WO2016110090A1 - 一种选择对焦区域的方法及装置 - Google Patents

一种选择对焦区域的方法及装置 Download PDF

Info

Publication number
WO2016110090A1
WO2016110090A1 PCT/CN2015/085354 CN2015085354W WO2016110090A1 WO 2016110090 A1 WO2016110090 A1 WO 2016110090A1 CN 2015085354 W CN2015085354 W CN 2015085354W WO 2016110090 A1 WO2016110090 A1 WO 2016110090A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
target
current picture
focus
face
Prior art date
Application number
PCT/CN2015/085354
Other languages
English (en)
French (fr)
Inventor
张本好
王琪琳
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2016110090A1 publication Critical patent/WO2016110090A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/67Focus control based on electronic image sensor signals
    • H04N23/675Focus control based on electronic image sensor signals comprising setting of focusing regions
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/61Control of cameras or camera modules based on recognised objects

Definitions

  • the present invention relates to the field of communications technologies, and in particular, to a method and apparatus for selecting a focus area.
  • Camera functionality is a very important application on smart devices such as smartphones or tablets. How to achieve higher quality photos is an important issue for camera applications.
  • the focus area selects the face area to ensure the accuracy of the face focus, and finally makes the human body image clearer.
  • the object of the present invention is to provide a method and a device for selecting a focus area, which automatically selects an active person in the scene as a focus area, so that the photographing effect of the active person in the scene is more clear, satisfies the photographing needs of different people, and brings the photograph to the photograph. pleasure.
  • an embodiment of the present invention provides a method for selecting a focus area, including: acquiring a current picture according to an operation of a user; acquiring a target position of performing a preset operation in the current picture; Defining a target area in the current picture, and acquiring face information in the target area; determining a focus area of the current picture according to the face information in the target area.
  • the preset operation is a gesture motion
  • the acquiring a target location for performing a preset operation in the current screen is specifically:
  • the preset operation is to emit a sound
  • the acquiring a target position of performing a preset operation in the current screen is specifically:
  • the target area is demarcated from the current picture according to the target location, specifically:
  • a rectangular area is demarcated from the current picture as the target area according to a preset rule.
  • the determining, according to the face information in the target area, the focus area of the current picture specifically includes:
  • the face area of the target area is selected as the focus area of the current picture
  • the statistical analysis is performed on all the face regions in the target area, and the focus area of the current picture is selected, specifically:
  • An embodiment of the present invention further provides an apparatus for selecting a focus area, including: a picture acquiring module, configured to acquire a current picture according to a user operation; and a position obtaining module configured to acquire a target position of performing a preset operation in the current picture And an area detecting module configured to: demarcate a target area from the current picture according to the target position, and acquire face information in the target area; and select a module, configured to be based on a face in the target area The information determines the focus area of the current picture.
  • the preset operation is a gesture motion
  • the location acquiring module includes:
  • a trajectory detection module configured to detect a trajectory of the gesture motion in the current picture
  • the gesture acquiring module is configured to acquire a center position of the gesture motion in the current screen according to the trajectory of the gesture motion, and determine that the center position is the target location.
  • the preset operation is to emit a sound
  • the location acquiring module includes:
  • the sound obtaining module is configured to acquire a target position in the current screen that emits a preset sound.
  • the area detecting module includes:
  • the area determining module is configured to use the target position as a center point, and define a rectangular area from the current picture as the target area according to a preset rule.
  • the selection module includes:
  • a first selection sub-module configured to detect face information of other areas in the current picture if the number of faces in the target area is 0, and select a focus area of the current picture according to face information of other areas;
  • a second selection sub-module configured to select a face area of the target area as a focus area of the current picture if the number of faces in the target area is equal to 1;
  • the third selection sub-module is configured to perform statistical analysis on all the face regions in the target region if the number of faces in the target region is greater than or equal to 2, and select a focus region of the current screen.
  • the third selection submodule includes:
  • a first unit configured to select a largest face area of all face areas in the target area as a focus area of the current picture
  • a second unit configured to select a central area of all face regions in the target area as a focus area of the current picture
  • the third unit is configured to use all the face regions in the target area as the focus areas.
  • a target area is demarcated from a current picture according to a target position in which a preset operation is performed in a current picture, where the target area is an active molecular area in a current picture;
