user to select a startup mode of the second recording mode different from the first recording mode.
  • the gesture recognition unit 20 may display a plurality of startup mode options in the recording function interface, wherein the startup mode option may include a gesture activation, a touch activation, and the like, which are not limited herein.
  • the gesture recognition unit 20 can obtain the option of the user click from the recording function interface, and determine the startup mode corresponding to the option clicked by the user as the startup mode of the second recording mode. For example, after the first recording screen is acquired by the recording unit 10, the gesture recognition unit 20 provides two preset second recording mode startup options, including gesture activation and touch activation, in the recording application interface. The option of detecting the click of the user is detected. If the option clicked by the user is the gesture start option, it is determined that the second recording mode startup mode is the gesture start.
  • the gesture recognition unit 20 may prompt the user to press (and/or touch) the physical button (and/or the virtual button) provided by the terminal in the recording function interface to select the second recording mode activation mode.
  • the gesture recognition unit 20 may prompt the user to select the second recording mode activation mode to start the gesture by long pressing the volume key in the recording function interface.
  • the gesture recognition unit 20 After the gesture recognition unit 20 prompts the user to select the second recording mode startup mode, it can be determined whether the startup mode selected by the user is the gesture activation mode. If the activation mode of the second recording mode selected by the user is the gesture activation, the gesture recognition unit 20 determines, by the image processing method, whether the first video captured by the recording unit 10 includes the first gesture.
  • the first gesture is a special gesture that is easy for the user to implement and easy for the terminal to recognize. For example, open your fingers and make a fist, or use your index finger to draw a closed circle in the air, or use your fingers to make a V-shaped gesture.
  • the above image processing method may include image feature extraction, human body gesture recognition, image stitching, and the like, which are not limited herein.
  • the gesture recognition unit 20 extracts the first record acquired by the recording unit 10 in the preset time period. For each frame image in the picture, feature extraction is performed on each frame image, and it is detected whether or not a specific gesture exists in the image. If it is detected that the multi-frame image contains a specific gesture, it is determined that there is a specific gesture in the first video frame.
  • the gesture recognition unit 20 extracts a first video frame segment having a duration of 5 s in the first video frame acquired by the video recording unit 10, and decomposes it into frame images, and performs feature extraction on each frame image to detect the image. Whether there is a V-shaped gesture, if it is determined that a multi-frame image in each of the above-mentioned frames has a V-shaped gesture, it is determined that there is a specific gesture in the first recorded image, and the specific gesture is the first gesture.
  • the mode switching unit 30 sets the channel of the target application in the background by a third-party algorithm that does not contain beauty, image beautification, and the like.
  • the default program flow switches to a stream of functional programs that contain third-party algorithms such as beauty and image beautification.
  • the recording unit 10 After the mode switching unit 30 performs the terminal recording mode switching, the recording unit 10 performs the second image data acquisition by the terminal camera in the second recording mode to obtain the second recording screen.
  • the second image data in the second recording mode to obtain the second video image refer to the implementation manner of acquiring the first image data in the first recording mode to obtain the first video image, as described in step S101. I will not repeat them here.
  • the image processing unit 40 extracts each frame image in the second video frame acquired by the video recording unit 10 in the preset time period, and determines whether there is a human face in each frame image by using a face recognition algorithm, and if the image is determined in the image In the presence of a human face, the position and size of each face and the positional information of each major facial organ and the number of faces are further determined. And the facial treatment of the above face is performed by a corresponding image processing method.
  • the above-mentioned beauty treatment may include one or more of face-lifting treatment, skin-beautifying treatment, facial features enhancement processing, or animation effect addition processing.
  • the above-mentioned beauty treatment is only an example, and is not exhaustive, and is not limited herein.
  • the above-mentioned skin treatment performs color enhancement processing on the skin of a human face to achieve an effect of brightening the skin.
  • the image cropping and splicing technique is used to enlarge the eyes in the face, and the nose in the face is improved, and finally the effect of the facial features is enhanced.
  • the image enhancement processing is performed on each of the frame images, and the beautification processing may include a filter effect addition, a picture sharpening, and the like, which is not limited herein.
  • image processing technology is used to adjust the color of each frame image, so that the color of each frame image tends to be warm, and the image warming function is realized, and finally the warming effect of the video image is realized.
  • the image processing unit 40 continues to determine whether the number of the face is greater than a preset threshold. If the determination is yes, The second screen is beautified, otherwise the face included in the second video screen is separately processed.
  • the above-mentioned beauty treatment and the above-mentioned beautification treatment are the same as above, and will not be described here. Through the above-mentioned beauty treatment and beautification processing, the second video screen has a special display effect.
  • the image processing unit 40 may detect whether the second gesture has a second gesture that is significantly different from the first gesture, and the implementation manner of the determining method In the above step S102, it is determined whether the first video frame includes the first gesture, and details are not described herein. If the terminal detects that the second gesture exists in the second video recording, the mode switching unit 30 switches the current recording mode of the terminal from the second recording mode to the first recording mode, where the terminal recording mode switching method is implemented. The implementation manner of the recording mode switching method in step S103 is the same, and details are not described herein again.
  • the terminal first receives a video start command, and starts the first video according to the video start command.
  • the mode performs acquisition of the first image data to obtain a first video frame.
  • the embodiment of the present application can increase the diversity of the video picture format obtained by the video application, improve the viewability of the video picture, and improve the user experience.
  • FIG. 3 is a schematic structural diagram of a terminal according to an embodiment of the present disclosure.
  • the terminal described in this embodiment may include a transceiver 100, a memory 200, and a processor 300.
  • the transceiver 100, the memory 200, and the processor 300 are connected by a bus;
  • the memory 200 is configured to store a set of program codes
  • the processor 300 and the transceiver 100 are configured to call program code stored in the memory 200, and perform the following operations:
  • the transceiver 100 is configured to receive a video start command.
  • the processor 300 is configured to start the first recording mode according to the receiving of the recording start command by the transceiver 100;
  • the transceiver 100 is further configured to perform collecting of the first video data in the first recording mode initiated by the processor 300 to obtain a first video recording screen;
  • the processor 300 is further configured to determine, according to the first image data collected by the transceiver 100, whether the first video frame includes a first gesture, and if the first video frame includes the first gesture, The terminal recording mode is switched from the first recording mode to the second recording mode;
  • the transceiver 100 is further configured to perform second image data acquisition in the second recording mode initiated by the processor 300 to obtain a second video recording screen;
  • the processor 300 is further configured to determine whether the second video frame collected by the transceiver 100 includes a human face, and if the second video frame includes the human face, the second video frame is The face is subjected to a beauty treatment, and if the face is not included in the second video screen, the second video frame is beautified.
  • the processor 300 is configured to:
  • An animation effect adding process is performed on the face in the second video frame collected by the transceiver 100.
  • the processor 300 is further configured to:
  • the second video frame collected by the transceiver 100 includes the human face, and the number of the faces is equal to or greater than a preset threshold, the second video frame is beautified.
  • the processor 300 is further configured to:
  • At least one activation mode corresponding to the second recording mode, where the at least one activation mode includes a gesture start, and each of the at least one activation mode corresponds to a user operation instruction;
  • the processor 300 is further configured to:
  • the transceiver 100 may include a touch panel, a fingerprint sensor (for collecting fingerprint information of the user and direction information of the fingerprint), a microphone, a display (LCD, etc.), a speaker, and the like.
  • the memory 200 can include read only memory and random access memory and provides instructions and data to the processor 300. A portion of the memory 200 can also include a non-volatile random access memory. For example, the memory 200 can also store information of a device type.
  • the processor 300 may be a central processing unit (CPU), and the processor may be another general-purpose processor, a digital signal processor (DSP), or an application specific integrated circuit (ASIC). , Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the transceiver 100, the memory 200, and the processor 300 described in the embodiment of the present application may implement the implementation manners described in the steps of the video recording method provided by the embodiment of the present application, and may also be implemented in the embodiment of the present application.
  • the video recording device refer to the implementations described in the foregoing embodiments, and details are not described herein.

