WO2021179830A1

WO2021179830A1 - Image composition guidance method and apparatus, and electronic device

Info

Publication number: WO2021179830A1
Application number: PCT/CN2021/074203
Authority: WO
Inventors: 薛致远; 李亚乾; 蒋燚
Original assignee: Oppo广东移动通信有限公司
Priority date: 2020-03-09
Filing date: 2021-01-28
Publication date: 2021-09-16
Also published as: CN114025097B; CN111327829A; CN114025097A; CN111327829B

Abstract

The embodiments of the present application disclose an image composition method and apparatus, and an electronic device. The image composition guidance method comprises: performing object recognition on a scene to be photographed; determining a first-type object and a second-type object from at least two recognized different types of objects; determining a common image composition positioning point according to state information of the first-type object and the second-type object; and if the image composition positioning point does not match the position of a preset image composition point, outputting prompt information for adjusting a photographing posture of an electronic device.

Description

构图指导方法、装置及电子设备Composition guidance method, device and electronic equipment

本申请要求于2020年3月9日提交中国专利局、申请号为202010159225.7、发明名称为“构图指导方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on March 9, 2020, the application number is 202010159225.7, and the invention title is "Composition Guidance Method, Apparatus, Electronic Equipment, and Storage Medium", the entire content of which is incorporated by reference In this application.

技术领域Technical field

本申请涉及电子技术领域，具体涉及一种构图指导方法、装置及电子设备。This application relates to the field of electronic technology, in particular to a composition guidance method, device and electronic equipment.

背景技术Background technique

随着科技的不断发展，诸如智能手机等电子设备上的摄像头像素越来越高，使得越来越多的用户倾向使用智能手机等电子设备进行拍照。各大电子设备厂商为满足用户的拍照需求，对电子设备硬件不断更新升级，以提高电子设备的拍照像素。但拍摄出高质量的照片，不但需要电子设备的摄像头具备较高分辨率，而且用户自身也应具备一定的专业拍摄技能，如合理地运用构图。With the continuous development of technology, the pixels of cameras on electronic devices such as smart phones are getting higher and higher, making more and more users tend to use smart phones and other electronic devices to take pictures. In order to meet users' photographing needs, major electronic equipment manufacturers continuously update and upgrade the hardware of electronic equipment to improve the photographic pixels of electronic equipment. However, to take high-quality photos, not only does the camera of the electronic device have a higher resolution, but the user himself should also have certain professional shooting skills, such as the rational use of composition.

发明内容Summary of the invention

本申请实施例提供一种构图指导方法、装置及电子设备，能够指导用户在拍摄时合理构图。The embodiments of the present application provide a composition guidance method, device, and electronic equipment, which can guide a user to rationally compose a picture when shooting.

第一方面，本申请实施例提供了一种构图指导方法，应用于电子设备，其中，构图指导方法包括：In the first aspect, an embodiment of the present application provides a composition guidance method, which is applied to an electronic device, wherein the composition guidance method includes:

对待拍摄场景进行对象识别；Perform object recognition on the scene to be shot;

当识别出所述待拍摄场景中包含至少两类不同类别的对象时，确定出所述待拍摄场景中的第一类对象和第二类对象；When it is recognized that the scene to be photographed contains at least two types of objects of different categories, determining the first type of object and the second type of object in the scene to be photographed;

根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点；Determining a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

当所述构图定位点与预设构图点的位置不匹配时，输出调整所述电子设备拍摄姿态的提示信息。When the composition positioning point does not match the position of the preset composition point, outputting prompt information for adjusting the shooting posture of the electronic device.

第二方面，本申请实施例提供了一种构图指导装置，应用于电子设备，其中，构图指导装置包括：In a second aspect, an embodiment of the present application provides a composition guidance device, which is applied to an electronic device, wherein the composition guidance device includes:

对象识别模块，用于对待拍摄场景进行对象识别；The object recognition module is used to perform object recognition on the scene to be photographed;

第一确定模块，用于当识别出所述待拍摄场景中包含至少两类不同类别的对象时，确定出所述待拍摄场景中的第一类对象和第二类对象；The first determining module is configured to determine the first type of object and the second type of object in the to-be-shot scene when it is recognized that the to-be-shot scene contains at least two types of objects of different types;

第二确定模块，用于根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点；A second determining module, configured to determine a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

构图指导模块，用于当所述构图定位点与预设构图点的位置不匹配时，输出调整所述电子设备拍摄姿态的提示信息。The composition guidance module is configured to output prompt information for adjusting the shooting posture of the electronic device when the position of the composition positioning point does not match the preset composition point.

第三方面，本申请实施例提供了一种电子设备，包括处理器和存储器，所述存储器中存储有计算机程序，其中，所述处理器通过调用所述存储器中存储的所述计算机程序，用于执行：In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, and a computer program is stored in the memory, wherein the processor uses the computer program stored in the memory to To execute:

附图说明Description of the drawings

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，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。In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

图1为本申请实施例提供的构图指导方法的第一种流程示意图。FIG. 1 is a schematic diagram of the first flow of a composition guidance method provided by an embodiment of this application.

图2为本申请实施例提供的构图指导方法的第二种流程示意图。FIG. 2 is a schematic diagram of a second flow of a composition guidance method provided by an embodiment of this application.

图3为本申请实施例提供的预览图像的示意图。FIG. 3 is a schematic diagram of a preview image provided by an embodiment of the application.

图4为本申请实施例提供的拍摄预览画面的示意图。FIG. 4 is a schematic diagram of a shooting preview screen provided by an embodiment of the application.

图5为本申请实施例提供的构图指导装置的第一种结构示意图。FIG. 5 is a schematic diagram of the first structure of a composition guidance device provided by an embodiment of the application.

图6为本申请实施例提供的构图指导装置的第二种结构示意图。FIG. 6 is a schematic diagram of a second structure of a composition guidance device provided by an embodiment of the application.

图7为本申请实施例提供的构图指导装置的第三种结构示意图。FIG. 7 is a schematic diagram of a third structure of a composition guidance device provided by an embodiment of the application.

图8为本申请实施例提供的电子设备的第一种结构示意图。FIG. 8 is a schematic diagram of the first structure of an electronic device provided by an embodiment of this application.

图9为本申请实施例提供的电子设备的第二种结构示意图。FIG. 9 is a schematic diagram of a second structure of an electronic device provided by an embodiment of the application.

具体实施方式Detailed ways

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、完整的描述。显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有付出创造性劳动前提下所获得的所有实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present invention.

本发明的说明书和权利要求书以及上述附图中的术语“第一”、“第二”、“第三”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应当理解，这样描述的对象在适当情况下可以互换。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含。例如，包含了一系列步骤的过程、方法或包含了一系列模块或单元的装置、终端、***不必限于清楚地列出的那些步骤或模块和单元，还可以包括没有清楚地列出的步骤或模块或单元，也可以包括对于这些过程、方法、装置、终端或***固有的其它步骤或模块或单元。The terms "first", "second", "third", etc. (if any) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and not necessarily used to describe a specific order Or precedence. It should be understood that the objects described in this way can be interchanged under appropriate circumstances. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, or a device, terminal, or system that includes a series of steps, or a device, terminal, or system including a series of modules or units is not necessarily limited to those clearly listed steps or modules and units, and may also include steps or modules that are not clearly listed. Modules or units may also include other steps or modules or units inherent to these processes, methods, devices, terminals or systems.

本申请实施例首先提供一种构图指导方法，该构图指导方法应用于电子设备。该构图指导方法的执行主体可以是本申请实施例提供的构图指导装置，或者集成了该构图指导装置的电子设备，该构图指导装置可以采用硬件或者软件的方式实现，电子设备可以是智能手机、平板电脑、掌上电脑、笔记本电脑、或者台式电脑等配置有处理器而具有处理能力的设备。The embodiment of the present application first provides a composition guidance method, which is applied to an electronic device. The execution subject of the composition guidance method may be the composition guidance device provided in the embodiment of the present application, or an electronic device integrated with the composition guidance device. The composition guidance device may be implemented in hardware or software. The electronic device may be a smart phone, Tablet computers, handheld computers, notebook computers, or desktop computers are equipped with processors and have processing capabilities.

本申请实施例提供一种构图指导方法，包括：The embodiment of the present application provides a composition guidance method, including:

当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象；When it is recognized that the scene to be photographed contains at least two types of objects of different categories, the first type of object and the second type of object in the scene to be photographed are determined;

根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；Determine a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。When the positioning point of the composition does not match the position of the preset composition point, a prompt message for adjusting the shooting posture of the electronic device is output.

在一实施例中，所述对待拍摄场景进行对象识别包括：In an embodiment, the performing object recognition on the scene to be photographed includes:

获取所述待拍摄场景的预览图像；Acquiring a preview image of the scene to be shot;

对所述预览图像进行语义分割，得到所述预览图像中每一个像素点所属的对象类别；Performing semantic segmentation on the preview image to obtain the object category to which each pixel in the preview image belongs;

根据所述预览图像中每一个像素点所属的对象类别识别出所述预览图像中的对象。The object in the preview image is identified according to the object category to which each pixel in the preview image belongs.

在一实施例中，所述根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点之前，还包括：In an embodiment, before determining a common composition anchor point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object, the method further includes:

确定所述第一类对象在所述预览图像中对应的第一显示区域，以及确定所述第二类对象在所述预览图像中对应的第二显示区域；Determining a first display area corresponding to the first type object in the preview image, and determining a second display area corresponding to the second type object in the preview image;

当所述第一显示区域在所述预览图像中的第一面积占比大于第一预设比例，且所述第二显示区域在所述预览图像中的第二面积占比大于第二预设比例时，根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点。When the proportion of the first area of the first display area in the preview image is greater than the first preset proportion, and the proportion of the second area of the second display area in the preview image is greater than the second preset In the case of a ratio, a common composition positioning point is determined for the first-type object and the second-type object according to the state information of the first-type object and the second-type object.

在一实施例中，所述根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点包括：In an embodiment, the determining a common composition anchor point for the first-type object and the second-type object according to the state information of the first-type object and the second-type object includes:

确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点；Determining a first center point of the first display area, and determining a second center point of the second display area;

获取所述第一显示区域与所述第二显示区域的面积比值；Acquiring an area ratio of the first display area to the second display area;

根据所述第一中心点、所述第二中心点以及所述面积比值确定所述构图定位点，所述构图定位点到所述第一中心点与所述第二中心点的距离之比等于所述面积比值。The composition positioning point is determined according to the first center point, the second center point, and the area ratio, and the ratio of the distance from the composition positioning point to the first center point to the second center point is equal to The area ratio.

在一实施例中，所述确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点包括：In an embodiment, the determining the first center point of the first display area and determining the second center point of the second display area includes:

获取所述第一显示区域中所有像素点的第一坐标值均值，将所述第一坐标值均值对应的像素点确定为所述第一中心点；Acquiring an average value of the first coordinate values of all pixels in the first display area, and determining a pixel point corresponding to the average value of the first coordinate value as the first center point;

获取所述第二显示区域中所有像素点的第二坐标值均值，将所述第二坐标值均值对应的像素点确定为所述第二中心点。The second coordinate value average value of all pixels in the second display area is acquired, and the pixel point corresponding to the second coordinate value average value is determined as the second center point.