  • the face information in the target area determines the focus area of the current picture, and the determined focus area is determined. Focusing makes the photographing effect of the active molecules in the scene clearer, and satisfying the people with different interests brings fun to the photograph and enhances the user experience.
  • FIG. 1 is a schematic diagram showing the basic steps of a method for selecting a focus area according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram showing a method for delineating a target area in a method for selecting a focus area according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram showing specific steps of an embodiment for selecting a focus area by using a gesture motion method according to an embodiment of the present invention
  • Fig. 4 is a view showing the configuration of a device for selecting a focus area in the embodiment of the present invention.
  • the embodiment of the present invention provides a method and a device for selecting a focus area according to the problem that the focus technology in the prior art cannot meet the requirements of some active molecules for photographing, and the target position of the preset operation is performed from the current screen according to the current screen. Defining a target area, which is an active molecular area in the current picture; determining a focus area of the current picture according to the face information in the target area, and determining the focus area to focus, so that the active elements in the scene The photo effect is more clear, and the people who are interested in different interests bring joy to the photo and enhance the user experience.
  • an embodiment of the present invention provides a method for selecting a focus area, including:
  • Step 11 Acquire a current picture according to a user operation
  • Step 12 Acquire a target location in the current screen for performing a preset operation
  • Step 13 Demarcate a target area from the current picture according to the target location, and acquire face information in the target area;
  • Step 14 Determine a focus area of the current picture according to the face information in the target area.
  • the method for selecting a focus area is generally applicable to a situation in which a plurality of people take a group photo to meet the needs of an active person, but is also suitable for a person taking a picture, for example, the current photographing environment is dim.
  • the face area in the current environment cannot be detected.
  • the target position can be located by performing a preset operation, and then the target area is positioned, thereby narrowing the detection area of the face detection technology, and performing face detection again, if it can be detected.
  • focus on the face area as the focus area if the face is still not detected, focus on the midpoint or target position of the target area as the focus area.
  • auxiliary technologies such as a face detection technology, a gesture body detection technology, a voice detection and positioning technology, a skin color detection technology, and the like, which are not enumerated here.
  • the current picture can be acquired by the camera.
  • the current picture is a preview image, and the current picture is only used to frame the first captured area, and the position of the person or object in the current picture can be Any change or increase or decrease.
  • the preset operation in the specific embodiment of the present invention may be gesture motion, sound generation or other motion mode. Specifically, when the preset operation is a gesture motion, correspondingly, step 12 is specifically:
  • Step 121 Detect a trajectory of gesture motion in the current picture
  • Step 122 Acquire a center position of the gesture motion in the current screen according to the trajectory of the gesture motion, and determine that the center position is the target location.
  • a method for detecting gesture motion is defined in advance, and the trajectory of the gesture motion is first detected, and then the center position of the gesture motion is obtained by a mathematical algorithm, and the center position is the target position.
  • step 12 is specifically:
  • Step 123 Acquire a target position in the current picture that emits a preset sound.
  • a radar positioning method may be used to determine a target position for emitting a preset sound; wherein the preset sound is used to prevent sounds other than the current picture from interfering with the positional positioning of the present invention, and the specific method thereof is It is not explained in detail in the present invention.
  • step 13 is specifically:
  • Step 131 Delimit a rectangular area from the current picture as the target area according to a preset rule according to a preset rule.
  • step 14 specifically includes:
  • Step 141 If the number of faces in the target area is 0, detecting face information of other areas in the current picture, and selecting a focus area of the current picture according to face information of other areas;
  • Step 142 if the number of faces in the target area is equal to 1, selecting a face area of the target area as a focus area of the current picture;
  • Step 143 If the number of faces in the target area is greater than or equal to 2, perform statistical analysis on all face regions in the target area, and select a focus area of the current picture.
  • step 143 is specifically:
  • Step 1431 selecting a largest face area among all the face areas in the target area as a focus area of the current picture.
  • Step 1432 selecting a central area of all face regions in the target area as a focus area of the current picture.
  • step 1433 all face regions in the target area are used as focus areas.
