WO2015184873A1 - 一种视频拍摄的处理方法、系统和装置 - Google Patents

一种视频拍摄的处理方法、系统和装置 Download PDF

Info

Publication number
WO2015184873A1
WO2015184873A1 PCT/CN2015/073507 CN2015073507W WO2015184873A1 WO 2015184873 A1 WO2015184873 A1 WO 2015184873A1 CN 2015073507 W CN2015073507 W CN 2015073507W WO 2015184873 A1 WO2015184873 A1 WO 2015184873A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
background
shooting
subject
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2015/073507
Other languages
English (en)
French (fr)
Inventor
陈建江
徐源源
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
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 ZTE Corp filed Critical ZTE Corp
Priority to KR1020177011342A priority Critical patent/KR20170060140A/ko
Priority to EP15803979.2A priority patent/EP3200444B1/en
Priority to JP2017522631A priority patent/JP6413018B2/ja
Priority to US15/522,500 priority patent/US10289914B2/en
Publication of WO2015184873A1 publication Critical patent/WO2015184873A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G06T11/60—Creating or editing images; Combining images with text
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/44—Event detection

Definitions

  • the present invention relates to the field of video capture technology, and in particular, to a method, system and device for processing video capture.
  • the shooting of mobile phones is a very important function.
  • mobile phone photographing and video recording are very frequently used, and users taking photos with mobile phones are not satisfied with ordinary results.
  • the various special effects of mobile phone camera can increase the appeal of the camera, and it is suitable for users to share and communicate.
  • the beautification of the camera effect has become a development trend, and its development speed has surpassed that of the card camera.
  • Dynamic video which is to shoot objects that change slowly into faster-changing objects.
  • the main principle is to lengthen the time between sampling video frames during shooting (for example, 1 frame per second), and play at normal frame rate during playback ( For example, 30 frames per second).
  • the cloud movement of the sky is shot, and the effect of playing after shooting forms a cloud with rapidly changing sky, such as a rapidly changing sunset, a fast moving nebula, and the like. This special effect gives a feeling of grand atmosphere.
  • the technical problem to be solved by the embodiments of the present invention is to provide a processing method, system and device for motion-sensing video shooting, which can shorten the time when the shooting subject appears in front of the camera and improve the user experience during the long-term motion video shooting.
  • an embodiment of the present invention provides a processing method for video shooting.
  • the method includes:
  • the subject in the background sample is photographed according to the first photographing sampling rate, and after receiving the instruction to stop photographing, the first video is generated;
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • comparing the first video with the second video, extracting a subject image from the first video, and generating a background transparent body image frame sequence including:
  • inserting each frame of the main body image frame into the third video in sequence includes:
  • the main image frame sequence is cyclically used for image superposition.
  • the video file in which the subject and the target background are recorded is played by the player in a loop.
  • the embodiment of the invention further provides a processing system for video shooting, the system comprising:
  • the shooting module is configured to: respectively shoot the subject in the background sample, the background sample and the target background, respectively generate a first video recording the subject plus the background sample, a second video recording the background sample, and a third video recording the target background Wherein the shooting duration of the first video and the second video is less than the shooting duration of the third video;
  • a video processing module configured to: compare the first video with the second video, extract a subject image from the first video, generate a background transparent subject image frame sequence, and set the subject image frame Each frame of the subject image in the sequence is sequentially superimposed into the third video to generate a video file in which the subject and the target background are recorded.
  • the shooting module is set to:
  • the subject in the background sample is photographed according to the first photographing sampling rate, and after receiving the instruction to stop photographing, the first video is generated;
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • the video processing module is configured to compare the first video and the second video in a manner, extract a subject image from the first video, and generate a background image frame of the subject transparent :
  • the video processing module is configured to sequentially insert each frame of the main body image frame into the third video in the following manner:
  • the video file in which the subject and the target background are recorded is played by the player in a loop.
  • An embodiment of the present invention further provides a video photographing apparatus, including a camera and a processor, wherein the camera is configured to respectively photograph a subject, a background sample, and a target background in a background sample under the control of the processor, Generating a first video of the recording subject plus the background sample, a second video recording the background sample, and a third video recording the background of the target, wherein the shooting duration of the first video and the second video is smaller than the shooting of the third video duration;
  • the processor is configured to control the camera to perform shooting, compare the first video and the second video, extract a subject image from the first video, and generate a background image sequence of a subject transparent Each frame of the subject image sequence is sequentially superimposed into the third video to generate a video file in which the subject and the target background are recorded.
  • the camera is set to:
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • the processor is configured to compare the first video and the second video in a manner, extract a subject image from the first video, and generate a background image frame of a transparent body image :
  • the processor is configured to sequentially insert each frame of the main body image frame into the third video in the following manner:
  • the device further includes:
  • the processor is further configured to: control the video file in which the subject and the target background are recorded to be played cyclically on the display screen.
  • the embodiment of the invention further provides a computer readable storage medium storing program instructions, which can be implemented when the program instructions are executed.
  • a processing method and system for motion video shooting processes a short video of a main body to generate a background transparent by separately capturing a short video of a main body, a short video of a background sample, and a long video of a target background.
  • the main image frame sequence superimposes the background transparent body image frame sequence on the long video of the target background to generate a motion video file of the subject in the target background, which can shorten the subject in front of the camera during long-term motion video shooting The time of emergence to improve the user experience.
  • FIG. 1 is a flowchart of a method for processing video capture according to an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of a processing system for video shooting according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a video capturing apparatus according to an embodiment of the present invention.
  • FIG. 4 is a flow chart of a method for processing motion picture capture according to an application example of the present invention.
  • an embodiment of the present invention provides a method for processing video capture, where the method includes:
  • the subject and the background sample in the background sample can be photographed for a short time, and the target background can be photographed for a long time.
  • the method also includes the following features:
  • the main body, the background sample, and the target background in the background sample are respectively photographed, and respectively generate a first video of the recording subject plus the background sample, a second video recording the background sample, and a third video of the recording target background, including:
  • the subject in the background sample is photographed according to the first photographing sampling rate, and after receiving the instruction to stop photographing, the first video is generated;
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • the first video and the second video are compared, and the subject image is extracted from the first video to generate a background image sequence of the subject image, including:
  • the main image frame sequence includes one or more frame body images
  • the superimposing each frame of the main body image frame into the third video in sequence includes:
  • the motion video file in which the subject and the target background are recorded may be played by the player in a loop.
  • an embodiment of the present invention provides a processing system for video shooting, the system comprising:
  • the shooting module is configured to: respectively shoot the subject in the background sample, the background sample and the target background, respectively generate a first video recording the subject plus the background sample, a second video recording the background sample, and a third video recording the target background Wherein the shooting duration of the first video and the second video is less than the shooting duration of the third video;
  • a video processing module configured to: compare the first video with the second video, extract a subject image from the first video, generate a background transparent subject image frame sequence, and set the subject image frame Each frame of the subject image in the sequence is sequentially superimposed into the third video to generate a video file in which the subject and the target background are recorded.
  • the shooting module is set to:
  • the subject in the background sample is photographed according to the first photographing sampling rate, and after receiving the instruction to stop photographing, the first video is generated;
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • the video processing module is configured to compare the first video and the second video, extract a subject image from the first video, and generate a background image sequence of the subject image transparently, including:
  • the video processing module is configured to sequentially superimpose each frame image in the main image frame sequence into the third video, including:
  • the motion video file in which the subject and the target background are recorded is played by the player in a loop.
  • an embodiment of the present invention further provides a video capturing apparatus, including a camera and a processor, wherein the camera is configured to control a subject, a background sample, and a background sample in a background sample under the control of the processor.
  • a video capturing apparatus including a camera and a processor, wherein the camera is configured to control a subject, a background sample, and a background sample in a background sample under the control of the processor.
  • Shooting the target background separately, respectively generating a first video recording the subject plus the background sample, recording a second video of the background sample, and recording a third video of the target background; wherein the shooting duration of the first video and the second video is less than The duration of the third video;
  • the processor is configured to control the camera to perform shooting, compare the first video and the second video, extract a subject image from the first video, and generate a background transparent body And a sequence of image frames, wherein each frame of the subject image sequence is sequentially superimposed into the third video to generate a video file in which the subject and the target background are recorded.
  • the camera is set to:
  • the background sample After receiving the instruction to shoot the background sample, the background sample is taken according to the first shooting sampling rate, and after receiving the instruction to stop shooting, the second video is generated;
  • first shooting sampling rate is greater than the second shooting sampling rate.
  • the processor is configured to compare the first video and the second video in a manner of: extracting a subject image from the first video, and generating a background image sequence of a transparent background image:
  • processor is configured to sequentially insert each frame of the main body image frame sequence into the third video in the following manner:
  • the apparatus may further include a display screen, the processor further configured to: control the video file in which the subject and the target background are recorded to be cyclically played on the display screen.
  • the process of shooting a portrait motion video of a mobile phone includes:
  • S101 preset shooting parameters, waiting for the user to start motion video shooting
  • the shooting parameters may include one or more of the following parameters: a slow shooting sampling rate of the shooting target background, a shooting duration of the portrait in the background sample, a shooting duration of the background sample, and a target background shooting duration.
  • a person shooting a frame at a normal shooting rate for example, 30 frames per second
  • a normal shooting rate for example, 30 frames per second
  • the preset shooting time for example, 3 seconds
  • the shooting of the portrait is stopped, and a portrait video clip is generated.
  • the user can also display the prompt information for the completion of the portrait shooting.
  • the background sample in the framing frame can be the same thing or different thing as the target background.
  • S104 detecting an instruction to take a background sample, performing a background sample video shooting, stopping shooting the background sample after receiving the instruction to stop shooting, or stopping shooting the background sample when the preset shooting time is reached. , generating a short video of the background sample;
  • the background sample in the framing frame is taken at a normal shooting rate (for example, 30 frames per second) for 1 second. That is, when it is detected that the user presses the stop button, or when the preset shooting time (for example, 1 second) is reached, the shooting of the background sample is stopped, and a background sample video clip is generated. After the shooting is completed, the user can also display the prompt information that the background sample shooting is completed.
  • a normal shooting rate for example, 30 frames per second
  • S105 detecting an instruction to shoot the target background, performing slow shooting on the target background, stopping the shooting of the target background after receiving the instruction to stop shooting, or stopping shooting the target background when the preset shooting time is reached. , generating a target background video;
  • the target background is photographed at a slow shooting rate (eg, 1 second for 1 frame) below the normal shooting rate, for 3 minutes (180 seconds). That is, when the user is detected to press Stop the button, or, when the preset shooting duration (for example, 3 minutes) is reached, stop shooting the target background and generate a target background long video. After the shooting is completed, the user can also display the prompt information of the target background shooting completion.
  • a slow shooting rate eg, 1 second for 1 frame
  • 3 minutes 180 seconds
  • slow shooting generally refers to 1 frame of 0.2-60 seconds, usually 1 frame of 1-5 seconds.
  • the player can also play the dynamic video file in a loop;
  • the sampling of the target background is set to 1 frame and 1 frame, and the target background of 180 frames can be captured in 3 minutes. Therefore, the motion video stream after the portrait is superimposed contains 180 frames, and the playback frame rate of the player is 1 second.
  • 180 frames can be played for 6 seconds. That is, the 3 minute (180 seconds) camera finishes playing in 6 seconds, and its time is accelerated by 30 times, realizing the effects of fast moving portraits and target backgrounds (such as clouds, sun, or ships).
  • the technical solution of the present invention is not used, the subject (such as a person) must be kept in front of the lens for 3 minutes. Such shooting conditions may be unacceptable to most users. Therefore, the above-mentioned dynamic video shooting solution can greatly reduce the time when the shooting subject (for example, a person) appears in front of the camera, and realize the special effect that the slow moving object becomes fast moving, bringing a new surprise experience to the mobile phone camera.
  • the processing method and system for dynamic video shooting provided by the above embodiments provide a background transparent subject image frame sequence by processing a short video of the main body, a short video of the background sample, and a long video of the target background, respectively.
  • the background transparent frame of the subject image is superimposed on the long video of the target background to generate a motion video file of the subject in the target background, which can shorten the time of the subject appearing in front of the camera during the long-term motion video shooting, and improve the user experience. .
  • all or part of the steps of the above embodiments may also be implemented by using an integrated circuit. These steps may be separately fabricated into individual integrated circuit modules, or multiple modules or steps may be fabricated into a single integrated circuit module. achieve.
  • the devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.
  • each device/function module/functional unit in the above embodiment When each device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium.
  • the above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
  • the embodiment of the invention can shorten the time when the shooting subject appears in front of the lens during long-time video shooting, and improve the user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Studio Devices (AREA)
  • Television Signal Processing For Recording (AREA)
  • Image Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