在一实施例中，所述获取所述第一显示区域与所述第二显示区域的面积比值包括：In an embodiment, the obtaining the area ratio of the first display area to the second display area includes:

获取所述第一显示区域与所述第二显示区域包含的像素点数量；Acquiring the number of pixels included in the first display area and the second display area;

计算出所述第一显示区域与所述第二显示区域包含的像素点数量比值；Calculating a ratio of the number of pixels contained in the first display area and the second display area;

将所述像素点数量比值作为所述面积比值。The ratio of the number of pixels is used as the area ratio.

在一实施例中，所述输出调整所述电子设备拍摄姿态的提示信息包括：In an embodiment, the output of the prompt information for adjusting the shooting posture of the electronic device includes:

在电子设备的拍摄预览界面上显示所述构图定位点与所述预设构图点；Displaying the composition positioning point and the preset composition point on the shooting preview interface of the electronic device;

在所述预览界面上显示所述构图定位点向所述预设构图点的移动方向，输出向所述移动方向调整所述电子设备拍摄姿态的提示信息。The movement direction of the composition positioning point to the preset composition point is displayed on the preview interface, and prompt information for adjusting the shooting posture of the electronic device in the movement direction is output.

在一实施例中，所述对待拍摄场景进行对象识别之后，还包括：In an embodiment, after the object recognition is performed on the scene to be photographed, the method further includes:

对于识别出的各个对象，在所述拍摄预览界面上分别标注各对象的类别以及属于所述类别的概率。For each identified object, the category of each object and the probability of belonging to the category are respectively marked on the shooting preview interface.

在后台判断所述预设构图点相对所述构图定位点的相对位置；Determine the relative position of the preset composition point with respect to the composition positioning point in the background;

语音提示向着该相对位置调整电子设备的拍摄姿态。The voice prompt adjusts the shooting posture of the electronic device toward the relative position.

在一实施例中，所述输出调整所述电子设备拍摄姿态的提示信息之后，还包括：In an embodiment, after outputting the prompt information for adjusting the shooting posture of the electronic device, the method further includes:

当调整至所述预设定位点与预设构图点的位置匹配时，对所述待拍摄场景进行拍摄，得到所述待拍摄场景的成像图像。When the position of the preset positioning point and the preset composition point are adjusted to match, the scene to be photographed is photographed to obtain an imaging image of the scene to be photographed.

请参照图1，图1为本申请实施例提供的构图指导方法的流程示意图。该构图指导方法应用于本申请实施例提供的电子设备，本申请实施例提供的构图指导方法可以包括以下步骤：Please refer to FIG. 1, which is a schematic flowchart of a composition guidance method provided by an embodiment of the application. The composition guidance method is applied to the electronic device provided in the embodiment of the present application, and the composition guidance method provided in the embodiment of the present application may include the following steps:

101，对待拍摄场景进行对象识别。101. Perform object recognition on the scene to be shot.

电子设备可以包括一个或多个摄像头，通过摄像头对待拍摄场景进行拍摄或者预览。电子设备还可以包括取景框，摄像头对待拍摄场景进行拍摄或者预览的画面可以显示在取景框中。电子设备在实现拍摄或预览功能时，摄像头拍摄或者预览的画面也可以显示在显示屏上。此时，电子设备的显示屏作为取景框。The electronic device may include one or more cameras, through which the scene to be shot is photographed or previewed. The electronic device may also include a viewfinder frame, and a picture of the scene to be photographed or previewed by the camera may be displayed in the viewfinder frame. When the electronic device realizes the function of shooting or previewing, the image captured or previewed by the camera can also be displayed on the display screen. At this time, the display screen of the electronic device serves as a viewfinder frame.

在一实施例中，电子设备在对待拍摄场景进行对象识别时，可以获取待拍摄场景的预览图像，通过识别预览图像识别待拍摄场景中的对象。其中，可以通过语义分割的方式对待拍摄场景进行对象识别。例如，对预览图像进行语义分割之前，预先在语义分割数据集上训练语义分割模型，在对预览图像进行语义分割时，将预览图像输入预先训练好的语义分割模型中进行语义分割。In one embodiment, when the electronic device performs object recognition on the scene to be shot, it can obtain a preview image of the scene to be shot, and recognize the object in the scene to be shot by recognizing the preview image. Among them, object recognition can be performed on the scene to be shot by means of semantic segmentation. For example, before semantic segmentation is performed on the preview image, the semantic segmentation model is pre-trained on the semantic segmentation data set, and when the preview image is semantically segmented, the preview image is input into the pre-trained semantic segmentation model for semantic segmentation.

例如，语义分割模型可以采用双侧分割网络(Bilateral Segmentation Network，BiSeNet) 算法。在将预览图像输入语义分割模型之前，先训练语义分割模型。BiSeNet算法作为一种基于卷积神经网络模型的实时语义分割算法，可以对输入的图像的每一个像素给出一个分类，从而精确标识出图像中的每一个物体的像素范围。在训练语义分割模型时，将图像输入BiSeNet算法，BiSeNet算法将图像同时送入两个路径进行计算。其中一个路径为步长小的空间路径，用于保留空间信息，从而生成高分辨率的特征图；另一个路径为快速下采样的语义路径，能够最大限度地获取感受野，并生成粗粒度分割图。空间路径保留输入图像的高分辨率，而语义路径则保证语义分割的速度。通过对两个路径的输出图像进行融合，将空间路径的高分辨率图像得到的空间信息融入语义路径的粗粒度分割图中，优化分割结果，从而同时兼顾语义分割的精度和速度，达到实时语义分割的效果。For example, the semantic segmentation model can adopt a Bilateral Segmentation Network (BiSeNet) algorithm. Before inputting the preview image into the semantic segmentation model, the semantic segmentation model is trained first. As a real-time semantic segmentation algorithm based on the convolutional neural network model, the BiSeNet algorithm can give a classification to each pixel of the input image, thereby accurately identifying the pixel range of each object in the image. When training the semantic segmentation model, the image is input to the BiSeNet algorithm, and the BiSeNet algorithm sends the image to two paths for calculation at the same time. One of the paths is a spatial path with a small step size, which is used to retain spatial information to generate high-resolution feature maps; the other path is a semantic path with fast down-sampling, which can maximize the receptive field and generate coarse-grained segmentation picture. The spatial path preserves the high resolution of the input image, while the semantic path guarantees the speed of semantic segmentation. By fusing the output images of the two paths, the spatial information obtained from the high-resolution images of the spatial path is integrated into the coarse-grained segmentation map of the semantic path, and the segmentation result is optimized, thereby taking into account the accuracy and speed of the semantic segmentation at the same time, and achieving real-time semantics The effect of segmentation.

在一实施例中，电子设备探测待拍摄场景中各个对象的红外辐射能量，通过光电转换、信号处理等手段，将待拍摄场景中各对象的红外辐射能量转化为待拍摄场景的红外热成像图。不同对象的表面温度不同，红外热辐射情况也不同，在红外热成像图上的成像情况也不同，因此在红外热成像图上可以用不同颜色反映各个对象表面不同的温度分布。红外热成像图上各个对象表面不同的温度分布的表示方法有多种，可选的，可以采用灰度图来表示，对象表面温度越高，红外热成像图上待分析目标的颜色越亮。通过分析红外热成像图像上的颜色分布，就能识别出待拍摄场景中的对象。通过红外热成像技术将对象发出的热辐射转换成可见光的图像，即使在漆黑的夜里也可以准确识别出待拍摄场景中的对象，而不受外界环境亮度的影响。In one embodiment, the electronic device detects the infrared radiation energy of each object in the scene to be photographed, and converts the infrared radiation energy of each object in the scene to be photographed into an infrared thermal imaging image of the scene to be photographed by means of photoelectric conversion and signal processing. . The surface temperature of different objects is different, the infrared heat radiation conditions are also different, and the imaging conditions on the infrared thermal imaging map are also different. Therefore, different colors can be used to reflect the different temperature distributions on the surface of each object on the infrared thermal imaging map. There are many ways to express different temperature distributions on the surface of each object on the infrared thermal imaging map. Optionally, it can be represented by a grayscale image. The higher the surface temperature of the object, the brighter the color of the target to be analyzed on the infrared thermal imaging map. By analyzing the color distribution on the infrared thermal imaging image, the objects in the scene to be photographed can be identified. Through infrared thermal imaging technology, the thermal radiation emitted by the object is converted into a visible light image, even in the dark night, the object in the scene to be photographed can be accurately identified without being affected by the brightness of the external environment.

待拍摄场景的画面信息可以显示在拍摄预览界面上，用户通过拍摄预览界面实时观察待拍摄场景，从而对摄像头的拍摄姿势进行调整，以获取更好的拍照效果。或者，也可以不对待拍摄场景的画面信息进行显示，而是直接在后台对画面信息进行对象识别。其中，待拍摄场景的画面信息包括但不限于上述举例的预览图像、红外热成像图的形式。The picture information of the scene to be shot can be displayed on the shooting preview interface, and the user observes the scene to be shot in real time through the shooting preview interface, so as to adjust the shooting posture of the camera to obtain a better shooting effect. Or, instead of displaying the screen information of the scene to be shot, the screen information can be directly identified in the background. Wherein, the picture information of the scene to be photographed includes but is not limited to the preview image and the infrared thermal imaging map in the above examples.

在一些实施方式中，在对待拍摄场景进行对象识别，识别出待拍摄场景中的对象后，可以在拍摄预览界面对各对象进行标注。例如，当从待拍摄场景中识别出两个人、一只狗和一棵树时，在拍摄预览界面将两个人分别单独框选起来，标注“人”；将一只狗单独框选起来，标注“狗”；将一棵树单独框选起来，标注“树”。可选的，在标注时，还可以标注对象属于该类别的概率。例如，两个人中有一个被识别为人的对象离得较近，根据算法判断出该对象属于“人”的概率为95％，则在标注该对象为“人”时，一并标注上概率“95％”；而另一个对象被识别为人的对象离得较远，根据算法判断出该对象属于“人”的概率只有50％，则在标注该对象为“人”时，一并标注上概率“50％”。如此，将对象识别的结果可视化，可以带给用户更加智能化的体验。In some embodiments, after object recognition is performed on the scene to be photographed and the objects in the scene to be photographed are identified, each object may be marked on the photographing preview interface. For example, when two people, a dog, and a tree are identified from the scene to be shot, the two people are individually selected in the shooting preview interface and marked as "person"; and a dog is individually selected and marked "Dog"; select a tree by box and mark it as "tree". Optionally, when labeling, the probability that the object belongs to the category can also be labeled. For example, if there is an object recognized as a human being in two persons, the probability that the object belongs to "person" is 95% according to the algorithm. Then when the object is labeled as "person", the probability " 95%"; and the object where another object is recognized as a person is far away. According to the algorithm, the probability that the object belongs to a "person" is only 50%. When the object is labeled as a "person", the probability is also marked "50%". In this way, visualizing the results of object recognition can bring users a more intelligent experience.

102，当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象。102. When it is recognized that the scene to be photographed includes at least two types of objects of different types, determine the first type of object and the second type of object in the scene to be photographed.

在对待拍摄场景进行对象识别时，识别出各对象所属的类别。其中类别可以包括人物类别和物体类别，物体类别中又可划分为不同的物体类别，例如，植物类别、建筑类别等。可以理解的是，在对待拍摄场景进行对象识别时，可能未识别到对象，也可能识别出一类、两类或者多类对象。When performing object recognition on the scene to be photographed, the category to which each object belongs is recognized. The categories can include character categories and object categories, and the object categories can be divided into different object categories, for example, plant categories, building categories, and so on. It is understandable that when performing object recognition on the scene to be photographed, the object may not be recognized, or one, two or more types of objects may be recognized.