  • the gesture motion is used as a preset operation in conjunction with FIG. 3, and the present invention is implemented based on the gesture body sensing detection technology.
  • the specific steps are as follows:
  • Step 1 Obtain image data of the current screen:
  • Step 2 detecting a face in the current image scene, and performing face information recording, including area information and a number of faces COUNT1;
  • Step 4 Start a gesture detection function, detect whether there is a gesture motion in the current scene, and record the related information;
  • Step 5 Analyze the gesture detection result; if the gesture motion is not detected, perform statistical analysis on the detected face region to select an appropriate focus area.
  • the largest face may be selected as the focus area.
  • the selection method includes: selecting a central area of the left and right faces or a face of a middle size, or a plurality of areas simultaneously focusing.
  • Step 6 Analyze the face information near the gesture, and further analyze the face information near the gesture; if the face number COUNT2 is equal to 0, perform statistical analysis on the previously detected face number COUNT1 to select a suitable focus area, and select In this way, you can select the largest face as the focus area.
  • Other options include: selecting the center area of the left and right faces or the face of the middle size, or multiple areas to focus at the same time. After selecting the focus area, exit the process or go to step 1;
  • the number of faces COUNT2 is greater than 1, statistical analysis is performed on the detected COUNT2 face to select an appropriate focus area.
  • the largest face can be selected as the focus area.
  • Other options include: selecting the center area of the left and right faces or the face of the middle size, or multiple areas to focus at the same time. After selecting the focus area above, exit the process or go to step 1.
  • an embodiment of the present invention further provides an apparatus for selecting a focus area, including:
  • the screen obtaining module 41 is configured to acquire a current screen according to an operation of the user;
  • the location obtaining module 42 is configured to acquire a target location in the current screen for performing a preset operation
  • the area detecting module 43 is configured to demarcate a target area from the current picture according to the target location, and acquire face information in the target area;
  • the selection module 44 is configured to determine a focus area of the current picture according to the face information in the target area.
  • the preset operation is a gesture motion
  • the location obtaining module 42 includes:
  • a trajectory detection module configured to detect a trajectory of the gesture motion in the current picture
  • the gesture acquiring module is configured to acquire a center position of the gesture motion in the current screen according to the trajectory of the gesture motion, and determine that the center position is the target location.
  • the preset operation is to emit a sound
  • the location obtaining module 42 includes:
  • the sound obtaining module is configured to acquire a target position in the current screen that emits a preset sound.
  • the area detecting module 43 includes:
  • the area determining module is configured to use the target position as a center point, and define a rectangular area from the current picture as the target area according to a preset rule.
  • the selecting module 44 includes:
  • a first selection sub-module configured to detect face information of other areas in the current picture if the number of faces in the target area is 0, and select a focus area of the current picture according to face information of other areas;
  • a second selection sub-module configured to select a face area of the target area as a focus area of the current picture if the number of faces in the target area is equal to 1;
  • the third selection sub-module is configured to perform statistical analysis on all the face regions in the target region if the number of faces in the target region is greater than or equal to 2, and select a focus region of the current screen.
  • the third selection submodule includes:
  • a first unit configured to select a largest face area of all face areas in the target area as a focus area of the current picture
  • a second unit configured to select a central area of all face regions in the target area as a focus area of the current picture
  • the third unit is configured to use all the face regions in the target area as the focus areas.
  • a target area is demarcated from a current picture according to a target position in which a preset operation is performed in a current picture, where the target area is an active molecular area in a current picture; and according to the target area
  • the face information in the middle determines the focus area of the current picture, and the determined focus area is in focus, so that the photographing effect of the active molecules in the scene is clearer, and the people who are interested in different interests bring joy to the photograph and improve the user experience.
  • the technical solution provided by the embodiment of the present invention may be used to select a focus area, and delineate a target area from a current picture according to a target position in which a preset operation is performed in the current picture, where the target area is an active molecular area in the current picture; Determining the focus area of the current picture according to the face information in the target area, and determining the focus area to focus, so that the photographing effect of the active molecules in the scene is more clear, and satisfying the interest of different people to bring photos to the camera, Improved user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