一种视频拍摄的处理方法、系统和装置,该方法包括:对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。

Description

一种视频拍摄的处理方法、系统和装置 技术领域
本发明涉及视频拍摄技术领域,尤其涉及的是一种视频拍摄的处理方法、系统和装置。
背景技术
手机的拍摄是非常重要的功能,在当前手机日常使用过程中,手机拍照及录像使用非常频繁,用户使用手机拍照摄像已不满足于普通的结果。手机摄像的各种特效,能增加摄像的吸引力,适合用户之间分享交流,当前为手机美化摄像效果已成为发展趋势,其发展速度已超过了卡片照相机。
动感视频,即将原来缓慢变化的物体拍摄成变化速度更快的物体,主要原理是拍摄时取样视频帧之间的时间拉长(例如,每秒1帧),播放时按正常的帧率播放(例如,每秒30帧)。例如,拍摄天空的云移动,拍摄后播放的效果形成天空快速变化的云,再比如快速变化的落日过程、快速移动的星云等。这种特效能给人一种宏大气势的感觉。
但在动感视频的拍摄过程中发现,用动感视频拍摄人像非常困难。原因是拍摄动感视频的持续时间较长,一般会拍摄几分钟甚至几小时,但如果被拍摄人员一直在镜头前维持几分钟或几小时来拍摄动感视频,用户难以接受,大大影响了用户拍摄动感视频的乐趣。
因此,需要有一个合适的解决方案来处理动感视频中的人像拍摄问题。
发明内容
本发明实施例所要解决的技术问题是提供一种动感视频拍摄的处理方法、系统和装置,能够在长时间动感视频拍摄过程中,缩短拍摄主体在镜头前出现的时间,改善用户体验。
为了解决上述技术问题,本发明实施例提供了一种视频拍摄的处理方法, 该方法包括:
对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
可选地,对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频,包括:
在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
可选地,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,包括:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
可选地,将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中,包括:
将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流 中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
可选地,所述记录了主体和目标背景的视频文件由播放器循环播放。
本发明实施例还提供一种视频拍摄的处理系统,该系统包括:
拍摄模块,设置为:对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
视频处理模块,设置为:将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
可选地,拍摄模块,是设置为:
在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
可选地,视频处理模块,是设置为以如下方式将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
可选地,视频处理模块,是设置为以如下方式将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中:
将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
可选地,所述记录了主体和目标背景的视频文件由播放器循环播放。
本发明实施例还提供一种视频拍摄装置,包括摄像头和处理器,其中,所述摄像头设置为在所述处理器的控制下对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
所述处理器设置为控制所述摄像头进行拍摄,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
可选地,所述摄像头是设置为:
在接收所述处理器到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
可选地,所述处理器是设置为以如下方式将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
可选地,所述处理器是设置为以如下方式将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中:
将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
可选地,所述装置还包括:
显示屏,所述处理器还设置为:控制所述记录了主体和目标背景的视频文件在所述显示屏上循环播放。
本发明实施例还提供一种计算机可读存储介质,存储有程序指令,当该程序指令被执行时可实现上面所述的方法。
与相关技术相比,本发明实施例提供的一种动感视频拍摄的处理方法和系统,通过分别拍摄主体短视频、背景样品短视频和目标背景的长视频,对主体短视频进行处理生成背景透明的主体图像帧序列,将背景透明的主体图像帧序列叠加到目标背景的长视频中,生成主体在目标背景中的动感视频文件,能够在长时间动感视频拍摄过程中,缩短拍摄主体在镜头前出现的时间,改善用户体验。
附图概述
图1为本发明实施例的一种视频拍摄的处理方法的流程图。
图2为本发明实施例的一种视频拍摄的处理系统的结构示意图。
图3为本发明实施例的一种视频拍摄装置的结构示意图。
图4为本发明应用示例的一种动感视频拍摄的处理方法的流程图。
本发明的较佳实施方式
下文中将结合附图对本发明的实施例进行详细说明。需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互任意组合。
如图1所示,本发明实施例提供了一种视频拍摄的处理方法,该方法包括:
S10,对处于背景样品中的主体、背景样品和目标背景进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;
S20,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
其中,可以对处于背景样品中的主体和背景样品分别进行短时拍摄,对目标背景进行长时的慢速拍摄。
该方法还包括下述特点:
其中,对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频,包括:
在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
其中,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,包括:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列;
其中,所述主体图像帧序列包括一帧或多帧主体图像;
其中,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,包括:
将所述主体图像帧序列中的每一帧主体图像叠加到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