Abstract

本申请实施例公开了一种拍照方法、装置及终端，该方法包括：接收录像启动指令，并根据录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面；根据第一图像数据判断第一录像画面中是否包含第一手势，若第一录像画面中包含第一手势，则将终端录像模式由第一录像模式切换至第二录像模式，并在第二录像模式下进行第二图像数据的采集以得到第二录像画面；判断第二录像画面中是否包含人脸，若第二录像画面中包含人脸，则对第二录像画面中的人脸进行美颜处理，若第二录像画面中不包含人脸，则对第二录像画面进行美化处理。采用本申请实施例，具有增加录像应用获取视频画面的形式多样性，提高视频画面的可观赏性，提升用户体验的优点。

Description

一种录像方法、装置及终端 技术领域
本申请涉及图像数据处理领域，尤其涉及一种录像方法、装置及终端。
背景技术
随着科学技术的不断发展，除了照相机以外，各种终端如智能手机、掌上电脑或可穿戴设备等，也安装了摄像头，也能提供拍照和录像功能，可使用户随时随地的记录并分享周围的景色。终端的各方面性能在不断地提高，这使得拍照和录像功能有了朝更多方向拓展的可能性。同时，这也使得终端用户对终端录像应用的体验要求越来越高。
现有技术中，一般情况下终端的录像应用只能进行简单的录像，并没有对录像画面进行进一步的处理，使得录像应用获取的视频画面形式单一，可观赏性低，用户的体验效果差。
发明内容
本申请实施例提供了一种录像方法、装置及终端，可增加录像应用获取的视频画面的形式多样性，提高视频画面的可观赏性，提升用户体验效果。
第一方面提供了一种录像方法，其可包括：
接收录像启动指令，并根据所述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面；
根据所述第一图像数据判断所述第一录像画面中是否包含第一手势；
若所述第一录像画面中包含所述第一手势，则将终端录像模式由所述第一录像模式切换至第二录像模式，在所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
判断所述第二录像画面中是否包含人脸；
若所述第二录像画面中包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面中不包含所述人脸，则对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述对所述第二录像画面中的所述人脸进行美颜处理包括：
对所述第二录像画面中的所述人脸进行瘦脸处理；或者
对所述第二录像画面中的所述人脸进行美肤处理；或者
对所述第二录像画面中的所述人脸进行五官增强处理；或者
对所述第二录像画面中的所述人脸进行动画效果添加处理。
在一些可能的实现方式中，所述方法还包括：
若所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值，则对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述根据所述第一图像数据判断所述第一录像画面中是否包含第一手势包括：
设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动， 所述至少一种启动方式中每种启动方式对应一种用户操作指令；
获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
在一些可能的实现方式中，所述将终端录像模式由所述第一录像模式切换至第二录像模式之后，所述方法还包括：
根据所述第二图像数据判断所述第二录像画面中是否包含第二手势，若所述第二录像画面中包含所述第二手势，则将所述终端录像模式由所述第二录像模式切换至所述第一录像模式。
第二方面提供了一种录像装置，其可包括：
录像单元，用于接收录像启动指令，并根据所述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面；
手势识别单元，用于根据所述录像单元采集的所述第一图像数据判断所述第一录像画面中是否包含第一手势；
模式切换单元，用于当所述手势识别单元识别确定所述第一录像画面中包含所述第一手势时，将终端录像模式由所述第一录像模式切换至第二录像模式；
所述录像单元，还用于在所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
画面处理单元，用于判断所述第二录像画面中是否包含人脸，若所述第二录像画面包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面不包含所述人脸，则对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述画面处理单元用于：
对所述第二录像画面中的所述人脸进行瘦脸处理；或者
对所述第二录像画面中的所述人脸进行美肤处理；或者
对所述第二录像画面中的所述人脸进行五官增强处理；或者
对所述第二录像画面中的所述人脸进行动画效果添加处理。
在一些可能的实现方式中，所述画面处理单元还用于：
当所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值时，对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述手势识别单元用于：
设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动，所述至少一种启动方式中每种启动方式对应一种用户操作指令；
获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
在一些可能的实现方式中，所述手势识别单元，还用于：
根据所述录像单元采集的所述第二图像数据判断所述第二录像画面中是否包含第二手势；
所述模式切换单元，还用于：
在所述手势识别单元确定得到所述第二录像画面中包含所述第二手势时，将所述终端 录像模式由所述第二录像模式切换至所述第一录像模式。
第三方面提供了一种终端，其可包括存储器、处理器和收发器；
所述存储器、处理器和收发器通过总线连接；
所述存储器用于存储一组程序代码；
所述处理器和所述收发器用于调用所述存储器中存储的程序代码，执行如下操作：
所述收发器，用于接收录像启动指令；
所述处理器，用于根据所述收发器接收到所述录像启动指令启动第一录像模式；
所述收发器，还用于在所述处理器启动的所述第一录像模式下进行第一录像数据的采集以得到第一录像画面；
所述处理器，还用于根据所述收发器采集的所述第一图像数据判断所述第一录像画面中是否包含第一手势，若所述第一录像画面中包含所述第一手势，则将终端录像模式由所述第一录像模式切换至第二录像模式；
所述收发器，还用于在所述处理器启动的所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
所述处理器，还用于判断所述收发器采集的所述第二录像画面中是否包含人脸，若所述第二录像画面中包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面中不包含所述人脸，则对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述处理器用于：
对所述收发器采集的所述第二录像画面中的所述人脸进行瘦脸处理；或者
对所述收发器采集的所述第二录像画面中的所述人脸进行美肤处理；或者