当识别出待拍摄场景中包含两类或两类以上不同类别的对象时，从中选择两类对象作为待拍摄场景中的第一类对象和第二类对象，电子设备将第一类对象和第二类对象作为主要的构图对象来指导构图。When it is recognized that the scene to be photographed contains two or more types of objects of different categories, the two types of objects are selected as the first type of object and the second type of object in the scene to be photographed, and the electronic device combines the first type of object and the second type of object. The second type of object is used as the main composition object to guide the composition.

其中，第一类对象和第二类对象可以分别为人物对象和物体对象，也可以为两类不同的物体对象。并且，这里的第一类对象和第二类对象只是为了区分不同类别的对象，而不用于描述特定的先后顺序。例如，可以将人物对象确定为第一类对象，将某个物体对象确定为第二类对象，也可以将某个物体对象确定为第一类对象，将人物对象确定为第二类对象。Among them, the first type of object and the second type of object may be a person object and an object object, respectively, or they may be two different types of object objects. Moreover, the first type of object and the second type of object here are only used to distinguish objects of different types, and not used to describe a specific sequence. For example, a person object may be determined as a first type object, and a certain object object may be determined as a second type object, or a certain object object may be determined as a first type object, and a person object may be determined as a second type object.

确定出待拍摄场景中的第一类对象和第二类对象的方式可以有多种。在一实施例中，可以获取待拍摄场景的预览图像或红外热成像图，将预览图像或红外热成像图显示在拍摄预览界面上，通过接收用户对拍摄预览界面的触控操作，由用户从各对象中选择出第一类对象和第二类对象。例如，接收用户对拍摄预览界面的两次触控操作，将两次触控操作所对应的对象确定为第一类对象和第二类对象。There are many ways to determine the first type of object and the second type of object in the scene to be shot. In one embodiment, a preview image or infrared thermal imaging image of the scene to be shot can be acquired, and the preview image or infrared thermal imaging image can be displayed on the shooting preview interface. By receiving the user's touch operation on the shooting preview interface, the user can download The first type of object and the second type of object are selected from each object. For example, two touch operations of the user on the shooting preview interface are received, and the objects corresponding to the two touch operations are determined as the first type of object and the second type of object.

或者，电子设备也可以根据各类对象的大小、位置等信息自动选择出第一类对象和第二类对象。Alternatively, the electronic device can also automatically select the first type of object and the second type of object based on the size and location of various types of objects.

在一实施方式中，获取待拍摄场景中各类对象与电子设备的距离(当同类对象中包含多个对象时，将多个对象中与电子设备最近的距离确定为该类对象与电子设备的距离)，将待拍摄场景中距离电子设备最近的两类对象作为第一类对象和第二类对象。In one embodiment, the distance between various objects in the scene to be photographed and the electronic device is obtained (when multiple objects of the same type are included, the closest distance between the multiple objects and the electronic device is determined as the distance between the object and the electronic device. Distance), the two types of objects closest to the electronic device in the scene to be photographed are regarded as the first type of object and the second type of object.

在一实施方式中，将人物对象确定为第一类对象，并根据预览图像获取不同类别的物体对象所对应的像素点数量，将对应像素点数量最多的物体对象确定为第二类对象。或者，将对应像素点数量最多的物体对象确定为第一类对象，将除第一类对象以外对应像素点数量最多的物体对象确定为第二类对象，等等。In one embodiment, a person object is determined as the first type of object, and the number of pixels corresponding to different types of object objects is acquired according to the preview image, and the object with the largest number of pixels is determined as the second type of object. Alternatively, the object with the largest number of corresponding pixels is determined as the first type of object, and the object with the largest number of corresponding pixels other than the first type of object is determined as the second type of object, and so on.

在一实施方式中，将人物对象确定为第一类对象，并根据红外热成像图获取不同类别的物体对象所对应的表面温度，将对应表面温度最高的物体对象确定为第二类对象。或者，将对应表面温度最高的物体对象确定为第一类对象，将除第一类对象以外对应表面温度最高的物体对象确定为第二类对象，等等。In one embodiment, the human object is determined as the first type of object, and the surface temperatures corresponding to different types of objects are obtained according to the infrared thermal imaging images, and the object with the highest surface temperature is determined as the second type of object. Or, the object with the highest corresponding surface temperature is determined as the first type of object, and the object with the highest corresponding surface temperature other than the first type of object is determined as the second type of object, and so on.

关于确定出待拍摄场景中的第一类对象和第二类对象，还可以使用其它多种方法，此处不一一赘述。With regard to determining the first type of object and the second type of object in the scene to be photographed, various other methods can also be used, which will not be repeated here.

103，根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点。103. Determine a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object.

其中，状态信息可以为第一类对象和第二类对象的大小、距离电子设备的距离、或者第一类对象和第二类对象的相对位置等。若通过摄像头获取了待拍摄场景的预览图像或红外热成像图等图像，则状态信息也可以为第一类对象和第二类对象在预览图像或者红外热成像图上的位置、面积等信息。Wherein, the status information may be the size of the first type of object and the second type of object, the distance from the electronic device, or the relative position of the first type of object and the second type of object, and so on. If an image such as a preview image or an infrared thermal imaging map of the scene to be photographed is acquired through the camera, the status information may also be information such as the position and area of the first type of object and the second type of object on the preview image or the infrared thermal imaging map.

由于第一类对象和第二类对象为两类不同的对象，为方便指导构图，为第一类对象和第二类对象确定出共同的构图定位点，用来代表第一类对象和第二类对象作为整体时的位置。之后，便可以通过对比该构图参考点与预设构图点的位置，决定是否需要在拍摄时指导用户构图。Since the first type of object and the second type of object are two different types of objects, in order to facilitate the composition guide, a common composition anchor point is determined for the first type of object and the second type of object to represent the first type of object and the second type of object. The position of the class object as a whole. After that, you can compare the position of the composition reference point with the preset composition point to determine whether it is necessary to guide the user in the composition when shooting.

在一实施例中，第一类对象和第二类对象的状态信息可以为第一类对象和第二类对象在预览图像中的位置信息。在预览图像中确定出第一类对象对应的第一显示区域和第二类对象对应的第二显示区域，获取第一显示区域中所有像素点的第一坐标值均值，将第一坐标值均值对应的像素点确定为第一中心点；获取第二显示区域中所有像素点的第二坐标值均值，将第二坐标值均值对应的像素点确定为第二中心点，将第一中心点和第二中心点连线的中点确定为第一类对象和第二类对象构图定位点。In an embodiment, the state information of the first-type object and the second-type object may be position information of the first-type object and the second-type object in the preview image. Determine the first display area corresponding to the first type of object and the second display area corresponding to the second type of object in the preview image, obtain the average value of the first coordinate values of all pixels in the first display area, and calculate the average value of the first coordinate value The corresponding pixel point is determined as the first center point; the second coordinate value average value of all pixels in the second display area is obtained, the pixel point corresponding to the second coordinate value average value is determined as the second center point, and the first center point and The midpoint of the line connecting the second center point is determined as the positioning point of the composition of the first type of object and the second type of object.

或者，在预览图像中用一矩形框将第一类对象从最上到最下、从最左到最右地框选起来，将该矩形的几何中心点确定为第一中心点，同理确定出第二类对象的第二中心点，将第一中心点和第二中心点连线的中点确定为第一类对象和第二类对象构图定位点。Or, in the preview image, use a rectangular frame to select the objects of the first category from top to bottom, and from left to right, and determine the geometric center point of the rectangle as the first center point, and determine it in the same way. The second center point of the second type of object determines the midpoint of the line connecting the first center point and the second center point as the positioning point of the composition of the first type of object and the second type of object.

104，当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。104. When the position of the composition positioning point does not match the position of the preset composition point, output prompt information for adjusting the shooting posture of the electronic device.

其中，预设构图点为预先设置的位置参考点，预设构图点可以为待拍摄场景的画面中心点，也即拍摄预览界面的几何中心点，也即预览图像或者红外热成像图的几何中心点，当然，也可以为其他位置的预设构图点，只要构图定位点与预设构图点的位置匹配时，拍摄的图像构图美观即可。Among them, the preset composition point is a preset position reference point, and the preset composition point may be the center point of the scene to be shot, that is, the geometric center point of the shooting preview interface, that is, the geometric center of the preview image or the infrared thermal image. The point, of course, can also be a preset composition point in other positions, as long as the composition positioning point matches the position of the preset composition point, and the captured image has a beautiful composition.

位置的匹配可以是二者位置相同，也可以是二者之间的距离小于预设阈值，或者二者的相对位置满足一定条件，例如，构图定位点位于预设构图点上方预设距离处视为位置相匹配。需要说明的是，无论构图定位点与预设构图点的位置是否匹配，都可以在电子设备的拍摄预览界面上显示构图定位点与预设构图点让用户看到，当然，也可以不显示在拍摄预览界面上。The position matching can be that the two positions are the same, or the distance between the two is less than the preset threshold, or the relative position of the two meets certain conditions, for example, the composition positioning point is located at the preset distance above the preset composition point. Matches for the location. It should be noted that regardless of whether the position of the composition positioning point matches the preset composition point, the composition positioning point and the preset composition point can be displayed on the shooting preview interface of the electronic device for the user to see, of course, it may not be displayed in the On the shooting preview interface.

在一实施例中，若构图定位点是根据第一类对象和第二类对象在摄像头采集到的图像(如预览图像、红外热成像图等)中的状态信息确定出来的，则可以先在图像上标记构图定位点，再根据图像与拍摄预览界面的对应关系，将构图定位点对应标记到拍摄预览界面，使用户可以在拍摄预览界面上看到代表第一类对象和第二类对象整***置的构图定位点。电子设备对比构图定位点与预设构图点在拍摄预览界面上的位置，当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息，指导用户构图。即，当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息的步骤可以包括：In one embodiment, if the composition positioning point is determined based on the status information of the first type of object and the second type of object in the image (such as preview image, infrared thermal imaging, etc.) collected by the camera, you can first Mark the composition anchor point on the image, and then mark the composition anchor point to the shooting preview interface according to the corresponding relationship between the image and the shooting preview interface, so that the user can see the entirety of the first type of object and the second type of object on the shooting preview interface Position the composition anchor point. The electronic device compares the position of the composition anchor point and the preset composition point on the shooting preview interface, and when the position of the composition anchor point does not match the preset composition point, it outputs prompt information for adjusting the shooting posture of the electronic device to guide the user in the composition. That is, when the position of the composition positioning point does not match the position of the preset composition point, the step of outputting prompt information for adjusting the shooting posture of the electronic device may include:

在电子设备的拍摄预览界面上显示构图定位点与预设构图点；Display the composition positioning point and the preset composition point on the shooting preview interface of the electronic device;

在预览界面上显示构图定位点向预设构图点的移动方向，输出向移动方向调整电子设备拍摄姿态的提示信息。The moving direction of the composition anchor point to the preset composition point is displayed on the preview interface, and the prompt information for adjusting the shooting posture of the electronic device in the moving direction is output.

若构图定位点与预设构图点的位置不匹配，电子设备可以在拍摄预览界面上提示用户该如何调整电子设备的拍摄姿态，使得构图定位点与预设构图点的位置匹配。而在拍摄预览界面上显示构图定位点向预设构图点的移动方向，能够使用户在拍摄预览界面上直观地看到如何调整电子设备的拍摄姿态。例如，向着该移动方向移动电子设备，或者向着该移动方向调整电子设备的拍摄角度等。If the position of the composition positioning point does not match the preset composition point, the electronic device may prompt the user on the shooting preview interface how to adjust the shooting posture of the electronic device, so that the composition positioning point matches the position of the preset composition point. Displaying the moving direction of the composition positioning point to the preset composition point on the shooting preview interface enables the user to intuitively see how to adjust the shooting posture of the electronic device on the shooting preview interface. For example, the electronic device is moved in the moving direction, or the shooting angle of the electronic device is adjusted in the moving direction.

在一实施方式中，调整电子设备拍摄姿态的提示信息也可以为语音的提示信息，此时即使不在拍摄预览界面上显示待拍摄场景的画面或者构图定位点、预设构图点，电子设备也可以指导用户进行构图。其中，电子设备可以在后台判断预设构图点相对构图定位点的相对位置，并语音提示用户向着该相对位置调整电子设备的拍摄姿态。In one embodiment, the prompt information for adjusting the shooting posture of the electronic device can also be voice prompt information. At this time, even if the image of the scene to be shot or the composition positioning point or the preset composition point is not displayed on the shooting preview interface, the electronic device can also Instruct the user to compose the picture. The electronic device can determine the relative position of the preset composition point relative to the composition positioning point in the background, and voice prompt the user to adjust the shooting posture of the electronic device toward the relative position.

随着电子设备拍摄姿态的调整，第一类对象和第二类对象在拍摄预览界面的位置也会随之改变，相应的由第一类对象和第二类对象的状态信息确定出的共同的构图定位点也会实时改变，电子设备可以根据实时改变的构图定位点重新判断构图定位点与预设构图点是否匹配以决定是否指导用户构图。With the adjustment of the shooting posture of the electronic device, the positions of the first type of object and the second type of object on the shooting preview interface will also change, correspondingly, the common one determined by the state information of the first type of object and the second type of object The composition positioning point will also change in real time, and the electronic device can re-determine whether the composition positioning point matches the preset composition point according to the composition positioning point that changes in real time to decide whether to guide the user to compose the picture.

例如，当预设构图点在构图定位点的右边时，电子设备可以提示用户向右边调整拍摄方向，实时确定新的构图定位点，并判断新的构图定位点是否与预设构图点匹配，若是，则输出拍摄提示信息以提示用户可以进行拍摄了，若否，则重新判断此时预设构图点相对新的构图定位点的相对位置，例如，用户不小心调整过度，导致预设构图点在新的构图定位点的左边位置，则电子设备可以提示用户向左边调整拍摄方向。For example, when the preset composition point is on the right of the composition anchor point, the electronic device can prompt the user to adjust the shooting direction to the right, determine the new composition anchor point in real time, and determine whether the new composition anchor point matches the preset composition point, if so , The shooting prompt information is output to remind the user that it is ready to shoot. If not, the relative position of the preset composition point relative to the new composition anchor point is re-judged at this time. For example, the user accidentally over-adjusts the preset composition point The left position of the positioning point of the new composition, the electronic device can prompt the user to adjust the shooting direction to the left.

即，输出调整电子设备拍摄姿态的提示信息之后，通过实时确定第一类对象和第二类对象的状态信息，以及根据状态信息实时确定的构图定位点，可以根据电子设备调整的拍摄姿态实时判断构图定位点与预设构图点的位置是否匹配，若匹配则停止构图指导，提示用户拍摄，若不匹配则继续提示用户调整拍摄姿态。That is, after outputting the prompt information for adjusting the shooting posture of the electronic device, by determining the status information of the first type of object and the second type of object in real time, and the composition positioning point determined in real time according to the status information, the shooting posture adjusted by the electronic device can be judged in real time Whether the positioning point of the composition matches the position of the preset composition point, if it matches, the composition guidance will be stopped and the user will be prompted to shoot, and if it does not match, the user will continue to prompt the user to adjust the shooting posture.

在一些实施方式中，输出调整电子设备拍摄姿态的提示信息之后，还可以包括：当构图定位点与预设构图点的位置匹配时，对待拍摄场景进行拍摄，得到待拍摄场景的成像图像。In some embodiments, after outputting the prompt information for adjusting the shooting posture of the electronic device, it may further include: when the composition positioning point matches the position of the preset composition point, shooting the scene to be shot to obtain an imaging image of the scene to be shot.

当电子设备的拍摄姿态被调整到使得述构图定位点与预设构图点的位置匹配时，电子设备可以提示用户进行拍摄，用户可以选择按照当前推荐的构图进行拍摄，得到待拍摄场景的成像图像，也可以坚持自己的构图，继续调整到自己喜欢的构图方式再进行拍摄。When the shooting posture of the electronic device is adjusted so that the position of the composition positioning point matches the preset composition point, the electronic device can prompt the user to shoot, and the user can choose to shoot according to the currently recommended composition to obtain an imaging image of the scene to be shot , You can also stick to your own composition and continue to adjust to your favorite composition before shooting.

本申请实施例提供的构图指导方法能够指导用户在拍摄时合理构图，但并不限制用户的构图，用户依旧可以选择自己喜欢的构图方式，在为用户进行指导的同时保留了构图的灵活性。The composition guidance method provided by the embodiments of the present application can guide the user to rationally compose the picture when shooting, but does not limit the user's composition. The user can still choose the composition method he likes, which provides guidance for the user while retaining the flexibility of the composition.

请继续参阅图2，图2为本申请实施例提供的构图指导方法的第二种流程示意图。该文本显示方法应用于本申请实施例提供的电子设备，该构图指导方法可以包括以下步骤：Please continue to refer to FIG. 2, which is a schematic diagram of the second flow of the composition guidance method provided by an embodiment of the application. The text display method is applied to the electronic device provided in the embodiment of the present application, and the composition guidance method may include the following steps:

201、获取待拍摄场景的预览图像。201. Obtain a preview image of a scene to be shot.

电子设备可以包括一个或多个摄像头，通过摄像头对待拍摄场景进行预览，获取待拍摄场景的预览图像。电子设备在实现预览功能时，摄像头预览的画面可以显示在拍摄预览界面上。The electronic device may include one or more cameras, through which the camera previews the scene to be shot, and obtains a preview image of the scene to be shot. When the electronic device realizes the preview function, the picture previewed by the camera can be displayed on the shooting preview interface.

202、对预览图像进行语义分割，得到预览图像中每一个像素点所属的对象类别。202. Perform semantic segmentation on the preview image to obtain the object category to which each pixel in the preview image belongs.

其中，对预览图像进行语义分割之前，预先在语义分割数据集上训练语义分割模型，在对预览图像进行语义分割时，将预览图像输入预先训练好的语义分割模型中进行语义分割。例如，语义分割模型可以采用BiSeNet算法。Wherein, before semantic segmentation is performed on the preview image, the semantic segmentation model is pre-trained on the semantic segmentation data set, and when the preview image is semantically segmented, the preview image is input into the pre-trained semantic segmentation model for semantic segmentation. For example, the semantic segmentation model can use the BiSeNet algorithm.

在一实施例中，将预览图像输入语义分割模型中进行语义分割，得到预览图像中每一个像素点所属的对象类别。其中对象类别可以包括人物类别和物体类别，物体类别中又可划分为不同的物体类别，例如，植物类别、建筑类别等。In one embodiment, the preview image is input into the semantic segmentation model for semantic segmentation, and the object category to which each pixel in the preview image belongs is obtained. The object categories can include person categories and object categories, and the object categories can be divided into different object categories, for example, plant categories, building categories, and so on.

203、根据预览图像中每一个像素点所属的对象类别识别出预览图像中的对象。203. Identify the object in the preview image according to the object category to which each pixel in the preview image belongs.

其中，预览图像中属于同一对象类别的像素点构成一类对象，对应于不同类的对象有不同的显示区域。Among them, the pixels in the preview image that belong to the same object category constitute one type of object, and there are different display areas corresponding to different types of objects.

204、当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象。204. When it is recognized that the scene to be photographed contains at least two types of objects of different types, determine the first type of object and the second type of object in the scene to be photographed.

可以理解的是，在对预览图像进行语义分割时，可能未识别到对象，也可能识别出一类、两类或者多类对象。It is understandable that when performing semantic segmentation on the preview image, the object may not be recognized, or one, two or more types of objects may be recognized.

在一实施方式中，将人物对象确定为第一类对象，并根据红外热成像图获取不同类别的物体对象所对应的表面温度，将对应表面温度最高的物体对象确定为第二类对象。或者，将对应表面温度最高的物体对象确定为第一类对象，将除第一类对象以外对应表面温度最高的物体对象确定为第二类对象，等等。In one embodiment, the human object is determined as the first type of object, and the surface temperatures corresponding to different types of objects are obtained according to the infrared thermal imaging images, and the object with the highest surface temperature is determined as the second type of object. Alternatively, the object with the highest corresponding surface temperature is determined as the first type of object, and the object with the highest corresponding surface temperature other than the first type of object is determined as the second type of object, and so on.

205、确定第一类对象在预览图像中对应的第一显示区域，以及确定第二类对象在预览图像中对应的第二显示区域。205. Determine a first display area corresponding to the first-type object in the preview image, and determine a second display area corresponding to the second-type object in the preview image.

在前述步骤中，通过语义分割识别出了预览图像中各像素点对应的对象类别，确定出了第一类对象和第二类对象。将第一类对象对应的像素点在预览图像中所占的区域确定为第一显示区域，将第二类对象对应的像素点在预览图像中所占的区域确定为第二显示区域。In the foregoing steps, the object category corresponding to each pixel in the preview image is identified through semantic segmentation, and the first type of object and the second type of object are determined. The area occupied by the pixels corresponding to the objects of the first type in the preview image is determined as the first display area, and the area occupied by the pixels corresponding to the objects of the second type in the preview image is determined as the second display area.

206、判断第一显示区域在预览图像中的第一面积占比是否大于第一预设比例。若是则转入步骤207，若不是则转入步骤209。206. Determine whether the proportion of the first area of the first display area in the preview image is greater than the first preset proportion. If yes, go to step 207, if not, go to step 209.

207、判断第二显示区域在预览图像中的第二面积占比是否大于第二预设比例。若是则转入步骤208，若不是则转入步骤209。207. Determine whether the second area ratio of the second display area in the preview image is greater than the second preset ratio. If yes, go to step 208, if not, go to step 209.

在一实施例中，根据语义分割得到的第一显示区域和第二显示区域判断待拍摄场景中的第一类对象和第二类对象是否符合预设条件，若符合则进入步骤208，若不符合则进入步骤209。可选的，若第一显示区域在预览图像中的第一面积占比大于第一预设比例，且第二显示区域在预览图像中的第二面积占比大于第二预设比例，则判定待拍摄场景中的第一类对象和第二类对象符合预设条件。In one embodiment, according to the first display area and the second display area obtained by semantic segmentation, it is determined whether the objects of the first type and the object of the second type in the scene to be photographed meet the preset conditions, if they do, go to step 208, if not, If yes, go to step 209. Optionally, if the proportion of the first area of the first display area in the preview image is greater than the first preset proportion, and the proportion of the second area of the second display area in the preview image is greater than the second preset proportion, then it is determined The objects of the first type and the objects of the second type in the scene to be photographed meet the preset conditions.

其中，第一预设比例和第二预设比例可以相同，也可以不同。例如，若拍摄场景中有人物对象，则即使人物对象的显示区域在预览图像中的面积占比稍微低一点也无妨，而对于体积庞大的建筑对象将建筑对象在预览图像中的面积占比则应高一些才能将其确定为拍摄的重点。例如，当第一类图像为人物对象，第二类对象为建筑对象时，若第一类对象在预览图像中的第一面积占比大于10％且第二类对象在预览图像中的第二面积占比大于30％，则判定待拍摄场景中的第一类对象和第二类对象符合预设条件，进入步骤208。第一预设比例和第二预设比例的大小可以根据对象类别的实际体积和用户的拍照习惯设定。Wherein, the first preset ratio and the second preset ratio may be the same or different. For example, if there are human subjects in the shooting scene, it does not matter if the display area of the human subjects occupy a slightly lower area in the preview image. For a large building object, the proportion of the architectural object in the preview image is It should be higher to determine it as the focus of shooting. For example, when the first type of image is a human object and the second type of object is a building object, if the first type of object in the preview image accounts for more than 10% of the first area and the second type of object is the second in the preview image If the area accounts for more than 30%, it is determined that the objects of the first type and the objects of the second type in the scene to be photographed meet the preset conditions, and step 208 is entered. The size of the first preset ratio and the second preset ratio can be set according to the actual volume of the object category and the user's photographing habits.

208、确定出第一显示区域的第一中心点，以及确定出第二显示区域的第二中心点。208. Determine the first center point of the first display area, and determine the second center point of the second display area.

在一实施例中，获取第一显示区域中所有像素点的第一坐标值均值，将第一坐标值均值对应的像素点确定为第一中心点；获取第二显示区域中所有像素点的第二坐标值均值，将第二坐标值均值对应的像素点确定为第二中心点。In one embodiment, the average value of the first coordinate values of all pixels in the first display area is obtained, and the pixel point corresponding to the average value of the first coordinate value is determined as the first center point; and the first center point of all pixels in the second display area is obtained. The average value of the two coordinate values, and the pixel point corresponding to the average value of the second coordinate value is determined as the second center point.

或者，在预览图像中用一矩形框将第一类对象从最上到最下、从最左到最右地框选起来，将该矩形的几何中心点确定为第一中心点，同理可确定出第二类对象的第二中心点。Or, use a rectangular frame in the preview image to select the first type of objects from top to bottom, and from left to right, and determine the geometric center point of the rectangle as the first center point, which can be determined in the same way Out the second center point of the second type of object.

209、不进行构图指导。209. No composition guidance.

若第一显示区域在预览图像中的第一面积占比不大于第一预设比例，和/或第二显示区域在预览图像中的第二面积占比不大于第二预设比例，则说明当前待拍摄场景不符合预设条件，待拍摄场景中的对象可以离得太远或者本身太小，导致没有合适的构图对象。此时，不对用户进行构图指导。If the proportion of the first area of the first display area in the preview image is not greater than the first preset proportion, and/or the proportion of the second area of the second display area in the preview image is not greater than the second preset proportion, it is indicated The current scene to be photographed does not meet the preset conditions, and the object in the scene to be photographed may be too far away or too small, resulting in no suitable composition object. At this time, no composition guidance is given to the user.

210、获取第一显示区域与第二显示区域的面积比值。210. Obtain an area ratio between the first display area and the second display area.

在确定构图定位点之前，计算第一显示区域与第二显示区域的面积比值。其中，第一显示区域与第二显示区域均是由多个像素点组成的像素范围。因而，为计算面积比值，可以无需知道第一显示区域和第二显示区域具体的面积数值，只需获取第一显示区域与第二显示区域包含的像素点数量比值即可。即，获取第一显示区域与第二显示区域的面积比值的步骤，可以包括：Before determining the composition positioning point, the area ratio of the first display area to the second display area is calculated. Wherein, both the first display area and the second display area are pixel ranges composed of a plurality of pixels. Therefore, in order to calculate the area ratio, it is not necessary to know the specific area values of the first display area and the second display area, and only need to obtain the ratio of the number of pixels contained in the first display area and the second display area. That is, the step of obtaining the area ratio between the first display area and the second display area may include:

获取第一显示区域与第二显示区域包含的像素点数量；Acquiring the number of pixels contained in the first display area and the second display area;

计算出第一显示区域与第二显示区域包含的像素点数量比值；Calculate the ratio of the number of pixels contained in the first display area and the second display area;

将像素点数量比值作为面积比值。The ratio of the number of pixels is taken as the area ratio.

211、根据第一中心点、第二中心点以及面积比值确定构图定位点，构图定位点到第一中心点与第二中心点的距离之比等于面积比值。211. Determine the composition positioning point according to the first center point, the second center point and the area ratio, and the ratio of the distance from the composition positioning point to the first center point and the second center point is equal to the area ratio.

请参阅图3，图3为本申请实施例提供的预览图像的示意图。其中，第一类对象为人物对象，第二类对象为建筑物对象，其中第一类对象在预设图像中的第一面积S1占比大于第一预设比例，第二类对象在预设图像中的第二面积S ₂占比大于第二预设比例。建立预览图像的坐标系x-O-y，可根据预览图像中第一中心点P1(x ₁,y ₁)、第二中心点P2(x ₂,y ₂)以及面积比值S ₁/S ₂为第一类对象和第二类对象确定出共同的构图定位点。设构图定位点在预览图像中的坐标为Pr(X,Y)，其中X和Y分别代表构图定位点的，构图定位点的横坐标X和纵坐标Y可以通过两个坐标确定公式确定： Please refer to FIG. 3, which is a schematic diagram of a preview image provided by an embodiment of the application. Among them, the first type of object is a person object, and the second type of object is a building object. Among them, the first type of object in the preset image has a larger proportion of the first area S1 than the first preset ratio, and the second type of object is in the preset image. The proportion of the second area S ₂ in the image is greater than the second preset proportion. Establish the coordinate system xOy of the preview image, according to the first center point P1 (x ₁ , y ₁ ), the second center point P2 (x ₂ , y ₂ ) and the area ratio S ₁ /S _{2 in the} preview image as the first type The object and the second type of object determine a common composition anchor point. Suppose the coordinates of the composition anchor point in the preview image are Pr(X, Y), where X and Y represent the composition anchor point respectively. The abscissa X and the ordinate Y of the composition anchor point can be determined by two coordinate determination formulas:

其中，在x方向上，构图定位点到第一中心点P1(x ₁,y ₁)的距离为： Among them, in the x direction, the distance from the composition positioning point to the first center point P1(x ₁ , y _{1) is:}

在x方向，构图定位点到第二中心点P2(x ₂,y ₂)的距离为： In the x direction, the distance from the positioning point of the composition to the second center point P2(x ₂ ,y _{2) is:}

在x方向上，构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比为： In the x direction, the ratio of the distance between the positioning point of the composition and the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y _{2) is:}

即，在x方向上，构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比等于面积比值S ₁/S ₂。 That is, in the x direction, the ratio of the distance from the composition positioning point to the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y ₂ ) is equal to the area ratio S ₁ /S ₂ .

在y方向上，构图定位点到第一中心点P1(x ₁,y ₁)的距离为： In the y direction, the distance from the positioning point of the composition to the first center point P1(x ₁ , y _{1) is:}

在y方向上，构图定位点到第二中心点P2(x ₂,y ₂)的距离为： In the y direction, the distance from the positioning point of the composition to the second center point P2(x ₂ ,y _{2) is:}

在y方向上，构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比为： In the y direction, the ratio of the distance between the positioning point of the composition and the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y _{2) is:}

即，在y方向上，构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比等于面积比值S ₁/S ₂。例如，以图3为例，若在图3中，建筑面积为人面积的2倍，则确定出的构图定位点到建筑的中心点的距离为到人的中心点的距离的2倍。 That is, in the y direction, the ratio of the distance from the composition positioning point to the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y ₂ ) is equal to the area ratio S ₁ /S ₂ . For example, taking Fig. 3 as an example, if the building area in Fig. 3 is twice the area of a person, the determined distance from the composition location point to the center point of the building is twice the distance from the center point of the person.

由于在x方向上和y方向上，构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比都等于面积比值S ₁/S ₂，可推得根据上述坐标确定公式得到的构图定位点的位置满足：构图定位点到第一中心点P1(x ₁,y ₁)与第二中心点P2(x ₂,y ₂)的距离之比等于面积比值S ₁/S ₂。 Since in the x direction and the y direction, the ratio of the distance between the composition positioning point and the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y ₂ ) is equal to the area ratio S ₁ / S ₂ , it can be deduced that the position of the composition positioning point obtained according to the above coordinate determination formula satisfies: the composition positioning point to the first center point P1 (x ₁ , y ₁ ) and the second center point P2 (x ₂ , y ₂ ) The distance ratio is equal to the area ratio S ₁ /S ₂ .

212、判断构图定位点与预设构图点的位置是否匹配,当构图定位点与预设构图点的位置不匹配时，转入步骤213，当构图定位点与预设构图点的位置匹配时，转入步骤215。212. Determine whether the position of the composition positioning point matches the preset composition point. When the composition positioning point does not match the position of the preset composition point, go to step 213. When the composition positioning point matches the position of the preset composition point, Go to step 215.

213、当构图定位点与预设构图点的位置不匹配时，在电子设备的拍摄预览界面上显示构图定位点与预设构图点。213. When the position of the composition positioning point and the preset composition point do not match, the composition positioning point and the preset composition point are displayed on the shooting preview interface of the electronic device.

214、在预览界面上显示构图定位点向预设构图点的移动方向，输出向移动方向调整电子设备拍摄姿态的提示信息。214. Display the moving direction of the composition positioning point to the preset composition point on the preview interface, and output prompt information for adjusting the shooting posture of the electronic device in the moving direction.

215、输出拍照的提示信息。215. Output prompt information for taking pictures.

位置的匹配可以是二者位置相同，也可以是二者之间的距离小于预设阈值，或者二者的相对位置满足一定条件，例如，构图定位点位于预设构图点上方预设距离处视为位置相匹配。The position matching can be that the two positions are the same, or the distance between the two is less than the preset threshold, or the relative position of the two meets certain conditions, for example, the composition positioning point is located at the preset distance above the preset composition point. Matches for the location.

图4为本申请提供的拍摄预览画面的示意图。请参阅图4(a)，其中，预设构图点可以为预览图像上的几何中心点，以位置的匹配为位置相同为例，构图定位点与预设构图点的位置不匹配时，根据预览图像与拍摄预览界面的对应关系，将预设构图点和预设构图点对应显示到拍摄预览界面上，在拍摄预览界面上标注出构图定位点向预设构图点的移动方向，以提示用户该如何调整电子设备的拍摄姿态，使得构图定位点与预设构图点的位置匹配。而在拍摄预览界面上显示构图定位点向预设构图点的移动方向，能够使用户在拍摄预览界面上直观地看到如何调整电子设备的拍摄姿态。例如，向着该移动方向移动电子设备，或者向着该移动方向调整电子设备的拍摄角度等。FIG. 4 is a schematic diagram of the shooting preview screen provided by this application. Please refer to Figure 4(a), where the preset composition point can be the geometric center point on the preview image. Take the position matching as the same position as an example. When the position of the composition positioning point and the preset composition point do not match, according to the preview The corresponding relationship between the image and the shooting preview interface, the preset composition point and the preset composition point are correspondingly displayed on the shooting preview interface, and the movement direction of the composition anchor point to the preset composition point is marked on the shooting preview interface to remind the user. How to adjust the shooting posture of the electronic device so that the positioning point of the composition matches the position of the preset composition point. Displaying the moving direction of the composition positioning point to the preset composition point on the shooting preview interface enables the user to intuitively see how to adjust the shooting posture of the electronic device on the shooting preview interface. For example, the electronic device is moved in the moving direction, or the shooting angle of the electronic device is adjusted in the moving direction.