其中,所述记录了主体和目标背景的动感视频文件可以由播放器循环播放。
如图2所示,本发明实施例提供了一种视频拍摄的处理系统,该系统包括:
拍摄模块,设置为:对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
视频处理模块,设置为:将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
其中,拍摄模块,是设置为:
在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
其中,视频处理模块,设置为将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,包括:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
其中,视频处理模块,设置为将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,包括:
将所述主体图像帧序列中的每一帧主体图像叠加到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
其中,所述记录了主体和目标背景的动感视频文件由播放器循环播放。
如图3所示,本发明实施例还提供一种视频拍摄装置,包括摄像头和处理器,其中,所述摄像头设置为在所述处理器的控制下对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
所述处理器设置为控制所述摄像头进行拍摄,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体 图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
其中,所述摄像头是设置为:
在接收所述处理器到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
其中,所述第一拍摄取样速率大于第二拍摄取样速率。
其中,所述处理器是设置为以如下方式将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列:
从所述第二视频中提取一帧图像作为背景样品图像;
将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
其中,所述处理器是设置为以如下方式将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中:
将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
所述装置还可以包括显示屏,所述处理器还设置为:控制所述记录了主体和目标背景的视频文件在所述显示屏上循环播放。
应用示例
如图4所示,手机拍摄人像动感视频的过程,包括:
S101,预置拍摄参数,等待用户启动动感视频拍摄;
其中,拍摄参数可以包括以下参数的一种或多种:拍摄目标背景的慢速拍摄取样速率、对处于背景样品中的人像的拍摄时长、对背景样品的拍摄时长、和目标背景拍摄时长。
S102,检测到用户启动动感视频拍摄;
S103,侦测到对人像进行拍摄的指令,进行人像视频短片拍摄,在接收到停止拍摄的指令后停止对人像的拍摄,或者,在达到预置拍摄时长时停止对人像的拍摄,生成人像短视频;
例如,以正常拍摄取样速率(比如,1秒30帧)拍摄取景框中的人员,连续拍3秒。也即,在检测到用户按下停止按钮,或者,在达到预置拍摄时长(比如,3秒)时,停止拍摄人像,生成人像视频短片。拍摄完成后还可以向用户显示人像拍摄完成的提示信息。
其中,取景框中的背景样品可以与目标背景是同一事物或不同的事物。
S104,侦测到对背景样品进行拍摄的指令,进行背景样品视频短片拍摄,在接收到停止拍摄的指令后停止对背景样品的拍摄,或者,在达到预置拍摄时长时停止对背景样品的拍摄,生成背景样品短视频;
例如,以正常拍摄取样速率(比如,1秒30帧)拍摄取景框中的背景样品,连续拍1秒。也即,在检测到用户按下停止按钮,或者,在达到预置拍摄时长(比如,1秒)时,停止拍摄背景样品,生成背景样品视频短片。拍摄完成后还可以向用户显示背景样品拍摄完成的提示信息。
S105,侦测到对目标背景进行拍摄的指令,进行目标背景慢速拍摄,在接收到停止拍摄的指令后停止对目标背景的拍摄,或者,在达到预置拍摄时长时停止对目标背景的拍摄,生成目标背景视频;
例如,以低于正常拍摄取样速率的慢速拍摄取样速率(比如,1秒1帧)对目标背景进行拍摄,连续拍摄3分钟(180秒)。也即,在检测到用户按下 停止按钮,或者,在达到预置拍摄时长(比如,3分钟)时,停止拍摄目标背景,生成目标背景长视频。拍摄完成后还可以向用户显示目标背景拍摄完成的提示信息。
其中,慢速拍摄一般是指0.2-60秒1帧,常用1-5秒1帧。
S106,比较人像短视频和背景样品短视频,生成除拍摄主体(人像)外其余部分是透明的主体图像帧序列。
S107,对目标背景视频进行取样获得序列帧,将背景透明的人像帧序列,按次序叠加在目标背景取样帧上,生成叠加了人像的动感视频文件。
S108,以正常播放速度(比如,1秒30帧)播放动感视频文件。
其中,播放器也可以循环播放动感视频文件;
其中,目标背景的采样设置为1秒1帧,3分钟可拍摄180帧目标背景,因此,叠加了人像后的动感视频码流包含180帧图像,当播放器的播放帧频为1秒播放30帧时,180帧可播放6秒。即3分钟(180秒)的摄像在6秒内完成播放,其时间加速了30倍,实现了人像和目标背景(比如,云彩,太阳,或船舶等)快速移动的特效。
如果不用本发明的技术方案,拍摄主体(例如人员)就得在镜头前维持3分钟,这样的拍摄条件,恐怕大部分用户无法接受。因此,采用上述动感视频拍摄方案,能大大减少拍摄主体(例如,人员)在镜头前出现的时间,实现缓慢运动物体变得快速移动的特效,给手机摄像带来新的惊喜体验。
上述实施例提供的一种动感视频拍摄的处理方法和系统,通过分别拍摄主体短视频、背景样品短视频和目标背景的长视频,对主体短视频进行处理生成背景透明的主体图像帧序列,将背景透明的主体图像帧序列叠加到目标背景的长视频中,生成主体在目标背景中的动感视频文件,能够在长时间动感视频拍摄过程中,缩短拍摄主体在镜头前出现的时间,改善用户体验。
本领域普通技术人员可以理解上述实施例的全部或部分步骤可以使用计算机程序流程来实现,所述计算机程序可以存储于一计算机可读存储介质中,所述计算机程序在相应的硬件平台上(如系统、设备、装置、器件等)执行,在执行时,包括方法实施例的步骤之一或其组合。
可选地,上述实施例的全部或部分步骤也可以使用集成电路来实现,这些步骤可以被分别制作成一个个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。
上述实施例中的各装置/功能模块/功能单元可以采用通用的计算装置来实现,它们可以集中在单个的计算装置上,也可以分布在多个计算装置所组成的网络上。
上述实施例中的各装置/功能模块/功能单元以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。上述提到的计算机可读取存储介质可以是只读存储器,磁盘或光盘等。
工业实用性
本发明实施例能够在长时间视频拍摄过程中,缩短拍摄主体在镜头前出现的时间,改善用户体验。