对所述收发器采集的所述第二录像画面中的所述人脸进行五官增强处理；或者
对所述收发器采集的所述第二录像画面中的所述人脸进行动画效果添加处理。
在一些可能的实现方式中，所述处理器还用于：
当所述收发器采集的所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值时，对所述第二录像画面进行美化处理。
在一些可能的实现方式中，所述处理器还用于：
设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动，所述至少一种启动方式中每种启动方式对应一种用户操作指令；
获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
在一些可能的实现方式中，所述处理器还用于：
根据所述收发器采集的所述第二图像数据判断所述第二录像画面中是包含第二手势，在确定所述第二录像画面中包含所述第二手势之后，将所述终端录像模式由所述第二录像模式切换至所述第一录像模式。
实施本申请实施例，具有如下有益效果：
在本申请实施例中，终端首先接收录像启动指令，并根据上述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面。然后，根据上述第一图像数据判断上述第一录像画面中是否包含第一手势，若上述第一录像画面中包含上述第一手势，则 将终端录像模式由上述第一录像模式切换至第二录像模式，并在上述第二录像模式下进行第二图像数据的采集以得到第二录像画面。最后判断上述第二录像画面中是否包含人脸，若该第二录像画面中包含上述人脸，则对该第二录像画面中的人脸进行美颜处理，若该第二录像画面中不包含上述人脸，则对该第二录像画面进行美化处理。采用本申请实施例可增加录像应用获取的视频画面形式的多样性，提高视频画面的可观赏性，提升用户体验效果。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍。显而易见的，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种录像方法的流程示意图；
图2是本申请实施例提供的一种录像装置的结构示意图；
图3是本申请实施例提供的一种终端的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明的实施例，本领域的普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本发明的保护范围。
具体实现中，本申请实施例提供的终端可包括：手机、电脑(包括带有摄像头的台式机和笔记本电脑)、平板电脑等具备录像功能的设备。上述设备仅是举例，而非穷举，包含但不限于上述设备。
下面将结合图1至图3对本申请实施例提供的录像方法、装置及终端进行具体描述。
参见图1，是本申请实施例提供的录像方法的实施例流程示意图。本申请实施例所描述的方法可用手机、电脑等具有拍照功能的设备实现，其中，对本申请实施例以终端为执行主体进行描述。本申请实施例中所描述的拍照方法，包括步骤：
S101，接收录像启动指令，并根据上述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面。
在一些可行的实施方式中，终端中的拍照功能和录像功能通常情况下会被集成在同一个目标应用程序中，例如，手机应用程序中的相机就同时具有录像功能和拍照功能。因此在终端接收录像启动指令之前，可需要用户开启终端中的目标应用程序(例如相机)，并选定该目标应用程序的功能为录像功能。
具体的，终端在获取上述录像启动指令之前，可通过检测用户对终端主界面中任意区域的点击来获取用户操作指令，根据终端预设的指令集判断该用户操作指令对应的终端功能是否为目标应用程序的开启。若该用户操作指令对应的功能为目标应用程序的开启，则 确定该用户操作指令为目标应用程序开启指令。其中，终端预设的指令集中包括至少一组用户操作指令与终端功能之间的对应关系。例如，终端在获取录像启动指令之前，检测到用户点击手机界面中相机的图标时所触发产生的用户操作指令，则可根据上述指令集确定该用户操作指令对应的终端功能为启动相机，并可确定该用户操作指令为应用程序开启指令。
可选的，终端还可以通过检测用户对终端所具备的物理按键(和/或虚拟按键)的按压(和/或触控)来获取用户操作指令。例如，终端在获取录像启动指令之前，可通过检测到用户对终端中的实体音量按键进行长时间的按压来获取用户操作指令，可根据终端预设的指令集确定该用户操作指令对应的终端功能为目标应用程序开启，则确定该用户操作指令为目标应用程序开启指令。本申请实施例可提高目标应用程序的启动方式的多样性和趣味性，适用性更强。
可选的，若终端确定上述用户操作指令为目标应用程序开启指令，还可在终端主界面上显示用户身份信息验证的提示信息，该提示信息用于请求用户进行身份信息验证。其中，用户身份信息验证的方式可包括密码验证、指纹验证、人脸识别验证、虹膜识别验证等，具体此处不做限定。当检测到用户通过身份信息验证后，开启上述目标应用程序。例如，终端获取目标应用程序开启指令后，在终端主界面中提示用户进行身份信息验证，身份信息验证方式可为指纹验证。在检测到用户的指纹识别结果为真后，开启上述目标应用程序，提高了目标应用程序的启动的安全性。
终端开启上述目标应用程序后，可提示用户进行该目标应用程序的应用功能的选择。终端可在该目标应用程序界面显示多个功能选项，上述功能选项可包括录像功能选项、拍照功能选项等，此处不作限定。终端通过检测用户对上述功能选项的点击来获取不同的用户操作指令，并根据预设的指令集判断获取的用户操作指令对应的终端功能是否为录像功能的选取。其中，该预设的指令集与上述预设的指令集为同一指令集，此处不再赘述。例如，终端在目标应用程序界面显示2个功能选项，包括录像功能选项和拍照功能选项。若检测到用户点击了拍照功能选项，则可获取一个用户操作指令，并可根据预设的指令集确定该用户操作指令对应的终端功能为拍照功能的选取。若检测到用户点击了录像功能选项，则可获取又一个用户操作指令，并可根据预设的指令集确定该用户操作指令对应的终端功能为录像功能的选取。
当终端确定获取的用户操作指令对应的终端功能为录像功能的选取，则开启上述目标应用程序默认的录像模式，通过终端摄像头采集第一图像数据并得到第一录像画。为方便描述，上述默认的录像模式可设定为第一录像模式。
可选的，终端在获取第一图像数据之前，可获取摄像头类型信息和拍照旋转信息。通过摄像头类型信息确定终端进行录像时使用的是前置摄像头还是后置摄像头。若使用的是前置摄像头，则可对终端摄像头采集到的图像数据进行镜像获取操作，若使用的是后置摄像头，则可不需要镜像获取操作。通过录像旋转信息确定用户使用终端进行录像时是否旋转了镜头。例如，若用户使用终端进行录像时是横向拍摄，则可确定用户旋转了镜头，若用户使用终端进行录像时是竖向拍摄，则用户没有旋转镜头。若用户旋转了镜头，则可对终端采集到的环境图像数据进行旋转操作，否则可不需要旋转操作。终端可对摄像头采集 到的图像数据进行镜像获取或旋转处理中的一种或多种处理操作，以得到上述第一图像数据。上述镜像获取操作和旋转操作的目的在于使得录像得到的视频画面更适于人眼观看。
例如，开启相机应用程序后，检测并判断用户是否点击了相机应用界面中的录像按钮，若判断为是，则开启相机应用程序默认的无特效录像模式(即第一录像模式)，并通过手机的前置摄像头或者后置摄像头进行环境图像数据的采集及处理以得到第一图像数据。可选的，手机通过摄像头采集环境图像数据之后，对环境图像数据进行镜像获取处理及旋转处理等处理之后可得到不含特效的录像画面(即第一录像画面)。