例如，图4(a)中预设构图点在构图定位点的右上方，电子设备可以提示用户向右上方调整拍摄方向，实时确定新的构图定位点，并判断新的构图定位点是否与预设构图点匹配，若是，则输出拍摄提示信息以提示用户可以进行拍摄了，若否，则重新判断此时预设构图点相对新的构图定位点的相对位置，例如，用户调整过度，调整过后预设构图点到了新的构图定位点的左下方位置，则电子设备可以提示用户向左下方调整拍摄方向。请继续参阅图4(b)，当电子设备的拍摄姿态被调整到使得述构图定位点与预设构图点的位置匹配时，电子设备可以提示用户进行拍摄，用户可以选择按照当前推荐的构图进行拍摄，得到待拍摄场景的成像图像，也可以坚持自己的构图，继续调整到自己喜欢的构图方式再进行拍摄。For example, in Figure 4(a), the preset composition point is at the upper right of the composition positioning point, and the electronic device can prompt the user to adjust the shooting direction to the upper right, determine the new composition positioning point in real time, and determine whether the new composition positioning point is consistent with the preset positioning point. Set the composition point to match, if yes, output a shooting prompt message to remind the user that the user is ready to shoot, if not, then re-judge the relative position of the preset composition point to the new composition anchor point at this time, for example, the user over-adjusted, after the adjustment When the preset composition point reaches the lower left position of the new composition positioning point, the electronic device may prompt the user to adjust the shooting direction to the lower left. Please continue to refer to Figure 4(b). When the shooting posture of the electronic device is adjusted so that the composition positioning point matches the position of the preset composition point, the electronic device can prompt the user to shoot, and the user can choose to follow the currently recommended composition Shoot, get the imaging image of the scene to be shot, you can also stick to your own composition and continue to adjust to your favorite composition before shooting.

具体实施时，本申请不受所描述的各个步骤的执行顺序的限制，在不产生冲突的情况下，某些步骤还可以采用其它顺序进行或者同时进行。During specific implementation, the present application is not limited by the order of execution of the various steps described, and certain steps may also be performed in other order or at the same time if there is no conflict.

由上可知，本申请实施例提供的构图指导方法，首先对待拍摄场景进行对象识别；当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象；然后根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。本申请实施例通过为待拍摄场景中的两类对象确定出共同的构图定位点，能够在构图定位点与预设构图点不匹配时提示用户改变电子设备的拍摄姿势，以此指导用户在拍摄时合理构图，拍出高质量的照片。It can be seen from the above that the composition guidance method provided by the embodiments of the present application first performs object recognition on the scene to be photographed; when it is recognized that the scene to be photographed contains at least two types of objects in different categories, the first type of object in the scene to be photographed is determined And the second type of object; then according to the state information of the first type of object and the second type of object to determine the common composition positioning point for the first type of object and the second type of object; when the position of the composition positioning point and the preset composition point are not When matching, output prompt information for adjusting the shooting posture of the electronic device. The embodiment of the application determines a common composition positioning point for two types of objects in the scene to be photographed, and can prompt the user to change the shooting posture of the electronic device when the composition positioning point does not match the preset composition point, thereby guiding the user in shooting Make a reasonable composition and take high-quality photos.

本申请实施例还提供一种构图指导装置。请参照图5，图5为本申请实施例提供的构图指导装置的第一结构示意图。其中该构图指导装置300应用于电子设备，该构图指导装置包括对象识别模块301、第一确定模块302、第二确定模块303以及构图指导模块304，如下：The embodiment of the present application also provides a composition guidance device. Please refer to FIG. 5. FIG. 5 is a schematic diagram of a first structure of a composition guiding device provided by an embodiment of the application. The composition guidance device 300 is applied to electronic equipment, and the composition guidance device includes an object recognition module 301, a first determination module 302, a second determination module 303, and a composition guidance module 304, as follows:

对象识别模块301，用于对待拍摄场景进行对象识别；The object recognition module 301 is used to perform object recognition on the scene to be photographed;

第一确定模块302，用于当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象；The first determining module 302 is configured to determine the first type of object and the second type of object in the to-be-shot scene when it is recognized that the to-be-shot scene contains at least two different types of objects;

第二确定模块303，用于根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；The second determining module 303 is configured to determine a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

构图指导模块304，用于当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。The composition guidance module 304 is configured to output prompt information for adjusting the shooting posture of the electronic device when the positioning point of the composition does not match the position of the preset composition point.

在一实施例中，对象识别模块301可以用于：In an embodiment, the object recognition module 301 may be used to:

获取待拍摄场景的预览图像；Obtain a preview image of the scene to be shot;

对预览图像进行语义分割，得到预览图像中每一个像素点所属的对象类别；Perform semantic segmentation on the preview image to obtain the object category to which each pixel in the preview image belongs;

根据预览图像中每一个像素点所属的对象类别识别出预览图像中的对象。Identify the object in the preview image according to the object category to which each pixel in the preview image belongs.

请一并参阅图6，图6为本申请实施例提供的构图指导装置300的第二种结构示意图。在一些实施例中，构图指导装置300还可以包括第三确定模块305，第三确定模块305用于：Please also refer to FIG. 6. FIG. 6 is a schematic diagram of a second structure of the composition guiding device 300 provided by an embodiment of the present application. In some embodiments, the composition guiding apparatus 300 may further include a third determining module 305, and the third determining module 305 is configured to:

确定第一类对象在预览图像中对应的第一显示区域，以及确定第二类对象在预览图像中对应的第二显示区域；Determine the first display area corresponding to the first type of object in the preview image, and determine the second display area corresponding to the second type of object in the preview image;

当第一显示区域在预览图像中的第一面积占比大于第一预设比例，且第二显示区域在预览图像中的第二面积占比大于第二预设比例时，根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点。When the proportion of the first area of the first display area in the preview image is greater than the first preset proportion, and the proportion of the second area of the second display area in the preview image is greater than the second preset proportion, according to the first type of object The state information of the second-type object and the first-type object determine a common composition anchor point for the first-type object and the second-type object.

请继续参阅图7，图7为本申请实施例提供的构图指导装置300的第三种结构示意图。在一些实施例中，第二确定模块303包括第一确定单元3031、获取单元3032和第二确定单元3033。Please continue to refer to FIG. 7, which is a schematic diagram of a third structure of the composition guiding device 300 provided by an embodiment of the application. In some embodiments, the second determining module 303 includes a first determining unit 3031, an acquiring unit 3032, and a second determining unit 3033.

第一确定单元3031确定出第一显示区域的第一中心点，以及确定出第二显示区域的第二中心点；The first determining unit 3031 determines the first center point of the first display area, and determines the second center point of the second display area;

获取单元3032获取第一显示区域与第二显示区域的面积比值；The obtaining unit 3032 obtains the area ratio of the first display area to the second display area;

第二确定单元3033根据第一中心点、第二中心点以及面积比值确定构图定位点，构图定位点到第一中心点与第二中心点的距离之比等于面积比值。The second determining unit 3033 determines the composition positioning point according to the first center point, the second center point, and the area ratio, and the ratio of the distance from the composition positioning point to the first center point and the second center point is equal to the area ratio.

在一实施例中，第一确定单元3031可以用于：In an embodiment, the first determining unit 3031 may be used to:

获取第一显示区域中所有像素点的第一坐标值均值，将第一坐标值均值对应的像素点确定为第一中心点；Obtaining an average value of the first coordinate values of all pixels in the first display area, and determining the pixel point corresponding to the average value of the first coordinate value as the first center point;

获取第二显示区域中所有像素点的第二坐标值均值，将第二坐标值均值对应的像素点确定为第二中心点。The second coordinate value average value of all pixels in the second display area is acquired, and the pixel point corresponding to the second coordinate value average value is determined as the second center point.

在一实施例中，获取单元3032可以用于：In an embodiment, the obtaining unit 3032 may be used to:

在一实施例中，构图指导模块304可以用于：In an embodiment, the composition guidance module 304 may be used to:

以上各个模块的具体实施可参见前面的实施例，在此不再赘述。The specific implementation of each of the above modules can be referred to the previous embodiments, which will not be repeated here.

由上可知，本申请实施例提供的构图指导装置，首先对象识别模块301对待拍摄场景进行对象识别；当识别出待拍摄场景中包含至少两类不同类别的对象时，第一确定模块302确定出待拍摄场景中的第一类对象和第二类对象；然后第二确定模块303根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；当构图定位点与预设构图点的位置不匹配时，构图指导模块304输出调整电子设备拍摄姿态的提示信息。本申请实施例通过为待拍摄场景中的两类对象确定出共同的构图定位点，能够在构图定位点与预设构图点不匹配时提示用户改变电子设备的拍摄姿势，以此指导用户在拍摄时合理构图，拍出高质量的照片。It can be seen from the above that, in the composition guidance device provided by the embodiment of the present application, first, the object recognition module 301 performs object recognition on the scene to be photographed; when it is recognized that the scene to be photographed contains at least two types of objects of different categories, the first determining module 302 determines The first type of object and the second type of object in the scene to be photographed; then the second determining module 303 determines a common composition location for the first type of object and the second type of object according to the state information of the first type of object and the second type of object Point; when the position of the composition positioning point and the preset composition point do not match, the composition guidance module 304 outputs prompt information for adjusting the shooting posture of the electronic device. The embodiment of the application determines a common composition positioning point for two types of objects in the scene to be photographed, and can prompt the user to change the shooting posture of the electronic device when the composition positioning point does not match the preset composition point, thereby guiding the user in shooting Make a reasonable composition and take high-quality photos.

本申请实施例还提供一种电子设备。电子设备可以是智能手机、平板电脑、游戏设备、AR(Augmented Reality，增强现实)设备、汽车、车辆周边障碍检测装置、音频播放装置、视频播放装置、笔记本、桌面计算设备、可穿戴设备诸如手表、眼镜、头盔、电子手链、电子项链、电子衣物等设备。The embodiment of the present application also provides an electronic device. Electronic equipment can be smart phones, tablet computers, gaming equipment, AR (Augmented Reality) equipment, automobiles, vehicle surrounding obstacle detection devices, audio playback devices, video playback devices, notebooks, desktop computing devices, wearable devices such as watches , Glasses, helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment.

参考图8，图8为本申请实施例提供的电子设备400的第一种结构示意图。其中，电子设备400包括处理器401和存储器402。处理器401与存储器402电性连接。Referring to FIG. 8, FIG. 8 is a schematic diagram of a first structure of an electronic device 400 according to an embodiment of the application. Among them, the electronic device 400 includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.

处理器401是电子设备400的控制中心，利用各种接口和线路连接整个电子设备的各个部分，通过运行或调用存储在存储器402内的计算机程序，以及调用存储在存储器402内的数据，执行电子设备的各种功能和处理数据，从而对电子设备进行整体监控。The processor 401 is the control center of the electronic device 400. It uses various interfaces and lines to connect various parts of the entire electronic device. Various functions and processing data of the equipment, so as to monitor the electronic equipment as a whole.

在本实施例中，电子设备400中的处理器401可以按照上述构图指导方法中的步骤，将一个或一个以上的计算机程序的进程对应的指令加载到存储器402中，并由处理器401来运行存储在存储器402中的计算机程序，从而实现上述构图指导方法中的步骤，例如：In this embodiment, the processor 401 in the electronic device 400 can load the instructions corresponding to the process of one or more computer programs into the memory 402 according to the steps in the above-mentioned composition guidance method, and the processor 401 can run the instructions. The computer program stored in the memory 402, so as to realize the steps in the above-mentioned composition guidance method, for example:

在一些情况下，在对待拍摄场景进行对象识别时，处理器401执行以下步骤：In some cases, when performing object recognition on the scene to be photographed, the processor 401 performs the following steps:

在一些情况下，在根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点之前，处理器401执行以下步骤：In some cases, before determining a common composition anchor point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object, the processor 401 performs the following steps:

在一些情况下，在根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点时，处理器401执行以下步骤：In some cases, when a common composition anchor point is determined for the first-type object and the second-type object according to the state information of the first-type object and the second-type object, the processor 401 performs the following steps:

确定出第一显示区域的第一中心点，以及确定出第二显示区域的第二中心点；Determine the first center point of the first display area, and determine the second center point of the second display area;

获取第一显示区域与第二显示区域的面积比值；Acquiring an area ratio between the first display area and the second display area;

根据第一中心点、第二中心点以及面积比值确定构图定位点，构图定位点到第一中心点与第二中心点的距离之比等于面积比值。The composition positioning point is determined according to the first center point, the second center point and the area ratio, and the ratio of the distance from the composition positioning point to the first center point to the second center point is equal to the area ratio.

在一些情况下，在确定出第一显示区域的第一中心点，以及确定出第二显示区域的第二中心点时，处理器401还执行以下步骤：In some cases, when the first center point of the first display area is determined and the second center point of the second display area is determined, the processor 401 further performs the following steps:

在一些情况下，在获取第一显示区域与第二显示区域的面积比值时，处理器401还执行以下步骤：In some cases, when acquiring the area ratio of the first display area to the second display area, the processor 401 further executes the following steps:

在一些情况下，在输出调整电子设备拍摄姿态的提示信息时，处理器401还执行以下步骤：In some cases, when outputting prompt information for adjusting the shooting posture of the electronic device, the processor 401 further executes the following steps:

请继续参考图9，图9为本申请实施例提供的电子设备400的第二种结构示意图。其中，电子设备400还包括：显示屏403、控制电路404、输入单元405、传感器406以及电源407。其中，处理器401分别与显示屏403、控制电路404、输入单元405、传感器406以及电源407电性连接。Please continue to refer to FIG. 9, which is a schematic diagram of the second structure of the electronic device 400 according to an embodiment of the application. Wherein, the electronic device 400 further includes: a display screen 403, a control circuit 404, an input unit 405, a sensor 406, and a power supply 407. The processor 401 is electrically connected to the display screen 403, the control circuit 404, the input unit 405, the sensor 406, and the power supply 407, respectively.

显示屏403可用于显示由用户输入的信息或提供给用户的信息以及电子设备的各种图形用户接口，这些图形用户接口可以由图像、文本、图标、视频和其任意组合来构成。The display screen 403 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of images, text, icons, videos, and any combination thereof.

控制电路404与显示屏403电性连接，用于控制显示屏403显示信息。The control circuit 404 is electrically connected to the display screen 403 for controlling the display screen 403 to display information.

输入单元405可用于接收输入的数字、字符信息或用户特征信息(例如指纹)，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。其中，输入单元405可以包括指纹识别模组。The input unit 405 can be used to receive inputted numbers, character information, or user characteristic information (such as fingerprints), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Wherein, the input unit 405 may include a fingerprint recognition module.

传感器406用于采集电子设备自身的信息或者用户的信息或者外部环境信息。例如，传感器406可以包括距离传感器、磁场传感器、光线传感器、加速度传感器、指纹传感器、霍尔传感器、位置传感器、陀螺仪、惯性传感器、姿态感应器、气压计、心率传感器等多个传感器。The sensor 406 is used to collect the information of the electronic device itself or the information of the user or the external environment information. For example, the sensor 406 may include multiple sensors such as a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a Hall sensor, a position sensor, a gyroscope, an inertial sensor, a posture sensor, a barometer, and a heart rate sensor.

电源407用于给电子设备400的各个部件供电。在一些实施例中，电源407可以通过电源管理***与处理器401逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。The power supply 407 is used to supply power to various components of the electronic device 400. In some embodiments, the power supply 407 may be logically connected to the processor 401 through a power management system, so that functions such as charging, discharging, and power consumption management can be managed through the power management system.

尽管图8及图9中未示出，电子设备400还可以包括摄像头、蓝牙模块等，在此不再赘述。Although not shown in FIG. 8 and FIG. 9, the electronic device 400 may also include a camera, a Bluetooth module, etc., which will not be repeated here.

在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见上文针对构图指导方法的详细描述，此处不再赘述。In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, please refer to the detailed description of the composition guidance method above, which will not be repeated here.

由上可知，本申请实施例提供了一种电子设备，电子设备中的处理器执行以下步骤：对待拍摄场景进行对象识别；当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象；根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。本申请实施例通过为待拍摄场景中的两类对象确定出共同的构图定位点，能够在构图定位点与预设构图点不匹配时提示用户改变电子设备的拍摄姿势，以此指导用户在拍摄时合理构图，拍出高质量的照片。It can be seen from the above that an embodiment of the present application provides an electronic device. The processor in the electronic device performs the following steps: performing object recognition on the scene to be photographed; Identify the first type of object and the second type of object in the scene to be photographed; determine the common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object; when the composition is positioned When the position of the point does not match the preset composition point, a prompt message for adjusting the shooting posture of the electronic device is output. The embodiment of the application determines a common composition positioning point for two types of objects in the scene to be photographed, and can prompt the user to change the shooting posture of the electronic device when the composition positioning point does not match the preset composition point, thereby guiding the user in shooting Make a reasonable composition and take high-quality photos.

本申请实施例还提供一种存储介质，存储介质中存储有计算机程序，当计算机程序在计算机上运行时，计算机执行上述任一实施例的构图指导方法。An embodiment of the present application also provides a storage medium in which a computer program is stored. When the computer program is run on a computer, the computer executes the composition guidance method of any one of the foregoing embodiments.

例如，在一些实施例中，当计算机程序在计算机上运行时，计算机执行以下步骤：For example, in some embodiments, when the computer program runs on the computer, the computer performs the following steps:

对待拍摄场景进行对象识别；当识别出待拍摄场景中包含至少两类不同类别的对象时，确定出待拍摄场景中的第一类对象和第二类对象；根据第一类对象和第二类对象的状态信息为第一类对象和第二类对象确定出共同的构图定位点；当构图定位点与预设构图点的位置不匹配时，输出调整电子设备拍摄姿态的提示信息。Perform object recognition on the scene to be photographed; when it is recognized that the scene to be photographed contains at least two different types of objects, determine the first type of object and the second type of object in the scene to be photographed; according to the first type of object and the second type of object The state information of the object determines a common composition positioning point for the first type of object and the second type of object; when the composition positioning point does not match the position of the preset composition point, a prompt message for adjusting the shooting posture of the electronic device is output.

以上各个操作的具体实施可参见前面的实施例，在此不再赘述。For the specific implementation of the above operations, please refer to the previous embodiments, which will not be repeated here.

需要说明的是，本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过计算机程序来指令相关的硬件来完成，计算机程序可以存储于计算机可读存储介质中，存储介质可以包括但不限于：只读存储器(ROM，Read Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁盘或光盘等。It should be noted that those of ordinary skill in the art can understand that all or part of the steps in the various methods of the foregoing embodiments can be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. The storage medium may include, but is not limited to: read only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks, and so on.

以上对本申请实施例所提供的构图指导方法、装置及电子设备进行了详细介绍。本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上，本说明书内容不应理解为对本申请的限制。The above describes in detail the composition guidance method, device and electronic equipment provided by the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation of the application. The descriptions of the above examples are only used to help understand the methods and core ideas of the application; at the same time, for those skilled in the art, according to the principles of the application There will be changes in the thinking, specific implementation and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

一种构图指导方法，应用于电子设备，其中，包括：A composition guidance method applied to electronic equipment, including:

对待拍摄场景进行对象识别；Perform object recognition on the scene to be shot;

当识别出所述待拍摄场景中包含至少两类不同类别的对象时，确定出所述待拍摄场景中的第一类对象和第二类对象；When it is recognized that the scene to be photographed contains at least two types of objects of different categories, determining the first type of object and the second type of object in the scene to be photographed;

根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点；Determining a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

当所述构图定位点与预设构图点的位置不匹配时，输出调整所述电子设备拍摄姿态的提示信息。When the composition positioning point does not match the position of the preset composition point, outputting prompt information for adjusting the shooting posture of the electronic device.
根据权利要求1所述的构图指导方法，其中，所述对待拍摄场景进行对象识别包括：The composition guidance method according to claim 1, wherein said performing object recognition on the scene to be photographed comprises:

获取所述待拍摄场景的预览图像；Acquiring a preview image of the scene to be shot;

对所述预览图像进行语义分割，得到所述预览图像中每一个像素点所属的对象类别；Performing semantic segmentation on the preview image to obtain the object category to which each pixel in the preview image belongs;

根据所述预览图像中每一个像素点所属的对象类别识别出所述预览图像中的对象。The object in the preview image is identified according to the object category to which each pixel in the preview image belongs.
根据权利要求2所述的构图指导方法，其中，所述根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点之前，还包括：The composition guidance method according to claim 2, wherein the common composition position is determined for the first-type object and the second-type object based on the state information of the first-type object and the second-type object Before the point, it also includes:

确定所述第一类对象在所述预览图像中对应的第一显示区域，以及确定所述第二类对象在所述预览图像中对应的第二显示区域；Determining a first display area corresponding to the first type object in the preview image, and determining a second display area corresponding to the second type object in the preview image;

当所述第一显示区域在所述预览图像中的第一面积占比大于第一预设比例，且所述第二显示区域在所述预览图像中的第二面积占比大于第二预设比例时，根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点。When the proportion of the first area of the first display area in the preview image is greater than the first preset proportion, and the proportion of the second area of the second display area in the preview image is greater than the second preset In the case of a ratio, a common composition positioning point is determined for the first-type object and the second-type object according to the state information of the first-type object and the second-type object.
根据权利要求3所述的构图指导方法，其中，所述根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点包括：4. The composition guidance method according to claim 3, wherein the common composition position is determined for the first type object and the second type object based on the state information of the first type object and the second type object Points include:

确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点；Determining a first center point of the first display area, and determining a second center point of the second display area;

获取所述第一显示区域与所述第二显示区域的面积比值；Acquiring an area ratio of the first display area to the second display area;

根据所述第一中心点、所述第二中心点以及所述面积比值确定所述构图定位点，所述构图定位点到所述第一中心点与所述第二中心点的距离之比等于所述面积比值。The composition positioning point is determined according to the first center point, the second center point, and the area ratio, and the ratio of the distance from the composition positioning point to the first center point to the second center point is equal to The area ratio.
根据权利要求4所述的构图指导方法，其中，所述确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点包括：4. The composition guidance method according to claim 4, wherein said determining the first center point of the first display area and determining the second center point of the second display area comprises:

获取所述第一显示区域中所有像素点的第一坐标值均值，将所述第一坐标值均值对应的像素点确定为所述第一中心点；Acquiring an average value of the first coordinate values of all pixels in the first display area, and determining a pixel point corresponding to the average value of the first coordinate value as the first center point;

获取所述第二显示区域中所有像素点的第二坐标值均值，将所述第二坐标值均值对应的像素点确定为所述第二中心点。The second coordinate value average value of all pixels in the second display area is acquired, and the pixel point corresponding to the second coordinate value average value is determined as the second center point.
根据权利要求4所述的构图指导方法，其中，所述获取所述第一显示区域与所述第二显示区域的面积比值包括：4. The composition guidance method according to claim 4, wherein said obtaining the area ratio of the first display area to the second display area comprises:

获取所述第一显示区域与所述第二显示区域包含的像素点数量；Acquiring the number of pixels included in the first display area and the second display area;

计算出所述第一显示区域与所述第二显示区域包含的像素点数量比值；Calculating a ratio of the number of pixels contained in the first display area and the second display area;

将所述像素点数量比值作为所述面积比值。The ratio of the number of pixels is used as the area ratio.
根据权利要求1所述的构图指导方法，其中，所述输出调整所述电子设备拍摄姿态的提示信息包括：The composition guidance method according to claim 1, wherein the outputting prompt information for adjusting the shooting posture of the electronic device comprises:

在电子设备的拍摄预览界面上显示所述构图定位点与所述预设构图点；Displaying the composition positioning point and the preset composition point on the shooting preview interface of the electronic device;

在所述预览界面上显示所述构图定位点向所述预设构图点的移动方向，输出向所述移动方向调整所述电子设备拍摄姿态的提示信息。The movement direction of the composition positioning point to the preset composition point is displayed on the preview interface, and prompt information for adjusting the shooting posture of the electronic device in the movement direction is output.
根据权利要求7所述的构图指导方法，其中，所述对待拍摄场景进行对象识别之后，还包括：The composition guidance method according to claim 7, wherein, after the object recognition is performed on the scene to be photographed, the method further comprises:

对于识别出的各个对象，在所述拍摄预览界面上分别标注各对象的类别以及属于所述类别的概率。For each identified object, the category of each object and the probability of belonging to the category are respectively marked on the shooting preview interface.
根据权利要求1所述的构图指导方法，其中，所述输出调整所述电子设备拍摄姿态的提示信息包括：The composition guidance method according to claim 1, wherein the outputting prompt information for adjusting the shooting posture of the electronic device comprises:

在后台判断所述预设构图点相对所述构图定位点的相对位置；Determine the relative position of the preset composition point with respect to the composition positioning point in the background;

语音提示向着该相对位置调整电子设备的拍摄姿态。The voice prompt adjusts the shooting posture of the electronic device toward the relative position.
根据权利要求1所述的构图指导方法，其中，所述输出调整所述电子设备拍摄姿态的提示信息之后，还包括：The composition guidance method according to claim 1, wherein after said outputting the prompt information for adjusting the shooting posture of the electronic device, the method further comprises:

当调整至所述预设定位点与预设构图点的位置匹配时，对所述待拍摄场景进行拍摄，得到所述待拍摄场景的成像图像。When the position of the preset positioning point and the preset composition point are adjusted to match, the scene to be photographed is photographed to obtain an imaging image of the scene to be photographed.
一种构图指导装置，应用于电子设备，其中，包括：A composition guidance device applied to electronic equipment, including:

对象识别模块，用于对待拍摄场景进行对象识别；The object recognition module is used to perform object recognition on the scene to be photographed;

第一确定模块，用于当识别出所述待拍摄场景中包含至少两类不同类别的对象时，确定出所述待拍摄场景中的第一类对象和第二类对象；The first determining module is configured to determine the first type of object and the second type of object in the to-be-shot scene when it is recognized that the to-be-shot scene contains at least two types of objects of different types;

第二确定模块，用于根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点；A second determining module, configured to determine a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

构图指导模块，用于当所述构图定位点与预设构图点的位置不匹配时，输出调整所述电子设备拍摄姿态的提示信息。The composition guidance module is configured to output prompt information for adjusting the shooting posture of the electronic device when the position of the composition positioning point does not match the preset composition point.
一种电子设备，包括处理器和存储器，所述存储器中存储有计算机程序，其中，所述处理器通过调用所述存储器中存储的所述计算机程序，用于执行：An electronic device includes a processor and a memory, and a computer program is stored in the memory, wherein the processor is configured to execute:

对待拍摄场景进行对象识别；Perform object recognition on the scene to be shot;

当识别出所述待拍摄场景中包含至少两类不同类别的对象时，确定出所述待拍摄场景中的第一类对象和第二类对象；When it is recognized that the scene to be photographed contains at least two types of objects of different categories, determining the first type of object and the second type of object in the scene to be photographed;

根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点；Determining a common composition positioning point for the first type of object and the second type of object according to the state information of the first type of object and the second type of object;

当所述构图定位点与预设构图点的位置不匹配时，输出调整所述电子设备拍摄姿态的提示信息。When the composition positioning point does not match the position of the preset composition point, outputting prompt information for adjusting the shooting posture of the electronic device.
根据权利要求12所述的电子设备，其中，在对待拍摄场景进行对象识别时，所述处理器用于执行：The electronic device according to claim 12, wherein, when performing object recognition on the scene to be photographed, the processor is configured to execute:

获取所述待拍摄场景的预览图像；Acquiring a preview image of the scene to be shot;

对所述预览图像进行语义分割，得到所述预览图像中每一个像素点所属的对象类别；Performing semantic segmentation on the preview image to obtain the object category to which each pixel in the preview image belongs;

根据所述预览图像中每一个像素点所属的对象类别识别出所述预览图像中的对象。The object in the preview image is identified according to the object category to which each pixel in the preview image belongs.
根据权利要求13所述的电子设备，其中，在根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点之前，所述处理器还用于执行：The electronic device according to claim 13, wherein before determining a common composition anchor point for the first type object and the second type object based on the state information of the first type object and the second type object , The processor is also used to execute:

确定所述第一类对象在所述预览图像中对应的第一显示区域，以及确定所述第二类对象在所述预览图像中对应的第二显示区域；Determining a first display area corresponding to the first type object in the preview image, and determining a second display area corresponding to the second type object in the preview image;

当所述第一显示区域在所述预览图像中的第一面积占比大于第一预设比例，且所述第二显示区域在所述预览图像中的第二面积占比大于第二预设比例时，根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点。When the proportion of the first area of the first display area in the preview image is greater than the first preset proportion, and the proportion of the second area of the second display area in the preview image is greater than the second preset In the case of a ratio, a common composition positioning point is determined for the first-type object and the second-type object according to the state information of the first-type object and the second-type object.
根据权利要求14所述的电子设备，其中，在根据所述第一类对象和所述第二类对象的状态信息为所述第一类对象和第二类对象确定出共同的构图定位点时，所述处理器用于执行：The electronic device according to claim 14, wherein when a common composition anchor point is determined for the first-type object and the second-type object based on the state information of the first-type object and the second-type object , The processor is used to execute:

确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点；Determining a first center point of the first display area, and determining a second center point of the second display area;

获取所述第一显示区域与所述第二显示区域的面积比值；Acquiring an area ratio of the first display area to the second display area;

根据所述第一中心点、所述第二中心点以及所述面积比值确定所述构图定位点，所述构图定位点到所述第一中心点与所述第二中心点的距离之比等于所述面积比值。The composition positioning point is determined according to the first center point, the second center point, and the area ratio, and the ratio of the distance from the composition positioning point to the first center point to the second center point is equal to The area ratio.
根据权利要求15所述的电子设备，其中，在确定出所述第一显示区域的第一中心点，以及确定出所述第二显示区域的第二中心点时，所述处理器用于执行：The electronic device according to claim 15, wherein when the first center point of the first display area is determined and the second center point of the second display area is determined, the processor is configured to execute:

获取所述第一显示区域中所有像素点的第一坐标值均值，将所述第一坐标值均值对应的像素点确定为所述第一中心点；Acquiring an average value of the first coordinate values of all pixels in the first display area, and determining a pixel point corresponding to the average value of the first coordinate value as the first center point;

获取所述第二显示区域中所有像素点的第二坐标值均值，将所述第二坐标值均值对应的像素点确定为所述第二中心点。The second coordinate value average value of all pixels in the second display area is acquired, and the pixel point corresponding to the second coordinate value average value is determined as the second center point.
根据权利要求15所述的电子设备，其中，在获取所述第一显示区域与所述第二显示区域的面积比值时，所述处理器用于执行：The electronic device according to claim 15, wherein, when acquiring the area ratio of the first display area to the second display area, the processor is configured to execute:

获取所述第一显示区域与所述第二显示区域包含的像素点数量；Acquiring the number of pixels included in the first display area and the second display area;

计算出所述第一显示区域与所述第二显示区域包含的像素点数量比值；Calculating a ratio of the number of pixels contained in the first display area and the second display area;

将所述像素点数量比值作为所述面积比值。The ratio of the number of pixels is used as the area ratio.
根据权利要求12所述的电子设备，其中，在输出调整所述电子设备拍摄姿态的提示信息时，所述处理器用于执行：The electronic device according to claim 12, wherein, when outputting prompt information for adjusting the shooting posture of the electronic device, the processor is configured to execute:

在电子设备的拍摄预览界面上显示所述构图定位点与所述预设构图点；Displaying the composition positioning point and the preset composition point on the shooting preview interface of the electronic device;

在所述预览界面上显示所述构图定位点向所述预设构图点的移动方向，输出向所述移动方向调整所述电子设备拍摄姿态的提示信息。The movement direction of the composition positioning point to the preset composition point is displayed on the preview interface, and prompt information for adjusting the shooting posture of the electronic device in the movement direction is output.
根据权利要求18所述的电子设备，其中，在对待拍摄场景进行对象识别之后，所述处理器还用于执行：The electronic device according to claim 18, wherein, after performing object recognition on the scene to be photographed, the processor is further configured to execute:

对于识别出的各个对象，在所述拍摄预览界面上分别标注各对象的类别以及属于所述类别的概率。For each identified object, the category of each object and the probability of belonging to the category are respectively marked on the shooting preview interface.
根据权利要求12所述的电子设备，其中，在输出调整所述电子设备拍摄姿态的提示信息之后，所述处理器还用于执行：The electronic device according to claim 12, wherein after outputting prompt information for adjusting the shooting posture of the electronic device, the processor is further configured to execute:

当调整至所述预设定位点与预设构图点的位置匹配时，对所述待拍摄场景进行拍摄，得到所述待拍摄场景的成像图像。When the position of the preset positioning point and the preset composition point are adjusted to match, the scene to be photographed is photographed to obtain an imaging image of the scene to be photographed.