Claims (16)

  1. 一种视频拍摄的处理方法,该方法包括:
    对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
    将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
  2. 如权利要求1所述的方法,其中:
    对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频,包括:
    在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
    在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
    在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
    其中,所述第一拍摄取样速率大于第二拍摄取样速率。
  3. 如权利要求1所述的方法,其中:
    将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,包括:
    从所述第二视频中提取一帧图像作为背景样品图像;
    将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述 第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
  4. 如权利要求1-3中任一项所述的方法,其中:
    将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中,包括:
    将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
  5. 如权利要求1所述的方法,其中:
    所述记录了主体和目标背景的视频文件由播放器循环播放。
  6. 一种视频拍摄的处理系统,该系统包括:
    拍摄模块,设置为:对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
    视频处理模块,设置为:将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第三视频中,生成记录了主体和目标背景的视频文件。
  7. 如权利要求6所述的系统,其中:
    拍摄模块,是设置为:
    在接收到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
    在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
    在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标 背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
    其中,所述第一拍摄取样速率大于第二拍摄取样速率。
  8. 如权利要求6所述的系统,其中:
    视频处理模块,是设置为以如下方式将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列:
    从所述第二视频中提取一帧图像作为背景样品图像;
    将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
  9. 如权利要求6-8中任一项所述的系统,其中:
    视频处理模块,是设置为以如下方式将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中:
    将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
  10. 如权利要求6所述的系统,其中:
    所述记录了主体和目标背景的视频文件由播放器循环播放。
  11. 一种视频拍摄装置,包括摄像头和处理器,其中,所述摄像头设置为在所述处理器的控制下对处于背景样品中的主体、背景样品和目标背景分别进行拍摄,分别生成记录主体加背景样品的第一视频、记录背景样品的第二视频和记录目标背景的第三视频;其中,所述第一视频和第二视频的拍摄时长小于所述第三视频的拍摄时长;
    所述处理器设置为控制所述摄像头进行拍摄,将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列,将所述主体图像帧序列中的每一帧主体图像依次叠加到所述第 三视频中,生成记录了主体和目标背景的视频文件。
  12. 如权利要求11所述的装置,其中:
    所述摄像头是设置为:
    在接收所述处理器到对主体进行拍摄的指令后,按照第一拍摄取样速率对处于背景样品中的主体进行拍摄,在接收到停止拍摄的指令后,生成第一视频;
    在接收到对背景样品进行拍摄的指令后,按照第一拍摄取样速率对背景样品进行拍摄,在接收到停止拍摄的指令后,生成第二视频;
    在接收到对目标背景进行拍摄的指令后,按照第二拍摄取样速率对目标背景进行拍摄,在接收到停止拍摄的指令后,生成第三视频;
    其中,所述第一拍摄取样速率大于第二拍摄取样速率。
  13. 如权利要求11所述的装置,其中:
    所述处理器是设置为以如下方式将所述第一视频和所述第二视频进行比对,从所述第一视频中提取出主体图像,生成背景透明的主体图像帧序列:
    从所述第二视频中提取一帧图像作为背景样品图像;
    将所述第一视频中的每一帧图像与所述背景样品图像进行比对,从所述第一视频的每一帧图像中去除背景样品图像,只保留主体图像,生成除主体外其余全是透明的主体图像帧序列。
  14. 如权利要求11-13中任一项所述的装置,其中:
    所述处理器是设置为以如下方式将所述主体图像帧序列中的每一帧主体图像依次插入到所述第三视频中:
    将所述主体图像帧序列中的每一帧主体图像插入到所述第三视频码流中,如所述第三视频码流还未达到最后一帧,则循环使用所述主体图像帧序列进行图像叠加。
  15. 如权利要求11所述的装置,还包括:
    显示屏,所述处理器还设置为:控制所述记录了主体和目标背景的视频 文件在所述显示屏上循环播放。
  16. 一种计算机可读存储介质,存储有程序指令,当该程序指令被执行时可实现权利要求1-5任一项所述的方法。
PCT/CN2015/073507 2014-10-28 2015-03-02 一种视频拍摄的处理方法、系统和装置 Ceased WO2015184873A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020177011342A KR20170060140A (ko) 2014-10-28 2015-03-02 비디오 촬영의 처리 방법, 시스템 및 장치
EP15803979.2A EP3200444B1 (en) 2014-10-28 2015-03-02 Method, system, and device for processing video shooting
JP2017522631A JP6413018B2 (ja) 2014-10-28 2015-03-02 ビデオキャプチャの処理方法、システム及び装置
US15/522,500 US10289914B2 (en) 2014-10-28 2015-03-02 Method, system, and device for processing video shooting