S102，根据上述第一图像数据判断上述第一录像画面中是否包含第一手势，若判断为是，则执行步骤S103。
在一些可行的实施方式中，终端得到上述第一录像画面后，可提示用户进行与上述第一录像模式不同的第二录像模式的启动方式的选择。终端可在录像功能界面中显示多个启动方式选项，其中，上述启动方式选项可包括手势启动、触控启动等，此处不做限定。终端可从录像功能界面上获取用户点击的选项，并将用户点击的选项对应的启动方式确定为第二录像模式的启动方式。例如，在获取第一录像画面后，在录像应用界面中提供2个预设的第二录像模式启动选项，包括手势启动和触控启动。检测用户点击的选项，若用户点击的选项为手势启动选项，则确定上述第二录像模式启动方式为手势启动。
可选的，终端可在录像功能界面中提示用户对终端所具备的物理按键(和/或虚拟按键)进行按压(和/或触控)来选择第二录像模式启动方式。例如，在录像功能界面中提示用户通过长按音量键选择第二录像模式启动方式为手势启动。
在终端确定上述第二录像模式启动方式后，判断用户选择的启动方式是否为手势启动方式。若用户选择的上述第二录像模式的启动方式为手势启动，则通过图像处理方法判断第一录像画面中是否包含第一手势。其中，上述第一手势为用户易于实现且易于终端识别的特殊性的手势。例如，张开五指再握拳，或者使用食指在空中划出一个闭合的圆形，或者用手指做出V字形手势等。上述图像处理方法可包括图像特征提取、人体姿态识别、图像拼接等方式，此处不做限定。例如，终端提取出预设时间段内的第一录像画面中的各帧图像，并对各帧图像进行特征提取，检测上述图像中是否存在特定手势。若检测出多帧图像中均含有特定的手势，则确定第一录像画面中存在特定手势。可选的，从多帧图像中提取出人体手指的位置，并对该多帧图像进行图像拼接，根据拼接结果判断上述手指的位置是否构成一个特定的手势动作。若判断为是，则确定第一录像画面中存在特定手势。例如，提取出第一录像画面中的时长为5s的第一录像画面片段，并分解成各帧图像，对各帧图像进行特征提取，检测上述图像中是否存在V字形手势。若判断出上述各帧图像中的多帧图像均存在V字形手势，则确定上述第一录像画面中存在特定手势，上述特定手势即为第一手势。
S103，将终端录像模式由上述第一录像模式切换至第二录像模式，在第二录像模式下进行第二图像数据的采集以得到第二录像画面。
在一些可行的实现方式中，终端判断上述第一录像画面中包含第一手势，则将终端录像模式由不含特效的上述第一录像模式切换至上述第二录像模式，并在第二录像模式下通过终端摄像头进行第二图像数据的采集以得到第二录像画面。可选的，根据终端设备信息 对终端摄像头采集的环境图像数据进行处理以得到第二图像数据，再通过对上述第二图像数据进行拼接处理以得到上述第二录像画面。
具体的，当终端确定上述第一录像画面包含上述第一手势后，在后台中将目标应用程序通道由不含有美颜、图像美化等第三方算法的默认程序流切换至含有美颜、图像美化等第三方算法的功能程序流，在第二录像模式下通过终端摄像头进行第二图像数据采集以得到第二录像画面。可选的，可根据终端设备信息对终端摄像头采集的环境图像数据进行预处理，以得到上述第二图像数据，再通过对上述第二图像数据进行拼接得到上述第二录像画面，在第二录像模式下采集第二图像数据以获得第二录像画面的实现方式具体可参见步骤S101中所述的在第一录像模式下采集第一图像数据以获得第一录像画面的实现方式，此处不再赘述。本申请实施例可通过手势触发终端的录像模式的切换，操作更便捷，终端录像模式的切换效率更高，提高了终端录像的趣味性，提升了终端的用户体验。
S104，判断上述第二录像画面中是否包含人脸，若判断为是，则执行步骤S105，否则执行步骤S106。
S105，对上述第二录像画面中的上述人脸进行美颜处理。
S106，对上述第二录像画面进行美化处理。
在一些可能的实现方式中，终端可通过图像处理方法对上述第二图像数据进行处理，以判断第二录像画面中是否包含人脸。若上述第二录像画面中存在人脸，则对上述人脸进行美颜处理，若上述第二录像画面中不包含人脸，则对上述第二录像画面进行美化处理。可选的，在判断出第二录像画面中存在人脸后，继续判断上述人脸的个数是否大于预设个数阈值，若判断为是，则对上述第二画面进行美化处理，否则分别对第二录像画面中包含的人脸进行美颜处理。
具体的，终端提取出预设时间段内的第二录像画面中的各帧图像，并通过人脸识别算法判断各帧图像中是否存在人脸，若判断上述图像中存在人脸，则进一步确定出每个人脸的位置、大小和各个主要面部器官的位置信息及人脸的个数。通过对应的图像处理方法对上述人脸进行美颜处理。其中，上述美颜处理可包括瘦脸处理、美肤处理、五官增强处理或动画效果添加处理中的一种或多种。上述美颜处理仅是举例，而非穷举，此处不做限定。例如，上述美肤处理包括使用图像增强技术对人脸的皮肤进行色彩增强处理，以达到提亮皮肤的效果。例如，使用图像裁剪及拼接技术对人脸中的眼睛进行放大处理，对人脸中的鼻子进行鼻梁提高处理等，最终达到五官显示效果增强的效果。若判断出上述图像中不存在人脸，则对上述各帧图像进行图像美化处理，上述美化处理可包括滤镜效果添加、图片锐化等，此处不做限定。例如，使用图像处理技术对各帧图像的色彩进行调节，使得各帧图像的色彩趋向于暖色系，实现图像的暖化功能，最终实现录像画面的暖化效果。可选的，在判断出第二录像画面中存在人脸后，继续判断上述人脸的个数是否大于预设个数阈值，若判断为是，则对上述第二画面进行美化处理，否则分别对第二录像画面中包含的人脸进行美颜处理。上述美颜处理和上述美化处理同上，此处便不再赘述。通过上述美颜处理和美化处理，使得第二录像画面具备了特殊的显示效果，提高视频画面的可观赏性，提升了终端的用户体验效果。
可选的，当终端处于上述第二录像模式时，终端可检测上述第二录像画面中是否存在 于上述第一手势具有明显区别的第二手势，判断方法的实现方式同上述步骤S102中判断第一录像画面中是否包含第一手势的实现方式，此处不再赘述。若终端检测到第二录像画面中存在第二手势，则将终端当前的录像模式由第二录像模式切换至第一录像模式，进而可通过普通模式进行终端录像，节省终端的功耗，同时也提高了终端录像模式的切换方式的多样性，操作更灵活。其中，终端录像模式切换方法的实现方式同步骤S103中录像模式切换方法的实现方式，此处不再赘述。
在本申请实施例中，终端首先接收录像启动指令，并根据上述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面。然后，根据上述第一图像数据判断上述第一录像画面中是否包含第一手势，若上述第一录像画面中包含上述第一手势，则将终端录像模式由上述第一录像模式切换至第二录像模式，并在上述第二录像模式下进行第二图像数据的采集以得到第二录像画面。最后判断上述第二录像画面中是否包含人脸，若该第二录像画面中包含上述人脸，则对该第二录像画面中的人脸进行美颜处理，若该第二录像画面中不包含上述人脸，则对该第二录像画面进行美化处理。采用本申请实施例可增加录像应用获取的视频画面形式的多样性，提高视频画面的可观赏性，提升用户体验效果。
参见图2，图2是本申请实施例提供的录像装置的结构示意图，本申请实施例所描述的图像处理装置，包括：
录像单元10，用于接收录像启动指令，并根据所述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面。
手势识别单元20，用于根据所述录像单元采集的所述第一图像数据判断所述第一录像画面中是否包含第一手势。