提供一种选择对焦区域的方法及装置,该方法包括:根据用户的操作获取当前画面;获取所述当前画面中执行一预设操作的目标位置;根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。实施例根据当前画面中执行预设操作的目标位置从当前画面中划定一目标区域,该目标区域为当前画面中的活跃分子区域;再根据该目标区域中的人脸信息确定当前画面的对焦区域,以确定的该对焦区域进行对焦,使得场景里的活跃分子的拍照效果更加清晰,满足了不同兴趣的人群给拍照带来了乐趣,提升了用户体验。

Description

一种选择对焦区域的方法及装置 技术领域
本发明涉及通信技术领域,特别涉及一种选择对焦区域的方法及装置。
背景技术
相机功能是智能终端如智能手机或平板电脑上非常重要的应用。如何取得较高质量的照片,是相机应用关注的重要问题。一般在单人或多人集体拍照中,对焦区域会选取人脸区域以保证面部对焦的准确性,最终使人体图像清晰些。但是在多人集体拍照时,总有活跃分子求“关注”,利用不同与他人的动作或声音(如挥手)使自己更突出;
然而,现有技术中的对焦技术无法满足这些活跃分子对于拍集体照的要求。
发明内容
本发明的目的在于提供一种选择对焦区域的方法及装置,自动选择场景里的积极人物作为对焦区域,使得场景里的积极人物的拍照效果更加清晰,满足不同人群的拍照需求,给拍照带来乐趣。
为了达到上述目的,本发明实施例提供一种选择对焦区域的方法,包括:根据用户的操作获取当前画面;获取所述当前画面中执行一预设操作的目标位置;根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
在本发明实施例中,所述预设操作为手势运动,相应地,所述获取所述当前画面中执行一预设操作的目标位置,具体为:
检测所述当前画面中手势运动的轨迹;
根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
在本发明实施例中,所述预设操作为发出声音,相应地,所述获取所述当前画面中执行一预设操作的目标位置,具体为:
获取所述当前画面中发出一预设声音的目标位置。
在本发明实施例中,所述根据所述目标位置从所述当前画面中划定一目标区域,具体为:
以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
在本发明实施例中,所述根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域,具体包括:
若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
在本发明实施例中,所述对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域,具体为:
选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
将所述目标区域内所有人脸区域均作为对焦区域。
本发明实施例还提供一种选择对焦区域的装置,包括:画面获取模块,设置为根据用户的操作获取当前画面;位置获取模块,设置为获取所述当前画面中执行一预设操作的目标位置;区域检测模块,设置为根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;选择模块,设置为根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
在本发明实施例中,所述预设操作为手势运动,相应地,所述位置获取模块包括:
轨迹检测模块,设置为检测所述当前画面中手势运动的轨迹
手势获取模块,设置为根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
其中,所述预设操作为发出声音,相应地,所述位置获取模块包括:
声音获取模块,设置为获取所述当前画面中发出一预设声音的目标位置。
其中,所述区域检测模块包括:
区域确定模块,设置为以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
其中,所述选择模块包括:
第一选择子模块,设置为若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
第二选择子模块,设置为若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
第三选择子模块,设置为若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
其中,所述第三选择子模块包括:
第一单元,设置为选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
第二单元,设置为选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
第三单元,设置为将所述目标区域内所有人脸区域均作为对焦区域。
本发明的上述技术方案至少具有如下有益效果:
本发明实施例的选择对焦区域的方法及装置中,根据当前画面中执行预设操作的目标位置从当前画面中划定一目标区域,该目标区域为当前画面中的活跃分子区域;再根据该目标区域中的人脸信息确定当前画面的对焦区域,以确定的该对焦区域进行 对焦,使得场景里的活跃分子的拍照效果更加清晰,满足了不同兴趣的人群给拍照带来了乐趣,提升了用户体验。
附图说明
图1表示本发明实施例的选择对焦区域的方法的基本步骤示意图;
图2表示本发明实施例的选择对焦区域的方法中目标区域的划定方法示意图;
图3表示本发明实施例中采用手势运动的方式选择对焦区域的实施例的具体步骤示意图;
图4表示本发明实施例中选择对焦区域的装置的组成结构图。
具体实施方式
为使本发明要解决的技术问题、技术方案和优点更加清楚,下面将结合附图及具体实施例进行详细描述。
本发明实施例针对现有技术中的对焦技术无法满足一些活跃分子对于拍照的要求的问题,提供一种选择对焦区域的方法及装置,根据当前画面中执行预设操作的目标位置从当前画面中划定一目标区域,该目标区域为当前画面中的活跃分子区域;再根据该目标区域中的人脸信息确定当前画面的对焦区域,以确定的该对焦区域进行对焦,使得场景里的活跃分子的拍照效果更加清晰,满足了不同兴趣的人群给拍照带来了乐趣,提升了用户体验。
如图1所示,本发明实施例提供一种选择对焦区域的方法,包括:
步骤11,根据用户的操作获取当前画面;
步骤12,获取所述当前画面中执行一预设操作的目标位置;
步骤13,根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;
步骤14,根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
本发明实施例提供的选择对焦区域的方法一般适用于多人拍摄集体照时为满足活跃分子的需求的情况下,但也同时适用于一人拍照时,例如当前的拍照环境较昏暗, 无法检测中当前环境下的人脸区域,此时可通过执行预设操作定位目标位置,继而定位目标区域,从而缩小了人脸检测技术的检测区域,再一次进行人脸检测,如果能够检测到人脸,则以该人脸区域为对焦区域进行对焦;如果仍然无法检测到人脸,则可以以该目标区域的中点或目标位置作为对焦区域进行对焦。需要说明的是,本发明实施例是基于多种辅助技术实现的,比如人脸检测技术、手势体感检测技术、声音检测定位技术、肤色检测技术等等,在此不一一列举。
本发明的上述实施例中,当前画面可通过摄像头获取,具体的,该当前画面为一预览图像,当前画面仅用于框定第一拍摄的区域,在该当前画面中的人或物的位置可任意变动或增减。本发明具体实施例中的预设操作可以为手势运动、发出声音或其它运动方式。具体的,当所述预设操作为手势运动,相应地,步骤12具体为:
步骤121,检测所述当前画面中手势运动的轨迹;
步骤122,根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
具体的,本发明实施例中,预先定义一种检测手势运动的方法,先检测出手势运动的轨迹,再通过数学算法得出手势运动的中心位置,则该中心位置则为目标位置。
或者,当所述预设操作为发出声音,相应地,步骤12具体为:
步骤123,获取所述当前画面中发出一预设声音的目标位置。
具体的,本发明实施例中可采用雷达定位的方法确定发出一预设声音的目标位置;其中,采用预设声音是为了防止当前画面之外的声音干扰本发明的位置定位,其具体方法在本发明中不详细解释。
本发明的上述实施例中,步骤13具体为:
步骤131,以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
如图2所示,设目标位置的坐标为(x,y),具体的,以此坐标(x,y)为中心点划出一个矩形区域,如定义矩形区域的宽度w=1/5m,高度h=1/7m;则图2中的矩形区域即为本发明实施例的目标区域。需要说明的是,该目标区域不一定为矩形,还可以为其他任意形状,在此不一一列举。
本发明的上述实施例中,步骤14具体包括:
步骤141,若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
步骤142,若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
步骤143,若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
具体的,步骤143具体为:
步骤1431,选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
步骤1432,选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
步骤1433,将所述目标区域内所有人脸区域均作为对焦区域。
为了更清楚的描述本发明实施例的具体方案,下面结合图3采用手势运动做为预设操作,并基于手势体感检测技术实现本发明,具体步骤如下:
步骤1,获取当前画面的图像数据:
步骤2,检测当前图像场景里的人脸,并做人脸信息记录,包括区域信息和人脸数目COUNT1;
步骤3,分析检测到的人脸信息;如果当前场景没有人脸信息,则选取中心区域做对焦区域;如果当前区域人脸数目COUNT1=1,则选用当前人脸区域做对焦区域。以上两种情况满足一个选取对焦区域后退出或转到步骤1。如果检测到人脸数目大于1,转入步骤4;
步骤4,启动手势检测功能,检测当前场景中是否有手势运动,并将此相关信息记录;
步骤5,分析手势检测结果;如果没有检测手势运动,对检测到的人脸区域做统计分析选取合适的对焦区域,作为一种选择方式,可以选取最大人脸作为对焦区域。其选择方式有:选取左右人脸的中心区域或是中间大小的人脸等,也可以是多个区域同时对焦。以上选取对焦区域后退出流程或是转到步骤1;如果检测到手势运动,则 检测手势运动附近的人脸并统计手势附近的人脸数目COUNT2;具体的,先检测出手势运动的中心点(x,y),依此中心点划出一个矩形区域,可以定义w=1/5Width,h=1/7Height,如图2所示。完成手势运动附近的人脸检测后转入到步骤6;
步骤6,分析手势附近的人脸信息,对于手势附近的人脸信息做进一步分析;如果人脸数目COUNT2等于0,对之前检测到的人脸数目COUNT1做统计分析选取合适的对焦区域,其选择方式,可以选取最大人脸作为对焦区域。其他选择方式有:选取左右人脸的中心区域或是中间大小的人脸等,也可以是多个区域同时对焦。以上选取对焦区域后退出流程或是转到步骤1;
如果人脸数目COUNT2等于1,则选取当前的人脸区域作为对焦区域,然后退出流程或是转到步骤1;
如果人脸数目COUNT2大于1,对检测到的COUNT2个人脸做统计分析选取合适的对焦区域,作为一种选择方式,可以选取最大人脸作为对焦区域。其他选择方式有:选取左右人脸的中心区域或是中间大小的人脸等,也可以是多个区域同时对焦。以上选取对焦区域后退出流程或是转到步骤1。
为了更好的实现上述目的,如图4所示,本发明实施例还提供一种选择对焦区域的装置,包括:
画面获取模块41,设置为根据用户的操作获取当前画面;
位置获取模块42,设置为获取所述当前画面中执行一预设操作的目标位置;
区域检测模块43,设置为根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;
选择模块44,设置为根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
具体的,本发明上述实施例中,所述预设操作为手势运动,相应地,所述位置获取模块42包括:
轨迹检测模块,设置为检测所述当前画面中手势运动的轨迹
手势获取模块,设置为根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
具体的,本发明上述实施例中,所述预设操作为发出声音,相应地,所述位置获取模块42包括:
声音获取模块,设置为获取所述当前画面中发出一预设声音的目标位置。
具体的,本发明上述实施例中,所述区域检测模块43包括:
区域确定模块,设置为以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
具体的,本发明上述实施例中,所述选择模块44包括:
第一选择子模块,设置为若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
第二选择子模块,设置为若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
第三选择子模块,设置为若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
具体的,本发明上述实施例中,所述第三选择子模块包括:
第一单元,设置为选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
第二单元,设置为选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
第三单元,设置为将所述目标区域内所有人脸区域均作为对焦区域。
本发明实施例的选择对焦区域的方法中,根据当前画面中执行预设操作的目标位置从当前画面中划定一目标区域,该目标区域为当前画面中的活跃分子区域;再根据该目标区域中的人脸信息确定当前画面的对焦区域,以确定的该对焦区域进行对焦,使得场景里的活跃分子的拍照效果更加清晰,满足了不同兴趣的人群给拍照带来了乐趣,提升了用户体验。
需要说明的是,本发明上述实施例中提供的选择对焦区域的装置的应用上述选择对焦区域的方法的装置,则上述方法的所有实施例均适用于该装置,且均能达到相同或相似的有益效果。
以上所述是本发明的优选实施方式,应当指出,对于本技术领域的普通技术人员来说,在不脱离本发明所述原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。
工业实用性
本发明实施例提供的技术方案,可以用于选择对焦区域,根据当前画面中执行预设操作的目标位置从当前画面中划定一目标区域,该目标区域为当前画面中的活跃分子区域;再根据该目标区域中的人脸信息确定当前画面的对焦区域,以确定的该对焦区域进行对焦,使得场景里的活跃分子的拍照效果更加清晰,满足了不同兴趣的人群给拍照带来了乐趣,提升了用户体验。