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410587144.1A CN105554361A (zh) 2014-10-28 2014-10-28 一种动感视频拍摄的处理方法和系统
CN201410587144.1 2014-10-28

Publications (1)

Publication Number Publication Date
WO2015184873A1 true WO2015184873A1 (zh) 2015-12-10

Family

ID=54766099

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/073507 Ceased WO2015184873A1 (zh) 2014-10-28 2015-03-02 一种视频拍摄的处理方法、系统和装置

Country Status (6)

Country Link
US (1) US10289914B2 (zh)
EP (1) EP3200444B1 (zh)
JP (1) JP6413018B2 (zh)
KR (1) KR20170060140A (zh)
CN (1) CN105554361A (zh)
WO (1) WO2015184873A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791448A (zh) * 2017-02-27 2017-05-31 努比亚技术有限公司 一种移动终端及拍摄方法
CN108282612B (zh) * 2018-01-12 2021-11-19 广州市百果园信息技术有限公司 视频处理方法及计算机存储介质、终端
CN109525886B (zh) * 2018-11-08 2020-07-07 北京微播视界科技有限公司 视频播放速度的控制方法、装置、设备和存储介质
CN110225241A (zh) * 2019-04-29 2019-09-10 努比亚技术有限公司 一种视频拍摄控制方法、终端及计算机可读存储介质
CN111641837A (zh) * 2019-09-24 2020-09-08 种红侠 视频画面即时互动平台和方法
CN111405199B (zh) 2020-03-27 2022-11-01 维沃移动通信(杭州)有限公司 一种图像拍摄方法和电子设备
CN111629151B (zh) * 2020-06-12 2023-01-24 北京字节跳动网络技术有限公司 视频合拍方法、装置、电子设备及计算机可读介质
CN114827695B (zh) * 2021-01-21 2023-05-30 北京字节跳动网络技术有限公司 视频录制方法、设备、电子设备及存储介质
CN116708751B (zh) * 2022-09-30 2024-02-27 荣耀终端有限公司 一种拍照时长的确定方法、装置和电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102339625A (zh) * 2011-09-20 2012-02-01 清华大学 视频对象级时域编辑方法及系统
CN103049894A (zh) * 2012-09-14 2013-04-17 深圳市万兴软件有限公司 一种图像处理的方法及其装置
CN103813106A (zh) * 2012-11-12 2014-05-21 索尼公司 图像处理设备、图像处理方法和程序
CN103903213A (zh) * 2012-12-24 2014-07-02 联想(北京)有限公司 一种拍摄方法和电子设备