模式切换单元30，用于当所述手势识别单元识别确定所述第一录像画面中包含所述第一手势时，将终端录像模式由所述第一录像模式切换至第二录像模式。
上述录像单元10，还用于所述第二录像模式下进行第二图像数据的采集以得到第二录像画面。
画面处理单元40，用于判断所述第二录像画面中是否包含人脸，若所述第二录像画面包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面不包含所述人脸，则对所述第二录像画面进行美化处理。
在一些可行的实施方式中，上述手势识别单元20用于：
设定第二录像模式对应的至少一种启动方式，上述至少一种启动方式中包括手势启动，上述至少一种启动方式中每种启动方式对应一种用户操作指令；
获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测上述第一录像画面中是否包括第一手势。
在一些可行的实施方式中，上述手势识别单元20还用于：
根据上述录像单元10采集的所述第二图像数据判断所述第二录像画面中是否包含第二手势。
在一些可行的实施方式中，上述模式切换单元30具体还用于：
在上述手势识别单元20确定得到所述第二录像画面中包含所述第二手势时，将所述终 端录像模式由所述第二录像模式切换至所述第一录像模式。
在一些可行的实施方式中，上述图像处理单元40用于：
对上述第二录像画面中的所述人脸进行瘦脸处理；或者
对上述第二录像画面中的所述人脸进行美肤处理；或者
对上述第二录像画面中的所述人脸进行五官增强处理；或者
对上述第二录像画面中的所述人脸进行动画效果添加处理。
在一些可行的实施方式中，上述画面处理单元40还用于：
当上述录像单元10获取的第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值时，对所述第二录像画面进行美化处理。
在一些可行的实施方式中，上述录像单元10可通过检测用户对终端主界面中任意区域的点击来获取用户操作指令，根据终端预设的指令集判断该用户操作指令对应的终端功能是否为目标应用程序的开启。若该用户操作指令对应的功能为目标应用程序的开启，则确定该用户操作指令为目标应用程序开启指令。其中，终端预设的指令集中包括至少一组用户操作指令与终端功能之间的对应关系。例如，在获取录像启动指令之前，上述录像单元10检测到用户点击手机界面中相机的图标时所触发产生的用户操作指令，则可根据上述指令集确定该用户操作指令对应的终端功能为启动相机，并可确定该用户操作指令为应用程序开启指令。
可选的，上述录像单元10还可以通过检测用户对终端所具备的物理按键(和/或虚拟按键)的按压(和/或触控)来获取用户操作指令。例如，在获取录像启动指令之前，上述录像单元10通过检测到用户对终端中的音量按键进行长时间的按压来获取用户操作指令，可根据终端预设的指令集确定该用户操作指令对应的终端功能为目标应用程序开启，则确定该用户操作指令为目标应用程序开启指令。
可选的，若上述录像单元10确定上述用户操作指令为上述目标应用程序开启指令，则可在终端主界面上显示用户身份信息验证的提示信息，该提示信息用于请求用户进行身份信息验证。其中，用户身份信息验证的方式可包括密码验证、指纹验证、人脸识别验证、虹膜识别验证等，具体此处不做限定。当检测到用户通过身份信息验证后，开启上述目标应用程序。例如，获取目标应用程序开启指令后，上述录像单元10在终端主界面中提示用户进行身份信息验证，身份信息验证方式可为指纹验证。在检测到用户的指纹识别结果为真后，开启上述目标应用程序。
开启上述目标应用程序后，上述录像单元10可提示用户进行上述目标应用程序的应用功能的选择。可在该目标应用程序界面显示多个功能选项，上述功能选项可包括录像功能选项、拍照功能选项等，此处不作限定。上述录像单元10通过检测用户对上述功能选项的点击来获取不同的用户操作指令，并根据预设的指令集判断该用户操作指令对应的终端功能是否为录像功能的选取，其中，该预设的指令集与上述预设的指令集为同一指令集，此处不再赘述。例如，上述录像单元10在目标应用程序界面显示2个功能选项，包括录像功能选项和拍照功能选项。若检测到用户点击了拍照功能选项，则可获取一个用户操作指令，并可根据预设的指令集确定该用户操作指令对应的终端功能为拍照功能的选取。若检测到用户点击了录像功能选项，则可获取与上述用户操作指令不同的又一用户操作指令，并可 根据预设的指令集确定该用户操作指令对应的终端功能为录像功能的选取。
当上述录像单元10确定获取的用户操作指令对应的终端功能为录像功能的选取时，上述录像单元10启动上述目标应用程序默认的录像模式，通过终端摄像头采集上述第一图像数据以得到第一录像画面。为方便描述，上述默认的录像模式可设定为第一录像模式。
可选的，在获取第一图像数据之前，上述录像单元10可获取摄像头类型信息和拍照旋转信息。通过摄像头类型信息确定终端进行录像时使用的是前置摄像头还是后置摄像头。若使用的是前置摄像头，则可对终端摄像头采集到的图像数据进行镜像获取操作，若使用的是后置摄像头，则可不需要镜像获取操作。通过录像旋转信息确定用户使用终端进行录像时是否旋转了镜头。例如，若用户使用终端进行录像时是横向拍摄，则可确定用户旋转了镜头，若用户使用终端进行录像时是竖向拍摄，则用户没有旋转镜头。若用户旋转了镜头，则可对终端采集到的环境图像数据进行旋转操作，否则可不需要旋转操作。上述录像单元10可对摄像头采集到的图像数据进行镜像获取或旋转处理中的一种或多种处理操作，以得到上述第一图像数据。上述镜像获取操作和旋转操作的目的在于使得录像得到的视频画面更适于人眼观看。
例如，开启相机应用程序后，上述录像单元10检测并判断用户是否点击了相机应用界面中的录像按钮，若判断为是，则开启相机应用程序默认的无特效录像模式，并通过手机的前置摄像头或者后置摄像头进行环境图像数据的采集及处理。可选的，手机通过摄像头采集环境图像数据之后，对环境图像数据进行镜像获取处理及旋转处理，以得到不含特效的录像画面。
在上述录像单元10获取上述第一录像画面后，上述手势识别单元20可提示用户进行与上述第一录像模式不同的第二录像模式的启动方式的选择。上述手势识别单元20可在录像功能界面中显示多个启动方式选项，其中，上述启动方式选项可包括手势启动、触控启动等，此处不做限定。上述手势识别单元20可从录像功能界面上获取用户点击的选项，并将用户点击的选项对应的启动方式确定为第二录像模式的启动方式。例如，在上述录像单元10获取第一录像画面后，上述手势识别单元20在录像应用界面中提供2个预设的第二录像模式启动选项，包括手势启动和触控启动。检测用户点击的选项，若用户点击的选项为手势启动选项，则确定上述第二录像模式启动方式为手势启动。
可选的，上述手势识别单元20可在录像功能界面中提示用户对终端所具备的物理按键(和/或虚拟按键)进行按压(和/或触控)来选择第二录像模式启动方式。例如，上述手势识别单元20可在录像功能界面中提示用户通过长按音量键选择第二录像模式启动方式为手势启动。
在上述手势识别单元20提示用户进行第二录像模式启动方式选择后，可判断用户选择的启动方式是否为手势启动方式。若用户选择的上述第二录像模式的启动方式为手势启动，则上述手势识别单元20通过图像处理方法判断上述录像单元10获取的第一录像画面中是否包含第一手势。其中，上述第一手势为用户易于实现且易于终端识别的特殊性的手势。例如，张开五指再握拳，或者使用食指在空中划出一个闭合的圆形，或者用手指做出V字形手势等。上述图像处理方法可包括图像特征提取、人体姿态识别、图像拼接等方式，此处不做限定。例如，上述手势识别单元20提取出预设时间段内上述录像单元10获取的第一录 像画面中的各帧图像，并对各帧图像进行特征提取，检测上述图像中是否存在特定手势。若检测出多帧图像中均含有特定的手势，则确定第一录像画面中存在特定手势。可选的，从多帧图像中提取出人体手指的位置，并对该多帧图像进行图像拼接，根据拼接结果判断上述手指的位置是否构成一个特定的手势动作，若判断为是，则确定第一录像画面中存在特定手势。例如，上述手势识别单元20提取出上述录像单元10获取的第一录像画面中的时长为5s的第一录像画面片段，并分解成各帧图像，对各帧图像进行特征提取，检测上述图像中是否存在V字形手势，若判断出上述各帧图像中的多帧图像均存在V字形手势，则确定上述第一录像画面中存在特定手势，上述特定手势即为第一手势。
当上述手势识别单元20确定上述录像单元10获取的第一录像画面包含上述第一手势后，上述模式切换单元30在后台中将目标应用程序的通道由不含有美颜、图像美化等第三方算法的默认程序流切换至含有美颜、图像美化等第三方算法的功能程序流。
上述录像单元10在上述模式切换单元30进行终端录像模式切换后，在第二录像模式下通过终端摄像头进行第二图像数据采集以得到第二录像画面。在第二录像模式下采集第二图像数据以获得第二录像画面的实现方式具体可参见步骤S101中所述的在第一录像模式下采集第一图像数据以获得第一录像画面的实现方式，此处不再赘述。
上述图像处理单元40提取出预设时间段内的上述录像单元10获取的第二录像画面中的各帧图像，并通过人脸识别算法判断各帧图像中是否存在人脸，若判断上述图像中存在人脸，则进一步确定除每个人脸的位置、大小和各个主要面部器官的位置信息及人脸的个数。并通过对应的图像处理方法对上述人脸进行美颜处理。其中，上述美颜处理可包括瘦脸处理、美肤处理、五官增强处理或动画效果添加处理中的一种或多种，上述美颜处理仅是举例，而非穷举，此处不做限定。例如，上述美肤处理，即使用图像增强技术对人脸的皮肤进行色彩增强处理，以达到提亮皮肤的效果。例如，使用图像裁剪及拼接技术对人脸中的眼睛进行放大处理，对人脸中的鼻子进行鼻梁提高处理等，最终达到五官显示效果增强的效果。若判断出上述图像中不存在人脸，则对上述各帧图像进行图像美化处理，上述美化处理可包括滤镜效果添加、图片锐化等，此处不做限定。例如，使用图像处理技术对各帧图像的色彩进行调节，使得各帧图像的色彩趋向于暖色系，实现图像的暖化功能，最终实现录像画面的暖化效果。可选的，上述图像处理单元40在判断出上述录像单元10获取的第二录像画面中存在人脸后，继续判断上述人脸的个数是否大于预设个数阈值，若判断为是，则对上述第二画面进行美化处理，否则分别对第二录像画面中包含的人脸进行美颜处理。上述美颜处理和上述美化处理同上，此处便不再赘述。通过上述美颜处理和美化处理，使得第二录像画面具备了特殊的显示效果。
可选的，当终端处于上述第二录像模式时，上述图像处理单元40可检测上述第二录像画面中是否存在于上述第一手势具有明显区别的第二手势，所述判断方法的实现方式同上述步骤S102中判断第一录像画面中是否包含第一手势的实现方式，此处不再赘述。若终端检测到第二录像画面中存在上述第二手势，则上述模式切换单元30将终端当前的录像模式由第二录像模式切换至第一录像模式，其中，终端录像模式切换方法的实现方式同步骤S103中录像模式切换方法的实现方式相同，此处不再赘述。
在本申请实施例中，终端首先接收录像启动指令，并根据上述录像启动指令启动第一录像 模式进行第一图像数据的采集以得到第一录像画面。然后，根据上述第一图像数据判断上述第一录像画面中是否包含第一手势，若上述第一录像画面中包含上述第一手势，则将终端录像模式由上述第一录像模式切换至第二录像模式，并在上述第二录像模式下进行第二图像数据的采集以得到第二录像画面。最后判断上述第二录像画面中是否包含人脸，若该第二录像画面中包含上述人脸，则对该第二录像画面中的人脸进行美颜处理，若该第二录像画面中不包含上述人脸，则对该第二录像画面进行美化处理。采用本申请实施例可增加录像应用获取的视频画面形式的多样性，提高视频画面的可观赏性，提升用户体验效果。
参见图3，图3是本申请实施例提供的终端的结构示意图，本申请实施例所描述的终端，可包括收发器100、存储器200、处理器300；
收发器100、存储器200、处理器300通过总线连接；
存储器200用于存储一组程序代码；
处理器300和收发器100用于调用存储器200中存储的程序代码，执行如下操作：
收发器100，用于接收录像启动指令；
处理器300，用于根据收发器100接收到所述录像启动指令启动第一录像模式；
收发器100，还用于在处理器300启动的所述第一录像模式下进行第一录像数据的采集以得到第一录像画面；
处理器300，还用于根据收发器100采集的所述第一图像数据判断所述第一录像画面中是否包含第一手势，若所述第一录像画面中包含所述第一手势，则将终端录像模式由所述第一录像模式切换至第二录像模式；
收发器100，还用于在处理器300启动的所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
处理器300，还用于判断收发器100采集的所述第二录像画面中是否包含人脸，若所述第二录像画面中包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面中不包含所述人脸，则对所述第二录像画面进行美化处理。
在一些可能的实现方式中，处理器300用于：
对收发器100采集的所述第二录像画面中的所述人脸进行瘦脸处理；或者
对收发器100采集的所述第二录像画面中的所述人脸进行美肤处理；或者
对收发器100采集的所述第二录像画面中的所述人脸进行五官增强处理；或者
对收发器100采集的所述第二录像画面中的所述人脸进行动画效果添加处理。
在一些可能的实现方式中，处理器300还用于：
当收发器100采集的所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值时，对所述第二录像画面进行美化处理。
在一些可能的实现方式中，处理器300还用于：
设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动，所述至少一种启动方式中每种启动方式对应一种用户操作指令；
获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
在一些可能的实现方式中，处理器300还用于：
根据收发器100采集的所述第二图像数据判断所述第二录像画面中是包含第二手势，在确定所述第二录像画面中包含所述第二手势之后，将所述终端录像模式由所述第二录像模式切换至所述第一录像模式。
应当理解，在本申请实施例中，收发器100可以包括触控板、指纹采传感器(用于采集用户的指纹信息和指纹的方向信息)、麦克风、显示器(LCD等)、扬声器等。该存储器200可以包括只读存储器和随机存取存储器，并向处理器300提供指令和数据。存储器200的一部分还可以包括非易失性随机存取存储器。例如，存储器200还可以存储设备类型的信息。
处理器300可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
具体实现中，本申请实施例中所描述的收发器100、存储器200、处理器300可执行本申请实施例提供的一种录像方法中各个步骤所描述的实现方式，也可执行本申请实施例所描述的录像装置的实现方式，具体可参见上述各个实施例所描述的实现方式，在此不再赘述。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。

Claims (10)

  1. 一种录像的方法，其特征在于，包括：
    接收录像启动指令，并根据所述录像启动指令启动第一录像模式进行第一图像数据的采集以得到第一录像画面；
    根据所述第一图像数据判断所述第一录像画面中是否包含第一手势；
    若所述第一录像画面中包含所述第一手势，则将终端录像模式由所述第一录像模式切换至第二录像模式，在所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
    判断所述第二录像画面中是否包含人脸；
    若所述第二录像画面中包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面中不包含所述人脸，则对所述第二录像画面进行美化处理。
  2. 根据权利要求1所述的方法，其特征在于，所述对所述第二录像画面中的所述人脸进行美颜处理包括：
    对所述第二录像画面中的所述人脸进行瘦脸处理；或者
    对所述第二录像画面中的所述人脸进行美肤处理；或者
    对所述第二录像画面中的所述人脸进行五官增强处理；或者
    对所述第二录像画面中的所述人脸进行动画效果添加处理。
  3. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    若所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值，则对所述第二录像画面进行美化处理。
  4. 根据权利要求1所述的方法，其特征在于，所述根据所述第一图像数据判断所述第一录像画面中是否包含第一手势包括：
    设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动，所述至少一种启动方式中每种启动方式对应一种用户操作指令；
    获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述将终端录像模式由所述第一录像模式切换至第二录像模式之后，所述方法还包括：
    根据所述第二图像数据判断所述第二录像画面中是否包含第二手势，若所述第二录像画面中包含所述第二手势，则将所述终端录像模式由所述第二录像模式切换至所述第一录像模式。
  6. 一种录像的装置，其特征在于，所述装置包括：
    录像单元，用于接收录像启动指令，并根据所述录像启动指令启动第一录像模式进行 第一图像数据的采集以得到第一录像画面；
    手势识别单元，用于根据所述录像单元采集的所述第一图像数据判断所述第一录像画面中是否包含第一手势；
    模式切换单元，用于当所述手势识别单元识别确定所述第一录像画面中包含所述第一手势时，将终端录像模式由所述第一录像模式切换至第二录像模式；
    所述录像单元，还用于在所述第二录像模式下进行第二图像数据的采集以得到第二录像画面；
    画面处理单元，用于判断所述第二录像画面中是否包含人脸，若所述第二录像画面包含所述人脸，则对所述第二录像画面中的所述人脸进行美颜处理，若所述第二录像画面不包含所述人脸，则对所述第二录像画面进行美化处理。
  7. 根据权利要求6所述的装置，其特征在于，所述画面处理单元用于：
    对所述第二录像画面中的所述人脸进行瘦脸处理；或者
    对所述第二录像画面中的所述人脸进行美肤处理；或者
    对所述第二录像画面中的所述人脸进行五官增强处理；或者
    对所述第二录像画面中的所述人脸进行动画效果添加处理。
  8. 根据权利要求6所述装置，其特征在于，所述画面处理单元用于：
    当所述第二录像画面中包含所述人脸，且所述人脸的个数等于或大于预设阈值时，对所述第二录像画面进行美化处理。
  9. 根据权利要求6所述的装置，其特征在于，所述手势识别单元用于：
    设定第二录像模式对应的至少一种启动方式，所述至少一种启动方式中包括手势启动，所述至少一种启动方式中每种启动方式对应一种用户操作指令；
    获取用户操作指令，若获取的所述用户操作指令对应的启动方式为手势启动，则检测所述第一录像画面中是否包括第一手势。
  10. 根据权利要求6-9任一项所述的装置，其特征在于，
    所述手势识别单元，还用于根据所述录像单元采集的所述第二图像数据判断所述第二录像画面中是否包含第二手势；
    所述模式切换单元，还用于在所述手势识别单元确定得到所述第二录像画面中包含所述第二手势时，将所述终端录像模式由所述第二录像模式切换至所述第一录像模式。
PCT/CN2017/105370 2017-10-09 2017-10-09 一种录像方法、装置及终端 WO2019071381A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201780095760.7A CN111201772A (zh) 2017-10-09 2017-10-09 一种录像方法、装置及终端
PCT/CN2017/105370 WO2019071381A1 (zh) 2017-10-09 2017-10-09 一种录像方法、装置及终端

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/105370 WO2019071381A1 (zh) 2017-10-09 2017-10-09 一种录像方法、装置及终端

Publications (1)

Publication Number Publication Date
WO2019071381A1 true WO2019071381A1 (zh) 2019-04-18

Family

ID=66100167

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/105370 WO2019071381A1 (zh) 2017-10-09 2017-10-09 一种录像方法、装置及终端

Country Status (2)

Country Link
CN (1) CN111201772A (zh)
WO (1) WO2019071381A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114245005A (zh) * 2021-11-29 2022-03-25 荣耀终端有限公司 一种电子设备的控制方法、装置以及相关设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115334237B (zh) * 2022-07-26 2024-01-23 广州紫为云科技有限公司 基于usb相机的人像对焦方法、装置及介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103973970A (zh) * 2013-02-01 2014-08-06 三星电子株式会社 控制相机装置的操作的方法和相机装置
CN104463782A (zh) * 2013-09-16 2015-03-25 联想(北京)有限公司 图像处理方法、装置和电子设备
CN104883505A (zh) * 2015-06-12 2015-09-02 联想(北京)有限公司 电子设备及其拍照控制方法
CN105303523A (zh) * 2014-12-01 2016-02-03 维沃移动通信有限公司 一种图像处理方法及移动终端
CN105657272A (zh) * 2016-02-04 2016-06-08 上海卓易科技股份有限公司 一种终端设备及其拍摄方法
CN105988566A (zh) * 2015-02-11 2016-10-05 联想(北京)有限公司 一种信息处理方法及电子设备
CN107015648A (zh) * 2017-03-28 2017-08-04 北京小米移动软件有限公司 图片处理方法及装置
WO2017161561A1 (en) * 2016-03-25 2017-09-28 Intel Corporation Gpu optimized and online single gaussian based skin likelihood estimation

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102638656A (zh) * 2012-04-18 2012-08-15 青岛海信移动通信技术股份有限公司 一种视频图像处理方法及装置
CN103152489B (zh) * 2013-03-25 2015-07-29 锤子科技（北京）有限公司 一种自拍图像的展现方法及装置
CN103413270A (zh) * 2013-08-15 2013-11-27 北京小米科技有限责任公司 一种图像的处理方法、装置和终端设备
KR102158214B1 (ko) * 2014-05-19 2020-09-22 엘지전자 주식회사 이동 단말기 및 그것의 제어방법
CN105049705B (zh) * 2015-06-19 2018-03-27 广东欧珀移动通信有限公司 一种拍摄模式切换方法及用户终端
CN105139357A (zh) * 2015-08-26 2015-12-09 深圳市金立通信设备有限公司 一种图像编辑的方法及终端
JP6611566B2 (ja) * 2015-11-02 2019-11-27 キヤノン株式会社 撮像装置、撮像装置の制御方法及びプログラム
CN105704390B (zh) * 2016-04-20 2019-04-16 Oppo广东移动通信有限公司 一种美颜拍照方法、装置及移动终端
CN105915673B (zh) * 2016-05-31 2019-04-02 努比亚技术有限公司 一种视频特效切换的方法和移动终端
CN106657814B (zh) * 2017-01-17 2018-12-04 维沃移动通信有限公司 一种视频录制方法及移动终端

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103973970A (zh) * 2013-02-01 2014-08-06 三星电子株式会社 控制相机装置的操作的方法和相机装置
CN104463782A (zh) * 2013-09-16 2015-03-25 联想(北京)有限公司 图像处理方法、装置和电子设备
CN105303523A (zh) * 2014-12-01 2016-02-03 维沃移动通信有限公司 一种图像处理方法及移动终端
CN105988566A (zh) * 2015-02-11 2016-10-05 联想(北京)有限公司 一种信息处理方法及电子设备
CN104883505A (zh) * 2015-06-12 2015-09-02 联想(北京)有限公司 电子设备及其拍照控制方法
CN105657272A (zh) * 2016-02-04 2016-06-08 上海卓易科技股份有限公司 一种终端设备及其拍摄方法
WO2017161561A1 (en) * 2016-03-25 2017-09-28 Intel Corporation Gpu optimized and online single gaussian based skin likelihood estimation
CN107015648A (zh) * 2017-03-28 2017-08-04 北京小米移动软件有限公司 图片处理方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114245005A (zh) * 2021-11-29 2022-03-25 荣耀终端有限公司 一种电子设备的控制方法、装置以及相关设备

Also Published As

Publication number Publication date
CN111201772A (zh) 2020-05-26

Similar Documents

Publication Publication Date Title
US11678734B2 (en) Method for processing images and electronic device
EP2960822B1 (en) Method and device for locking file
CN108833818B (zh) 视频录制方法、装置、终端及存储介质
WO2019001152A1 (zh) 拍照方法及移动终端
WO2016177154A1 (zh) 一种切换移动终端工作模式的方法及装置
US9904774B2 (en) Method and device for locking file
KR102018887B1 (ko) 신체 부위 검출을 이용한 이미지 프리뷰
WO2016145830A1 (zh) 图像处理方法、终端及计算机存储介质
CN112585566B (zh) 用于与具有内置摄像头的设备进行交互的手遮脸输入感测
CN104484858B (zh) 人物图像处理方法及装置
CN107835359A (zh) 一种移动终端的拍照触发方法、移动终端及存储设备
CN107710221B (zh) 一种用于检测活体对象的方法、装置和移动终端
EP3328062A1 (en) Photo synthesizing method and device
CN108810256A (zh) 一种控制方法和装置
US20240005695A1 (en) Fingerprint Recognition Method and Electronic Device
TWI752105B (zh) 特徵圖像的獲取方法及獲取裝置、使用者認證方法
WO2021120626A1 (zh) 一种图像处理方法、终端及计算机存储介质
KR20150003501A (ko) 전자 디바이스 및 전자 디바이스에서 지문을 이용한 인증 방법
CN105072335B (zh) 一种拍照方法及用户终端
WO2017140108A1 (zh) 压力检测方法和装置
WO2019071381A1 (zh) 一种录像方法、装置及终端
WO2021189927A1 (zh) 图像处理方法、装置、电子设备及存储介质
WO2018133305A1 (zh) 一种图像处理的方法及装置
TW201714074A (zh) 使用手勢的拍照方法、系統與電子裝置
CN109561215B (zh) 对美颜功能进行控制的方法、装置、终端及存储介质

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: 17928335

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: 17928335

Country of ref document: EP

Kind code of ref document: A1