Claims (12)

  1. 一种选择对焦区域的方法,包括:
    根据用户的操作获取当前画面;
    获取所述当前画面中执行一预设操作的目标位置;
    根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;
    根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
  2. 根据权利要求1所述的选择对焦区域的方法,其中,所述预设操作为手势运动,相应地,所述获取所述当前画面中执行一预设操作的目标位置,包括:
    检测所述当前画面中手势运动的轨迹;
    根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
  3. 根据权利要求1所述的选择对焦区域的方法,其中,所述预设操作为发出声音,相应地,所述获取所述当前画面中执行一预设操作的目标位置,包括:
    获取所述当前画面中发出一预设声音的目标位置。
  4. 根据权利要求1所述的选择对焦区域的方法,其中,所述根据所述目标位置从所述当前画面中划定一目标区域,包括:
    以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
  5. 根据权利要求1所述的选择对焦区域的方法,其中,所述根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域,具体包括:
    若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
    若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
    若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
  6. 根据权利要求5所述的选择对焦区域的方法,其中,所述对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域,包括:
    选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
    选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
    将所述目标区域内所有人脸区域均作为对焦区域。
  7. 一种选择对焦区域的装置,其中,包括:
    画面获取模块,设置为根据用户的操作获取当前画面;
    位置获取模块,设置为获取所述当前画面中执行一预设操作的目标位置;
    区域检测模块,设置为根据所述目标位置从所述当前画面中划定一目标区域,并获取所述目标区域中的人脸信息;
    选择模块,设置为根据所述目标区域中的人脸信息确定出所述当前画面的对焦区域。
  8. 根据权利要求7所述的选择对焦区域的装置,其中,所述预设操作为手势运动,相应地,所述位置获取模块包括:
    轨迹检测模块,设置为检测所述当前画面中手势运动的轨迹
    手势获取模块,设置为根据所述手势运动的轨迹,获取所述当前画面中手势运动的中心位置,确定所述中心位置为所述目标位置。
  9. 根据权利要求7所述的选择对焦区域的装置,其中,所述预设操作为发出声音,相应地,所述位置获取模块包括:
    声音获取模块,设置为获取所述当前画面中发出一预设声音的目标位置。
  10. 根据权利要求7所述的选择对焦区域的装置,其中,所述区域检测模块包括:
    区域确定模块,设置为以所述目标位置为中心点,按照预设划定规则从所述当前画面中划定一矩形区域作为所述目标区域。
  11. 根据权利要求7所述的选择对焦区域的装置,其中,所述选择模块包括:
    第一选择子模块,设置为若所述目标区域中人脸的数目为0,检测所述当前画面中其他区域的人脸信息,并根据其他区域的人脸信息选择当前画面的对焦区域;
    第二选择子模块,设置为若所述目标区域中人脸的数目等于1,选择所述目标区域的人脸区域作为所述当前画面的对焦区域;
    第三选择子模块,设置为若所述目标区域中人脸的数目大于或者等于2,对所述目标区域中的所有人脸区域做统计分析,选取所述当前画面的对焦区域。
  12. 根据权利要求11所述的选择对焦区域的装置,其中,所述第三选择子模块包括:
    第一单元,设置为选取所述目标区域中所有人脸区域中最大的人脸区域作为所述当前画面的对焦区域;或者
    第二单元,设置为选取所述目标区域中所有人脸区域的中心区域作为所述当前画面的对焦区域;或者
    第三单元,设置为将所述目标区域内所有人脸区域均作为对焦区域。
PCT/CN2015/085354 2015-01-05 2015-07-28 一种选择对焦区域的方法及装置 WO2016110090A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510004656.5 2015-01-05
CN201510004656.5A CN105827928A (zh) 2015-01-05 2015-01-05 一种选择对焦区域的方法及装置

Publications (1)

Publication Number Publication Date
WO2016110090A1 true WO2016110090A1 (zh) 2016-07-14

Family

ID=56355449

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/CN2015/075722 WO2016110012A1 (zh) 2015-01-05 2015-04-01 一种选择对焦区域的方法及装置、计算机可读存储介质
PCT/CN2015/085354 WO2016110090A1 (zh) 2015-01-05 2015-07-28 一种选择对焦区域的方法及装置

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/075722 WO2016110012A1 (zh) 2015-01-05 2015-04-01 一种选择对焦区域的方法及装置、计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN105827928A (zh)
WO (2) WO2016110012A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11006038B2 (en) 2018-05-02 2021-05-11 Qualcomm Incorporated Subject priority based image capture

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106231132B (zh) * 2016-09-20 2019-06-11 努比亚技术有限公司 移动终端及峰值对焦方法
US10027879B2 (en) * 2016-11-15 2018-07-17 Google Llc Device, system and method to provide an auto-focus capability based on object distance information
CN107566731A (zh) * 2017-09-28 2018-01-09 努比亚技术有限公司 一种对焦方法及终端、计算机存储介质
CN110505408B (zh) * 2019-09-12 2021-07-27 深圳传音控股股份有限公司 终端拍摄方法、装置、移动终端及可读存储介质
CN113808066A (zh) * 2020-05-29 2021-12-17 Oppo广东移动通信有限公司 图像选取方法、装置、存储介质及电子设备
WO2021258321A1 (zh) * 2020-06-24 2021-12-30 华为技术有限公司 一种图像获取方法以及装置
CN112565602A (zh) * 2020-11-30 2021-03-26 北京地平线信息技术有限公司 图像拍摄装置的控制方法、装置及计算机可读存储介质
CN113810599A (zh) * 2021-08-12 2021-12-17 惠州Tcl云创科技有限公司 一种利用ai动作识别对指定区域对焦的方法、移动终端及存储介质
CN116074624B (zh) * 2022-07-22 2023-11-10 荣耀终端有限公司 一种对焦方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101378455A (zh) * 2007-08-31 2009-03-04 卡西欧计算机株式会社 根据取得的图像确定主要拍摄物的图像区域的装置及方法
CN101547306A (zh) * 2008-03-28 2009-09-30 鸿富锦精密工业(深圳)有限公司 摄像装置及其对焦方法
US20090322936A1 (en) * 2008-06-25 2009-12-31 Altek Corporation Auto focusing method for face detection of digital imaging device
JP2011030008A (ja) * 2009-07-27 2011-02-10 Canon Inc 撮像装置
CN103945114A (zh) * 2013-01-22 2014-07-23 宏达国际电子股份有限公司 图像提取***及其方法
JP2014206711A (ja) * 2013-04-16 2014-10-30 キヤノン株式会社 撮像装置およびその制御方法

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007011200A (ja) * 2005-07-04 2007-01-18 Konica Minolta Photo Imaging Inc 撮像装置
US8055067B2 (en) * 2007-01-18 2011-11-08 DigitalOptics Corporation Europe Limited Color segmentation
CN101452181A (zh) * 2007-12-03 2009-06-10 鸿富锦精密工业(深圳)有限公司 电子装置的自动对焦***及方法
JP4582212B2 (ja) * 2008-06-24 2010-11-17 カシオ計算機株式会社 撮像装置及びプログラム
CN101770139B (zh) * 2008-12-29 2012-08-29 鸿富锦精密工业(深圳)有限公司 对焦控制***及方法
CN101567975A (zh) * 2009-05-26 2009-10-28 深圳华为通信技术有限公司 一种选取对焦区域的方法及装置
JP5459031B2 (ja) * 2010-04-13 2014-04-02 ソニー株式会社 情報処理装置、情報処理方法及びプログラム
CN102638654B (zh) * 2012-03-28 2015-03-25 华为技术有限公司 一种输出多画面的方法、装置及设备
CN103685905B (zh) * 2012-09-17 2016-12-28 联想(北京)有限公司 一种拍照方法及电子设备
CN103220465A (zh) * 2013-03-21 2013-07-24 广东欧珀移动通信有限公司 一种使用手机拍照时进行精确定位人脸图像的方法、装置及移动终端
CN104079812B (zh) * 2013-03-25 2018-08-10 联想(北京)有限公司 一种图像信息获取方法及装置
WO2015058381A1 (zh) * 2013-10-23 2015-04-30 华为终端有限公司 从连拍图像中选择图像的方法和终端
CN103763471A (zh) * 2014-01-16 2014-04-30 宇龙计算机通信科技(深圳)有限公司 数码变焦方法及装置
CN104092936B (zh) * 2014-06-12 2017-01-04 小米科技有限责任公司 自动对焦方法及装置
CN104168425B (zh) * 2014-09-02 2017-09-19 厦门美图之家科技有限公司 一种防止手持拍照抖动或对焦模糊的拍照方法与移动终端
CN105007426A (zh) * 2015-07-27 2015-10-28 厦门美图之家科技有限公司 一种基于人脸识别的对焦方法和对焦***

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101378455A (zh) * 2007-08-31 2009-03-04 卡西欧计算机株式会社 根据取得的图像确定主要拍摄物的图像区域的装置及方法
CN101547306A (zh) * 2008-03-28 2009-09-30 鸿富锦精密工业(深圳)有限公司 摄像装置及其对焦方法
US20090322936A1 (en) * 2008-06-25 2009-12-31 Altek Corporation Auto focusing method for face detection of digital imaging device
JP2011030008A (ja) * 2009-07-27 2011-02-10 Canon Inc 撮像装置
CN103945114A (zh) * 2013-01-22 2014-07-23 宏达国际电子股份有限公司 图像提取***及其方法
JP2014206711A (ja) * 2013-04-16 2014-10-30 キヤノン株式会社 撮像装置およびその制御方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11006038B2 (en) 2018-05-02 2021-05-11 Qualcomm Incorporated Subject priority based image capture
US11470242B2 (en) 2018-05-02 2022-10-11 Qualcomm Incorporated Subject priority based image capture

Also Published As

Publication number Publication date
CN105827928A (zh) 2016-08-03
WO2016110012A1 (zh) 2016-07-14

Similar Documents

Publication Publication Date Title
WO2016110090A1 (zh) 一种选择对焦区域的方法及装置
US10880495B2 (en) Video recording method and apparatus, electronic device and readable storage medium
US9262696B2 (en) Image capture feedback
US9750420B1 (en) Facial feature selection for heart rate detection
US9189611B2 (en) Adapting content and monitoring user behavior based on facial recognition
US10467498B2 (en) Method and device for capturing images using image templates
JP5276111B2 (ja) セルフ撮影の際に顔の構図を決定できるようにサポートする方法及びシステム
JP6593629B2 (ja) 画像処理装置、固体撮像素子、および電子機器
US9934823B1 (en) Direction indicators for panoramic images
US20160210752A1 (en) A method, apparatus, and system for displaying a graphical user interface
JP6104227B2 (ja) 画像識別方法および画像識別装置
US9824723B1 (en) Direction indicators for panoramic images
TW200819815A (en) Imaging apparatus, control method of imaging apparatus, and computer program
CN107395957B (zh) 拍照方法、装置、存储介质及电子设备
JP2013525906A (ja) 肌色領域及び顔領域に基づく視点検出器
CN109478227A (zh) 计算设备上的虹膜或其他身体部位识别
US10013632B2 (en) Object tracking apparatus, control method therefor and storage medium
WO2018098860A1 (zh) 照片合成方法及装置
US20180288315A1 (en) Imaging method and electronic device thereof
CN106713740A (zh) 定位跟踪摄像方法与***
US10257414B2 (en) Method and system for smart group portrait
WO2014206274A1 (en) Method, apparatus and terminal device for processing multimedia photo-capture
US9584510B2 (en) Image capture challenge access
JP6373446B2 (ja) ビデオフレームを選択するプログラム、システム、装置、及び方法
KR101414362B1 (ko) 영상인지 기반 공간 베젤 인터페이스 방법 및 장치

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: 15876594

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: 15876594

Country of ref document: EP

Kind code of ref document: A1