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4344534B2 (ja) * 2003-04-30 2009-10-14 セコム株式会社 画像処理システム
JP2006109211A (ja) * 2004-10-07 2006-04-20 Matsushita Electric Ind Co Ltd 動画合成装置
GB2441365B (en) * 2006-09-04 2009-10-07 Nds Ltd Displaying video data
JP5313127B2 (ja) * 2007-04-02 2013-10-09 株式会社エム・ソフト 映像合成方法、映像合成システム
US20080303949A1 (en) * 2007-06-08 2008-12-11 Apple Inc. Manipulating video streams
CN101500092A (zh) * 2008-10-16 2009-08-05 黄福宝 广播级mtv合成方法
JP4807432B2 (ja) * 2009-03-31 2011-11-02 カシオ計算機株式会社 撮像装置、画像処理方法及びプログラム
US8818175B2 (en) * 2010-03-08 2014-08-26 Vumanity Media, Inc. Generation of composited video programming
JP5604916B2 (ja) * 2010-03-12 2014-10-15 カシオ計算機株式会社 画像処理装置及びプログラム
EP2619761B1 (en) * 2010-09-22 2018-06-20 NDS Limited Enriching digital photographs
US8982179B2 (en) * 2012-06-20 2015-03-17 At&T Intellectual Property I, Lp Apparatus and method for modification of telecommunication video content
US20140087877A1 (en) * 2012-09-27 2014-03-27 Sony Computer Entertainment Inc. Compositing interactive video game graphics with pre-recorded background video content
US9007531B2 (en) * 2013-08-28 2015-04-14 Vonage Network Llc Methods and apparatus for expanding a field of view in a video communication session
CN104079833A (zh) * 2014-07-02 2014-10-01 深圳市中兴移动通信有限公司 拍摄星轨视频的方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102339625A (zh) * 2011-09-20 2012-02-01 清华大学 视频对象级时域编辑方法及系统
CN103049894A (zh) * 2012-09-14 2013-04-17 深圳市万兴软件有限公司 一种图像处理的方法及其装置
CN103813106A (zh) * 2012-11-12 2014-05-21 索尼公司 图像处理设备、图像处理方法和程序
CN103903213A (zh) * 2012-12-24 2014-07-02 联想(北京)有限公司 一种拍摄方法和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3200444A4 *

Also Published As

Publication number Publication date
EP3200444A4 (en) 2017-10-25
KR20170060140A (ko) 2017-05-31
CN105554361A (zh) 2016-05-04
US10289914B2 (en) 2019-05-14
EP3200444A1 (en) 2017-08-02
JP6413018B2 (ja) 2018-10-24
EP3200444B1 (en) 2020-01-29
JP2017538331A (ja) 2017-12-21
US20170316270A1 (en) 2017-11-02

Similar Documents

Publication Publication Date Title
US10289914B2 (en) Method, system, and device for processing video shooting
US10367997B2 (en) Enriched digital photographs
US9456138B2 (en) Image processing apparatus, image processing method and computer readable recording medium having program for generating time-lapse moving image
CN108377334B (zh) 短视频拍摄方法、装置及电子终端
CN104767933B (zh) 一种具备拍照功能的便携数码设备及筛选照片的方法
CN103152521B (zh) 一种移动终端中实现景深效果的方法及移动终端
CN106713768B (zh) 人景图像合成方法、系统和计算机设备
US20120249728A1 (en) Image capturing apparatus for enabling generation of data of panoramic image with wide dynamic range
CN109922252B (zh) 短视频的生成方法及装置、电子设备
CN104539864B (zh) 记录图像的方法和装置
US9888176B2 (en) Video apparatus and photography method thereof
TW200922290A (en) Image capturing apparatus and method for providing image blur information
CN104219444A (zh) 视频拍摄的处理方法及装置
CN104394315A (zh) 一种拍摄图像的方法
WO2017080241A1 (zh) 延时摄影方法和装置
JP2007159088A5 (zh)
US10075631B2 (en) Imaging apparatus, imaging method and recording medium having program for performing self-timer shooting
JP2014187551A (ja) 画像取得装置、画像取得方法及びプログラム
CN101594459A (zh) 选择影像系统及其方法
CN104735342B (zh) 动态图像处理装置、动态图像处理方法及记录介质
CN105812642A (zh) 一种信息处理方法及电子设备
JP2010288212A (ja) カメラ及び動画編集用プログラム
CN104410782A (zh) 一种终端
WO2016175003A1 (ja) 撮影装置、撮影装置の制御方法、および制御プログラム
JP2005218126A5 (zh)

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: 15803979

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2015803979

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015803979

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 20177011342

Country of ref document: KR

Kind code of ref document: A

Ref document number: 2017522631

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 15522500

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE