技术领域technical field
本发明涉及通信领域，具体而言，涉及一种辅助拍照方法、装置及终端。The present invention relates to the field of communications, and in particular, to a method, device and terminal for assisting in photographing.
背景技术Background technique
在工作和生活中，通常有如下拍照需求：对同一被拍摄对象，每隔一段时间需要进行一次拍照，然后将拍照结果组成图像序列，从而进行比较或记录。例如，每天在同一位置对场景进行拍摄，并根据拍摄场景分析天气的变化。In work and life, there is usually a demand for taking photos as follows: for the same subject to be photographed, it is necessary to take a photo at intervals, and then compose the photo results into an image sequence for comparison or recording. For example, the scene is filmed in the same location every day, and changes in the weather are analyzed according to the filmed scene.
由于需要进行比较或为了更好地观察效果，需要被拍摄对象在图像中的位置和姿态是基本一致的，即拍摄设备的拍摄位置和角度是基本一致的。相关技术中，通过将相机进行固定在一个位置，且固定为一种姿态，从而拍摄到上述一组图像。对于这种处理方式，拍照间隔时间较短则比较容易操作，然而如果拍照间隔时间较长，则很难将相机固定在一个位置，且固定为一种姿态，所以可能不具备可操作性。Due to the need for comparison or better observation of the effect, the position and posture of the subject in the image need to be basically the same, that is, the shooting position and angle of the shooting device are basically the same. In related technologies, the above-mentioned group of images is captured by fixing the camera at a position and in a posture. For this processing method, it is easier to operate if the interval between photographs is short. However, if the interval between photographs is long, it is difficult to fix the camera at a position and in a posture, so it may not be operable.
因此，在拍摄过程中，如何帮助用户获取被拍摄对象的位置和姿态基本一致的多张照片，是目前亟待解决的技术问题。Therefore, during the shooting process, how to help the user obtain a plurality of photos in which the positions and postures of the objects to be photographed are basically the same is a technical problem to be solved urgently.
发明内容Contents of the invention
本发明的目的，在于提供一种辅助拍照方法、装置及终端，以解决上述问题至少之一。The object of the present invention is to provide an auxiliary photographing method, device and terminal to solve at least one of the above problems.
根据本发明的第一方面，提供了一种辅助拍照方法。According to a first aspect of the present invention, an auxiliary photographing method is provided.
根据本发明的辅助拍照方法包括：在进行场景拍摄时，实时地获取图像帧；将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配；实时地输出匹配得到的匹配度。The auxiliary photographing method according to the present invention includes: acquiring an image frame in real time when shooting a scene; matching the currently acquired image frame with a template image corresponding to the scene in real time; and outputting a matching degree obtained by matching in real time.
将上述图像帧实时地与上述模板图像进行匹配包括：获取上述模板图像的第一特征点；获取上述图像帧的第二特征点；使用上述第一特征点与上述第二特征点实时地进行匹配得到上述匹配度。Matching the image frame with the template image in real time includes: acquiring the first feature point of the template image; acquiring the second feature point of the image frame; using the first feature point to match the second feature point in real time Get the matching degree above.
获取上述第一特征点和上述第二特征点包括：分别对上述图像帧和上述模板图像提取轮廓特征；在提取的轮廓特征中，删除长度小于第一阈值的轮廓特征；删除响应小于第二阈值的图像角点；将执行删除操作后的轮廓特征和角点确定为特征点；对特征点进行筛选处理，直至特征点均衡分布，并确定各特征点邻域内的边缘方向，得到最终特征点。Obtaining the above-mentioned first feature point and the above-mentioned second feature point includes: extracting contour features from the above-mentioned image frame and the above-mentioned template image respectively; among the extracted contour features, deleting the contour features whose length is less than the first threshold; deleting the response less than the second threshold The corner points of the image; the contour features and corner points after the deletion operation are determined as feature points; the feature points are screened until the feature points are evenly distributed, and the edge direction in the neighborhood of each feature point is determined to obtain the final feature point.
将上述图像帧实时地与上述模板图像进行匹配包括：通过图像纹理分析，分别将上述图像帧和上述模板图像划分为多个纹理单一的区域；对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配。Matching the above-mentioned image frame with the above-mentioned template image in real time includes: respectively dividing the above-mentioned image frame and the above-mentioned template image into a plurality of regions with single texture through image texture analysis; The block area, which is matched block by block.
在将上述图像帧实时地与上述模板图像进行匹配之前，还包括：响应用户操作，设置上述模板图像各个选择区域的匹配权重；将上述图像帧实时地与上述模板图像进行匹配包括：根据上述匹配权重确定上述匹配度。Before matching the above-mentioned image frame with the above-mentioned template image in real time, it also includes: responding to user operation, setting the matching weight of each selected area of the above-mentioned template image; matching the above-mentioned image frame with the above-mentioned template image in real time includes: according to the above-mentioned matching The weights determine the degree of matching described above.
在将当前获取的上述图像帧实时地与预设的模板图像进行匹配之前，还包括：在对上述场景第一次拍照后，将得到的照片确定为上述模板图像；从对上述场景第二次拍照开始，在每次拍照后，将当前拍摄得到的所有照片求平均，获取平均后的照片，确定为上述模板图像。Before matching the above-mentioned image frame currently acquired with the preset template image in real time, it also includes: after taking a photo of the above-mentioned scene for the first time, determining the obtained photo as the above-mentioned template image; At the beginning of taking a photo, after each photo is taken, all the photos currently taken are averaged, and the averaged photo is obtained, which is determined as the above-mentioned template image.
在实时地获取图像帧之前，还包括：对上述模板图像进行处理，得到拍摄参考图像，其中，上述拍摄参考图像为从上述模板图像中获取的第一特征点，或者上述拍摄参考图像为半透明的上述模板图像；将上述拍摄参考图像与上述终端实时拍摄的图像叠加。Before acquiring the image frame in real time, it also includes: processing the above-mentioned template image to obtain a shooting reference image, wherein the above-mentioned shooting reference image is the first feature point obtained from the above-mentioned template image, or the above-mentioned shooting reference image is translucent The above-mentioned template image; superimposing the above-mentioned shooting reference image and the image captured by the above-mentioned terminal in real time.
在输出匹配得到的上述匹配度时，还包括：通过特征点匹配，获取将上述图像帧变换至上述模板图像的变换矩阵；采用上述变换矩阵对上述当前的图像帧进行变换处理，以变换到上述模板图像的姿态。When outputting the above-mentioned matching degree obtained by matching, it also includes: obtaining a transformation matrix for transforming the above-mentioned image frame into the above-mentioned template image through feature point matching; using the above-mentioned transformation matrix to perform transformation processing on the above-mentioned current image frame to transform to the above-mentioned The pose of the template image.
根据本发明的第二方面，提供了一种辅助拍照装置。According to a second aspect of the present invention, an auxiliary photographing device is provided.
根据本发明的辅助拍照装置包括：第一获取模块，用于在进行场景拍摄时，实时地获取图像帧；匹配模块，用于在将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配；输出模块，用于实时地输出匹配得到的匹配度。The auxiliary photographing device according to the present invention includes: a first acquiring module, used to acquire an image frame in real time when shooting a scene; a matching module, used to match the currently acquired image frame to a template image corresponding to the above scene in real time performing matching; an output module configured to output a matching degree obtained by matching in real time.
上述匹配模块包括：第一获取单元，用于提取上述模板图像的第一特征点；第二获取单元，用于获取上述图像帧的第二特征点；第一匹配单元，用于使用上述第一特征点与上述第二特征点实时地进行匹配得到上述匹配度。The above-mentioned matching module includes: a first acquisition unit for extracting the first feature point of the above-mentioned template image; a second acquisition unit for acquiring the second feature point of the above-mentioned image frame; a first matching unit for using the above-mentioned first feature point The feature points are matched with the second feature points in real time to obtain the matching degree.
上述匹配模块包括：纹理分析模块，用于通过图像纹理分析，分别将上述图像帧和上述模板图像划分为多个纹理单一的区域；第二匹配单元，用于对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配。The above-mentioned matching module includes: a texture analysis module, which is used to divide the above-mentioned image frame and the above-mentioned template image into a plurality of regions with a single texture through image texture analysis; Each divided area is matched block by block.
上述装置还包括：设置模块，用于响应用户操作，设置上述模板图像中各个选择区域的匹配权重；上述匹配模块还包括：确定单元，用于根据上述匹配权重确定上述匹配度。The above device also includes: a setting module, configured to respond to user operations, and set the matching weights of each selected area in the template image; the above matching module further includes: a determining unit, configured to determine the matching degree according to the matching weights.
上述装置还包括：第一确定模块，用于在对上述场景第一次拍照后，将得到的照片确定为上述模板图像；第二确定模块，用于从对上述场景第二次拍照开始，在每次拍照后，将当前拍摄得到的所有照片求平均，获取平均后的照片，确定为上述模板图像。The above-mentioned device also includes: a first determination module, configured to determine the obtained photo as the template image after taking a photo of the above-mentioned scene for the first time; a second determination module, used to start from the second photo-taking of the above-mentioned scene, and After each photo is taken, all the photos currently taken are averaged, and the averaged photo is obtained, which is determined as the above template image.
上述装置还包括：第二获取模块，用于对上述模板图像进行处理，得到拍摄参考图像，其中，上述拍摄参考图像包括从上述模板图像中获取的第一特征点，或者上述拍摄参考图像为半透明的上述模板图像；叠加模块，用于将上述拍摄参考图像与上述终端实时拍摄的图像叠加。The above-mentioned device also includes: a second acquisition module, configured to process the above-mentioned template image to obtain a shooting reference image, wherein the above-mentioned shooting reference image includes the first feature points obtained from the above-mentioned template image, or the above-mentioned shooting reference image is half The above-mentioned transparent template image; an overlay module, configured to overlay the above-mentioned captured reference image and the image captured by the above-mentioned terminal in real time.
上述装置还包括：第三获取模块，用于通过特征点匹配，获取将上述图像帧变换至上述模板图像的变换矩阵；处理模块，用于采用上述变换矩阵对上述当前的图像帧进行变换处理，以变换到上述模板图像的姿态。The above device also includes: a third acquisition module, configured to obtain a transformation matrix for transforming the above image frame into the above template image through feature point matching; a processing module, configured to use the above transformation matrix to perform transformation processing on the above current image frame, In the pose transformed to the template image above.
根据本发明的第三方面，提供了一种终端。According to a third aspect of the present invention, a terminal is provided.
根据本发明的终端包括：一个或多个处理器；存储器；和一个或多个模块，上述一个或多个模块存储于上述存储器中并被配置成由上述一个或多个处理器执行，上述一个或多个模块用于：在进行场景拍摄时，实时地获取图像帧；将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配；实时地输出匹配得到的匹配度。The terminal according to the present invention includes: one or more processors; memory; and one or more modules, the one or more modules are stored in the memory and configured to be executed by the one or more processors, the one or more modules One or more modules are used to: acquire image frames in real time when shooting a scene; match the currently acquired image frames with the template image corresponding to the above scene in real time; and output the matching degree obtained by matching in real time.
本公开的实施例提供的技术方案可以包括以下有益效果：与现有技术中的当拍照间隔时间较长，很难将相机固定在一个位置且固定为一种姿态，因而不具备可操作性相比，在对场景拍摄时，将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配，实时地输出匹配得到的匹配度，可以辅助用户获取被拍摄对象的位置和姿态基本一致的多张照片，从而有效提高用户体验。The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: Compared with the prior art, when the time interval between taking photos is long, it is difficult to fix the camera at a position and in a posture, so it is not operable. For example, when shooting a scene, the currently acquired image frame is matched with the template image corresponding to the above scene in real time, and the matching degree obtained by the matching is output in real time, which can assist the user to obtain the image that the position and posture of the object to be photographed are basically consistent. Multiple photos, thus effectively improving the user experience.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性的，并不能限制本公开。It is to be understood that both the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure.
附图说明Description of drawings
图1为根据本发明实施例的辅助拍照方法的流程图；Fig. 1 is the flow chart of the auxiliary photographing method according to the embodiment of the present invention;
图2为根据本发明实施例一的辅助拍照方法的流程图；FIG. 2 is a flow chart of a method for assisting photographing according to Embodiment 1 of the present invention;
图3为根据本发明实施例一的辅助拍照方法的流程图；FIG. 3 is a flow chart of a method for assisting photographing according to Embodiment 1 of the present invention;
图4为根据本发明实施例的辅助拍照装置的结构框图；Fig. 4 is a structural block diagram of an auxiliary photographing device according to an embodiment of the present invention;
图5为根据本发明实施例一的辅助拍照装置的结构框图；5 is a structural block diagram of an auxiliary photographing device according to Embodiment 1 of the present invention;
图6为根据本发明实施例二的辅助拍照装置的结构框图；以及6 is a structural block diagram of an auxiliary photographing device according to Embodiment 2 of the present invention; and
图7为根据本发明实施例的终端的结构示意图。Fig. 7 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本发明的实施例，并与说明书一起用于解释本发明的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.
具体实施方式Detailed ways
下面通过具体的实施例子并结合附图对本发明做进一步的详细描述。The present invention will be described in further detail below through specific implementation examples and in conjunction with the accompanying drawings.
图1为根据本发明实施例的辅助拍照方法的流程图。如图1所示，该辅助拍照方法主要包括以下处理：FIG. 1 is a flowchart of a method for assisting in photographing according to an embodiment of the present invention. As shown in Figure 1, the auxiliary photographing method mainly includes the following processing:
在步骤S101中，在进行场景拍摄时，实时地获取图像帧；In step S101, during scene shooting, image frames are acquired in real time;
在步骤S103中，将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配；In step S103, matching the above-mentioned image frame currently acquired with the template image corresponding to the above-mentioned scene in real time;
在步骤S105中，实时地输出匹配得到的匹配度。In step S105, the matching degree obtained by matching is output in real time.
图1所示的方法中，在进行场景拍摄时，将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配，实时地输出匹配得到的匹配度，可以辅助用户获取被拍摄对象的位置和姿态基本一致的多张照片，从而有效提高用户体验。In the method shown in FIG. 1, when shooting a scene, the image frame currently acquired is matched with the template image corresponding to the scene in real time, and the matching degree obtained by matching is output in real time, which can assist the user to obtain the image of the object being photographed. Multiple photos with basically the same position and posture can effectively improve user experience.
上文所述的模板图像可以通过以下方式确定：在针对上述场景第一次拍照后，将得到的照片确定为上述模板图像；从针对上述场景第二次拍照开始，在每次拍照后，将当前拍摄得到的所有照片加权求平均，获取平均后的照片，确定为上述模板图像。The above-mentioned template image can be determined in the following manner: after taking the first photo of the above-mentioned scene, the obtained photo is determined as the above-mentioned template image; starting from the second photo-taking of the above-mentioned scene, after each photo-taking, All the currently captured photos are weighted and averaged, and the averaged photo is obtained and determined as the above template image.
通过上述处理，从终端第二次拍照开始，在每次拍照后，由于是将当前拍摄得到的所有照片加权求平均后的照片中更新为上述模板图像，因此，有效保证了针对场景拍摄得到的各张照片之间被拍摄对象的位置和姿态更加接近。Through the above processing, starting from the second time the terminal takes pictures, after each time the pictures are taken, the weighted and averaged pictures of all the pictures currently taken are updated to the above-mentioned template images, therefore, it is effectively ensured that the pictures taken for the scene The positions and poses of the subjects are closer between each photo.
其中，对于图像的求平均方法，可以如下：Among them, the average method for the image can be as follows:
以用户共拍照得到10张照片为例，需要对于每个像素点进行如下处理：Taking a total of 10 photos taken by the user as an example, each pixel needs to be processed as follows:
将每张图片中对应的像素点的像素值(例如RGB值)相加，并除以10得到平均像素值。The pixel values (for example, RGB values) of corresponding pixel points in each picture are summed up, and divided by 10 to obtain an average pixel value.
在对每个像素进行处理后，将全部处理后的像素点组成平均图像。After processing each pixel, all the processed pixels form an average image.
其中，在对图像求平均时，可以进行加权，也可以不进行加权。Wherein, when averaging images, weighting may or may not be performed.
当然，在具体实现过程中，也可以始终将第一次拍照后得到的照片确定为上述模板图像，这种方案更简单，更易于实现。Of course, in the specific implementation process, the photo obtained after the first photo taking can always be determined as the above template image, which is simpler and easier to implement.
在实时地获取图像帧之前，还可以包括以下处理：对上述模板图像进行处理，得到拍摄参考图像，其中，该拍摄参考图像为从模板图像中获取的第一特征点(本文中第一特征点指从模板图像中获取的特征点，第二特征点指从当前获取的图像帧中获取的特征点)，或者上述拍摄参考图像为半透明的上述模板图像；将上述拍摄参考图像与上述终端实时拍摄的图像叠加，具体地，将拍摄参考图像叠加在上述终端实时拍摄的图像上层并输出给用户。Before acquiring the image frame in real time, the following processing may also be included: the above-mentioned template image is processed to obtain a shooting reference image, wherein the shooting reference image is the first feature point (the first feature point in this paper) obtained from the template image Refers to the feature points obtained from the template image, the second feature point refers to the feature points obtained from the currently acquired image frame), or the above-mentioned template image that the above-mentioned shooting reference image is translucent; the above-mentioned shooting reference image and the above-mentioned terminal are real-time The captured image is superimposed, specifically, the captured reference image is superimposed on the image captured by the terminal in real time and output to the user.
为了更好地辅助用户得到与模板图像中被拍摄对象的位置和姿态更为接近的照片，可以在实时拍摄的图像上叠加拍摄参考图像，引导用户调整到最佳位置，从而获取与模板图像更为匹配的照片。In order to better assist the user to obtain a photo that is closer to the position and posture of the subject in the template image, the reference image can be superimposed on the real-time captured image to guide the user to adjust to the best position, so as to obtain a photo that is closer to the template image. for matching photos.
可以采用多种方式获取拍摄参考图像来引导用户调整到最佳位置。例如，方式一：从上述模板图像中获取第一特征点，将第一特征点叠加在上述终端实时拍摄的图像上层并输出给用户，用户在针对上述场景的拍摄过程中，根据第一特征点不断调整拍摄位置；方式二：对模板图像进行半透明化处理，得到半透明化的模板图像，并半透明化的该模板图像叠加在终端实时拍摄的图像上层，用户在针对上述场景的拍摄过程中，根据半透明化的模板图像不断调整拍摄位置。A shooting reference image may be obtained in various ways to guide the user to adjust to the best position. For example, method 1: obtain the first feature point from the above-mentioned template image, superimpose the first feature point on the upper layer of the image captured by the above-mentioned terminal in real time and output it to the user. Constantly adjust the shooting position; Method 2: Translucently process the template image to obtain a translucent template image, and superimpose the translucent template image on the upper layer of the image captured by the terminal in real time. In , the shooting position is constantly adjusted according to the translucent template image.
上述步骤S103中，可以采用多种方式将上述图像帧实时地与上述模板图像进行匹配。例如：In the above-mentioned step S103, the above-mentioned image frame can be matched with the above-mentioned template image in real time in various ways. For example:
方式一：获取上述模板图像的第一特征点；获取上述图像帧的第二特征点；使用上述第一特征点与上述第二特征点将上述模板图像与上述图像帧实时地进行匹配得到上述匹配度。Method 1: Obtain the first feature point of the above-mentioned template image; obtain the second feature point of the above-mentioned image frame; use the above-mentioned first feature point and the above-mentioned second feature point to match the above-mentioned template image and the above-mentioned image frame in real time to obtain the above-mentioned matching Spend.
上述获取模板图像的第一特征点可以进一步包括以下处理：The above-mentioned acquisition of the first feature point of the template image may further include the following processing:
1、对上述模板图像提取轮廓特征；1. Extract contour features from the above template image;
2、在提取的轮廓特征中，删除长度小于第一阈值的轮廓特征和响应小于第二阈值的图像角点；2. Among the extracted contour features, delete contour features whose length is less than the first threshold and image corners whose response is less than the second threshold;
3、将执行删除操作后的轮廓特征和角点确定为特征点，对特征点进行筛选处理，直至特征点均衡分布，并确定各特征点邻域内的边缘方向，得到最终特征点。3. The contour features and corner points after the deletion operation are determined as feature points, and the feature points are screened until the feature points are evenly distributed, and the edge direction in the neighborhood of each feature point is determined to obtain the final feature point.
同理，上述获取图像帧的第二特征点也可以进一步包括以下处理：Similarly, the above acquisition of the second feature point of the image frame may further include the following processing:
1、对上述图像帧提取轮廓特征；1. Extract contour features from the above image frame;
2、在提取的轮廓特征中，删除长度小于第一阈值的轮廓特征和响应小于第二阈值的图像角点；2. Among the extracted contour features, delete contour features whose length is less than the first threshold and image corners whose response is less than the second threshold;
3、将执行删除操作后的轮廓特征和角点确定为特征点，对特征点进行筛选处理，直至特征点均衡分布，并确定各特征点邻域内的边缘方向，得到最终特征点。3. The contour features and corner points after the deletion operation are determined as feature points, and the feature points are screened until the feature points are evenly distributed, and the edge direction in the neighborhood of each feature point is determined to obtain the final feature point.
可以采用以下方式从模板图像或者图像帧中提取轮廓特征：对模板图像或图像帧进行二值化处理，将模板图像或图像帧转换为只包括黑白两种颜色的图像，以区分各图像的目标区域与背景区域。从该二值化处理后的模板图像或图像帧的目标区域中提取轮廓特征。Contour features can be extracted from the template image or image frame in the following ways: Binarize the template image or image frame, convert the template image or image frame into an image that only includes black and white colors, to distinguish the target of each image area and background area. Contour features are extracted from the binarized template image or the target area of the image frame.
使用上述第一特征点与上述第二特征点将上述模板图像与上述图像帧实时地进行匹配可以进一步包括以下处理：Using the first feature point and the second feature point to match the template image with the image frame in real time may further include the following processing:
首先对需要匹配的两幅图像(模板图像和当前获取的图像帧)分别提取特征点，得到两个特征点集合。以每一个特征点为中心，计算该特征点领域内的边缘方向，将其邻域内的像素值作为该特征点的描述符，确定模板图像中每一个特征点的坐标位置，分别在上述图像帧查找以该坐标位置对应的局部区域内存在的以特征点为中心的邻域。计算对应的两个邻域的重叠部分的像素差的平方和。根据平方和的计算结果确定对应的两个邻域的匹配度。综合两幅图像中对应的邻域的匹配度计算结果，确定两幅图像的匹配度。Firstly, feature points are extracted from the two images (template image and currently acquired image frame) to be matched to obtain two sets of feature points. Taking each feature point as the center, calculate the edge direction in the field of the feature point, and use the pixel value in its neighborhood as the descriptor of the feature point to determine the coordinate position of each feature point in the template image, respectively in the above image frame Find the neighborhood centered on the feature point that exists in the local area corresponding to the coordinate position. Computes the sum of squares of the pixel differences in the overlapping parts of the corresponding two neighborhoods. The matching degree of the corresponding two neighborhoods is determined according to the calculation result of the sum of squares. The matching degree calculation results of the corresponding neighborhoods in the two images are integrated to determine the matching degree of the two images.
方式二：通过图像纹理分析，分别将上述图像帧和上述模板图像划分为多个纹理单一的区域；对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配。Method 2: through image texture analysis, divide the above-mentioned image frame and the above-mentioned template image into a plurality of single-textured regions respectively; and perform matching block by block for the divided regions in the above-mentioned image frame and the above-mentioned template image.
其中，纹理分析指的是通过一定的图像处理技术抽取出纹理特征，从而获得纹理的定量或定性描述的处理过程。具体地，需要对图像进行纹理特征分析，按照纹理相似性程度进行区域生长，将图像帧和上述模板图像分别分割成多个纹理单一区域。Among them, texture analysis refers to the process of extracting texture features through certain image processing techniques to obtain quantitative or qualitative descriptions of textures. Specifically, it is necessary to analyze the texture features of the image, perform region growth according to the degree of texture similarity, and divide the image frame and the above-mentioned template image into multiple regions with a single texture.
对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配可以进一步包括以下处理：确定模板图像中每一个纹理区域的坐标位置，分别在上述图像帧中查找与该坐标位置对应的局部区域内的纹理区域。计算对应的两个纹理区域的解视差值,得到纹理单一区域的稠密视差图。根据计算结果确定对应的两个纹理区域的匹配度。综合两幅图像中对应的纹理区域的匹配度计算结果，确定两幅图像的匹配度。For each block area divided in the above-mentioned image frame and the above-mentioned template image, performing block-by-block matching may further include the following processing: determine the coordinate position of each texture area in the template image, and search for the coordinate position corresponding to the coordinate position in the above-mentioned image frame Texture regions within the local region of . Calculate the disparity values of the corresponding two texture regions, and obtain the dense disparity map of the single texture region. The matching degree of the corresponding two texture regions is determined according to the calculation result. The matching degree calculation results of the corresponding texture regions in the two images are integrated to determine the matching degree of the two images.
在将上述图像帧实时地与上述模板图像进行匹配之前，还可以包括以下处理：响应用户操作，设置上述模板图像各个选择区域的匹配权重；将上述图像帧实时地与上述模板图像进行匹配包括：根据上述匹配权重确定上述匹配度。Before the above-mentioned image frame is matched with the above-mentioned template image in real time, the following processing may also be included: responding to the user operation, setting the matching weight of each selected area of the above-mentioned template image; matching the above-mentioned image frame with the above-mentioned template image in real time includes: The matching degree is determined according to the matching weight.
用户可以在模板图像(例如，第一拍摄后的照片)中手动选择需要重点匹配的区域，或者非重点匹配的区域，构造一个匹配权重图，重点匹配区域拥有较大权重，非重点区域权重较小。例如，上面提到的综合两幅图像中对应的纹理区域的匹配度计算结果，确定两幅图像的匹配度时，可以考虑匹配权重图中各个区域对应的权重值，即需要重点匹配的区域对应的权重值较大，非重点匹配的区域对应的权重值较小，甚至有些无需关注的区域对应的权重值可以设置为零。因此，由于在计算两幅图像的匹配度时结合了权重值这个参数，进一步优化了匹配结果。In the template image (for example, the photo after the first shot), the user can manually select the area that needs to be matched with key points, or the area that is not key to match, and construct a matching weight map. Small. For example, when calculating the matching results of the corresponding texture regions in the two images mentioned above, when determining the matching degree of the two images, you can consider the weight values corresponding to each region in the matching weight map, that is, the regions that need to be matched correspond to The weight value corresponding to the non-key matching area is relatively large, and the weight value corresponding to some areas that do not need to be concerned can even be set to zero. Therefore, since the parameter of weight value is combined when calculating the matching degree of two images, the matching result is further optimized.
在输出匹配得到的上述匹配度时，还可以包括以下处理：通过特征点匹配，获取将上述图像帧变换至上述模板图像的变换矩阵；采用上述变换矩阵对上述当前的图像帧进行变换处理，以变换到上述模板图像的姿态。When outputting the above-mentioned degree of matching obtained by matching, the following processing may also be included: through feature point matching, obtain a transformation matrix that transforms the above-mentioned image frame into the above-mentioned template image; use the above-mentioned transformation matrix to perform transformation processing on the above-mentioned current image frame, to Transform to the pose of the template image above.
上面提到的方案中，虽然在用户拍摄时，可以实时给出当前匹配度(例如，匹配分数)，但仍需要用户手动调整，来找到一个精确的位置。使用特征点匹配技术，获取当前图像向模板图像的变换矩阵，将当前图像变换到模板图像的姿态。这样，用户在调整时无需非常精确，只需要大概对齐即可，因而有效提高了用户体验。In the solution mentioned above, although the current matching degree (for example, matching score) can be given in real time when the user is shooting, the user still needs to manually adjust to find an accurate position. Use the feature point matching technology to obtain the transformation matrix from the current image to the template image, and transform the current image to the pose of the template image. In this way, the user does not need to be very precise when adjusting, but only roughly aligns, thus effectively improving user experience.
以下结合图2和图3进一步描述上述实施方式。The above embodiment will be further described below with reference to FIG. 2 and FIG. 3 .
图2为根据本发明实施例一的辅助拍照方法的流程图。如图2所示，终端第一次拍摄图像帧时，该辅助拍照方法主要包括以下处理：FIG. 2 is a flow chart of a method for assisting photographing according to Embodiment 1 of the present invention. As shown in Figure 2, when the terminal captures an image frame for the first time, the auxiliary photographing method mainly includes the following processing:
在步骤S201中，在对上述场景第一次拍照后，得到图像帧。In step S201, an image frame is obtained after the above-mentioned scene is photographed for the first time.
在步骤S203中，对得到的图像帧进行模糊、降采样处理。In step S203, the obtained image frame is blurred and down-sampled.
由于本发明中每两次拍摄时间间隔较长，拍摄景物除主体不变外，可能会有小幅变动，如景物中花草树木的变化、颜色变化、有运动物体干扰等。本发明只关注图像中大尺度上的匹配，对于细微变化不予以关注，所以可以将图像进行高斯模糊、然后降采样，这样既可以去除噪声、又降低了处理复杂度。Because the time interval of every two shots in the present invention is long, except for the main body of the shooting scene, there may be small changes, such as changes in flowers, plants and trees in the scene, color changes, and interference from moving objects. The present invention only pays attention to the large-scale matching in the image, and does not pay attention to the subtle changes, so the image can be Gaussian blurred and then down-sampled, which can not only remove noise, but also reduce processing complexity.
在步骤S205中，对得到的图像帧去除光照影响。In step S205, the influence of illumination is removed from the obtained image frame.
由于两次拍摄天气、光照可能有很大区别，从而影响到图像匹配，所以匹配前需要对图像进行处理以去除光照影响。例如，可以采用Retinex图像增强方法，降低光照对图像的影响。Since the weather and lighting of the two shots may be very different, which will affect the image matching, the image needs to be processed before matching to remove the lighting effect. For example, the Retinex image enhancement method can be used to reduce the influence of light on the image.
在步骤S207中，对得到的图像帧提取特征点。In step S207, feature points are extracted from the obtained image frame.
提取特征点可以进一步包括以下处理：Extracting feature points may further include the following processing:
1、对上述图像帧提取轮廓特征。1. Extract contour features from the above image frames.
2、在提取的轮廓特征中，删除长度小于第一阈值的边缘轮廓和响应小于第二阈值的图像角点。其中，上述第一阈值和第二阈值可以根据实际情况动态设置。2. In the extracted contour feature, delete the edge contour whose length is less than the first threshold and the image corners whose response is less than the second threshold. Wherein, the above-mentioned first threshold and second threshold may be dynamically set according to actual conditions.
3、将执行删除操作后的轮廓特征和角点确定为特征点，对特征点进行筛选处理，直至特征点均衡分布，即整张图像上单位面积内特征点的个数差别不应该过大，以防在图像的某个区域过度聚集，造成匹配时过度倾向于密集纹理区域。3. Determine the contour features and corner points after the deletion operation as feature points, and filter the feature points until the feature points are evenly distributed, that is, the difference in the number of feature points per unit area on the entire image should not be too large. In order to prevent excessive aggregation in a certain area of the image, causing excessive preference for dense texture areas when matching.
4、计算各特征点邻域内的边缘方向。4. Calculate the edge direction in the neighborhood of each feature point.
在步骤S209中，将提取的特征点进行保存，其中，将当前图像帧设置为上文所述的模板图像。In step S209, the extracted feature points are saved, wherein the current image frame is set as the above-mentioned template image.
在对图像帧进行上述处理后，可以有效去除噪声、降低处理复杂度，并降低光照对图像的影响。此外，对特征点进行筛选处理，均衡特征点分布，可以防止在图像的某个区域过度聚集，造成匹配时过度倾向于密集纹理区域。因此，通过上述处理，便于后续更有效地执行图像匹配。After the above processing is performed on the image frame, noise can be effectively removed, processing complexity can be reduced, and the influence of light on the image can be reduced. In addition, screening the feature points and balancing the distribution of feature points can prevent excessive aggregation in a certain area of the image, resulting in excessive preference for dense texture areas during matching. Therefore, through the above processing, it is convenient to perform image matching more efficiently later.
图3为根据本发明实施例二的辅助拍照方法的流程图。如图3所示，除终端第一次拍摄图像帧之外，其余每次拍摄图像帧，主要包括以下处理：FIG. 3 is a flow chart of a method for assisting photographing according to Embodiment 2 of the present invention. As shown in Figure 3, except for the first image frame captured by the terminal, the other image frames captured each time mainly include the following processing:
在步骤S301中，上述终端针对上述场景拍照后，得到图像帧。In step S301, the terminal obtains an image frame after taking a picture of the scene.
在步骤S303中，对得到的图像帧进行模糊、降采样处理。In step S303, the obtained image frame is blurred and down-sampled.
在步骤S305中，对得到的图像帧去除光照影响。In step S305, the influence of illumination is removed from the obtained image frame.
在步骤S307中，对得到的图像帧提取特征点。具体可以参见上述步骤S207的描述，此处不再赘述。In step S307, feature points are extracted from the obtained image frame. For details, refer to the description of the above step S207, which will not be repeated here.
在步骤S309中，使用该图像帧中提取的特征点与模板图像中提取的特征点进行图像匹配，得到匹配分数。In step S309, image matching is performed using the feature points extracted in the image frame and the feature points extracted in the template image to obtain a matching score.
在步骤S311中，通过匹配分数，引导用户将终端调整到最佳位置(即对应匹配分数最大的位置)，拍摄图像。In step S311, the user is guided to adjust the terminal to an optimal position (that is, the position corresponding to the maximum matching score) according to the matching score, and take an image.
在步骤S313中，计算序列图像平均图(即将当前拍摄得到的所有照片求平均)并更新为模板图像，按照步骤S303，步骤S305，以及步骤S307提取序列图像平均图的特征点，并进行保存。In step S313, the sequence image average map is calculated (averaging all photos obtained by the current shooting) and updated as a template image, and the feature points of the sequence image average map are extracted according to step S303, step S305, and step S307, and saved.
通过图2和图3的处理，终端针对场景拍摄多次后，可以得到被拍摄对象位置和姿态基本一致的一个序列图像，该序列图像可以进行方便的比较，整个序列图像除平铺展开外，更适合的展现方式是进行动态展现，如存为GIF格式或短视频。Through the processing in Figure 2 and Figure 3, after the terminal shoots the scene multiple times, it can obtain a sequence of images with basically the same position and posture of the photographed object, which can be compared conveniently. A more suitable display method is to perform dynamic display, such as saving as GIF format or short video.
图4为根据本发明实施例的辅助拍照装置的结构框图。如图4所示，该辅助拍照装置主要包括：第一获取模块40，用于进行场景拍摄时，实时地获取图像帧；匹配模块42，与上述第一获取模块40相连接，用于在将当前获取的上述图像帧实时地与关于上述场景对应的模板图像进行匹配；输出模块44，与上述匹配模块42相连接，用于实时地输出匹配得到的匹配度。Fig. 4 is a structural block diagram of an auxiliary photographing device according to an embodiment of the present invention. As shown in Figure 4, the auxiliary photographing device mainly includes: a first acquisition module 40, which is used to acquire image frames in real time when shooting a scene; a matching module 42, which is connected with the above-mentioned first acquisition module 40, for The currently acquired image frame is matched with the template image corresponding to the above scene in real time; the output module 44 is connected with the matching module 42 and configured to output the matching degree obtained by matching in real time.
图4所示的装置中，在进行场景拍摄时，匹配模块32将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配，输出模块44实时地输出匹配得到的匹配度，可以辅助用户获取被拍摄对象的位置和姿态基本一致的多张照片，从而有效提高用户体验。In the device shown in FIG. 4 , when shooting a scene, the matching module 32 matches the above-mentioned image frame currently acquired with the template image corresponding to the above-mentioned scene in real time, and the output module 44 outputs the matching degree obtained by matching in real time, which can assist The user obtains a plurality of photos in which the positions and postures of the photographed objects are basically the same, thereby effectively improving the user experience.
如图5所示，上述匹配模块42可以进一步包括：第一获取单元420，用于提取上述模板图像的第一特征点；第二获取单元422，用于获取上述图像帧的第二特征点；第一匹配单元424，分别于第一获取单元420和第二获取单元422相连接，用于使用上述第一特征点与上述第二特征点实时地进行匹配得到上述匹配度。As shown in FIG. 5 , the matching module 42 may further include: a first acquisition unit 420, configured to extract the first feature point of the template image; a second acquisition unit 422, configured to acquire the second feature point of the image frame; The first matching unit 424 is connected to the first acquiring unit 420 and the second acquiring unit 422 respectively, and is configured to use the first feature point and the second feature point to match in real time to obtain the matching degree.
如图6所示，上述匹配模块42可以进一步包括：纹理分析模块426，用于通过图像纹理分析，分别将上述图像帧和上述模板图像划分为多个纹理单一的区域；第二匹配单元428，与纹理分析模块426相连接，用于对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配。As shown in FIG. 6, the above-mentioned matching module 42 may further include: a texture analysis module 426, which is used to divide the above-mentioned image frame and the above-mentioned template image into a plurality of regions with a single texture through image texture analysis; the second matching unit 428, It is connected with the texture analysis module 426, and is used to perform block-by-block matching on the divided block regions in the image frame and the template image.
如图5和图6所示，上述装置还可以包括：设置模块46，与上述匹配模块42相连接，用于响应用户操作，设置上述模板图像中各个选择区域的匹配权重；则上述匹配模块42还可以包括确定单元430，用于根据上述匹配权重确定上述匹配度。As shown in Figure 5 and Figure 6, the above-mentioned device can also include: a setting module 46, connected to the above-mentioned matching module 42, for responding to user operations, setting the matching weights of each selected area in the above-mentioned template image; then the above-mentioned matching module 42 A determining unit 430 may also be included, configured to determine the matching degree according to the matching weight.
如图5和图6所示，上述装置还可以包括：第一确定模块48，与上述匹配模块42相连接，用于在对上述场景第一次拍照后，将得到的照片确定为上述模板图像；第二确定模块50，与上述匹配模块42相连接，用于从对上述场景第二次拍照开始，在每次拍照后，将当前拍摄得到的所有照片求平均，获取平均后的照片，确定为上述模板图像。As shown in Fig. 5 and Fig. 6, the above-mentioned device may also include: a first determination module 48, connected to the above-mentioned matching module 42, for determining the obtained photo as the above-mentioned template image after taking a photo of the above-mentioned scene for the first time The second determination module 50 is connected with the above-mentioned matching module 42, and is used to start from taking pictures of the above-mentioned scene for the second time, after each picture, average all the pictures obtained by the current shooting, obtain the averaged pictures, and determine for the above template image.
如图5和图6所示，上述装置还可以包括：第二获取模块52，与所述输出模块44相连接，用于对上述模板图像进行处理，得到拍摄参考图像，其中，上述拍摄参考图像包括从上述模板图像中获取的第一特征点，或者上述拍摄参考图像为半透明的上述模板图像；叠加模块，用于将上述拍摄参考图像与上述终端实时拍摄的图像叠加。As shown in FIG. 5 and FIG. 6, the above-mentioned device may further include: a second acquisition module 52, connected to the output module 44, for processing the above-mentioned template image to obtain a shooting reference image, wherein the above-mentioned shooting reference image It includes the first feature point obtained from the above-mentioned template image, or the above-mentioned template image in which the above-mentioned photographing reference image is semi-transparent; and an overlay module, configured to superimpose the above-mentioned photographing reference image and the image captured by the terminal in real time.
如图5和图6所示，上述装置还可以包括：第三获取模块54，与匹配模块42相连接，用于通过特征点匹配，获取将上述图像帧变换至上述模板图像的变换矩阵；处理模块56，与上述第三获取模块54相连接，用于采用上述变换矩阵对上述当前的图像帧进行变换处理，以变换到上述模板图像的姿态。As shown in Figures 5 and 6, the above-mentioned device may also include: a third acquisition module 54, connected to the matching module 42, for obtaining a transformation matrix for converting the above-mentioned image frame to the above-mentioned template image through feature point matching; processing The module 56 is connected with the above-mentioned third obtaining module 54, and is used to transform the above-mentioned current image frame by using the above-mentioned transformation matrix, so as to transform to the posture of the above-mentioned template image.
上述装置中各模块，各单元相互结合的实施方式具体可以参见图1至图3的描述，此处不再赘述。The implementation of the combination of modules and units in the above-mentioned device can refer to the descriptions in FIG. 1 to FIG. 3 , which will not be repeated here.
图7为根据本发明实施例的终端的结构示意图。如图7所示，该终端可以用于实施上述实施例中提供的辅助拍照方法。其中，该终端可以为手机、数码相机、平板电脑pad、穿戴式移动设备(如智能眼镜)等。Fig. 7 is a schematic structural diagram of a terminal according to an embodiment of the present invention. As shown in FIG. 7 , the terminal can be used to implement the method for assisting in photographing provided in the foregoing embodiments. Wherein, the terminal may be a mobile phone, a digital camera, a tablet computer pad, a wearable mobile device (such as smart glasses), and the like.
终端可以包括通信单元710、包括有一个或一个以上计算机可读存储介质的存储器720、输入单元730、显示单元740、传感器750、音频电路760、无线保真(wireless fidelity，简称为WiFi)模块770、包括有一个或者一个以上处理核心的处理器780、以及电源790等部件。本领域技术人员可以理解，图7中示出的终端结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：The terminal may include a communication unit 710, a memory 720 including one or more computer-readable storage media, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, and a wireless fidelity (wireless fidelity, referred to as WiFi) module 770 , including a processor 780 with one or more processing cores, a power supply 790 and other components. Those skilled in the art can understand that the terminal structure shown in FIG. 7 does not constitute a limitation on the terminal, and may include more or less components than those shown in the figure, or combine some components, or arrange different components. in:
通信单元710可用于收发信息或通话过程中，信号的接收和发送，该通信单元710可以为射频(Radio Frequency，简称为RF)电路、路由器、调制解调器、等网络通信设备。特别地，当通信单元710为RF电路时，将基站的下行信息接收后，交由一个或者一个以上处理器780处理；另外，将涉及上行的数据发送给基站。通常，作为通信单元的RF电路包括但不限于天线、至少一个放大器、调谐器、一个或多个振荡器、用户身份模块(SIM)卡、收发信机、耦合器、低噪声放大器(Low Noise Amplifier，简称为LNA)、双工器等。此外，通信单元710还可以通过无线通信与网络和其他设备通信。无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯系统(Global System of Mobile communication，简称为GSM)、通用分组无线服务(General Packet Radio Service，简称为GPRS)、码分多址(Code Division Multiple Access，简称为CDMA)、宽带码分多址(Wideband Code Division Multiple Access,简称为WCDMA)、长期演进(Long Term Evolution,简称为LTE)、电子邮件、短消息服务(Short Messaging Service，简称为SMS)等。存储器720可用于存储软件程序以及模块，处理器780通过运行存储在存储器720的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器720可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据终端的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器720可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器720还可以包括存储器控制器，以提供处理器780和输入单元730对存储器720的访问。The communication unit 710 can be used to send and receive information or receive and send signals during a call. The communication unit 710 can be a radio frequency (Radio Frequency, referred to as RF) circuit, router, modem, and other network communication equipment. In particular, when the communication unit 710 is an RF circuit, after receiving the downlink information of the base station, it is processed by one or more processors 780; in addition, the uplink data is sent to the base station. Typically, an RF circuit serving as a communication unit includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a Low Noise Amplifier (LNA) , referred to as LNA), duplexer, etc. In addition, the communication unit 710 can also communicate with a network and other devices through wireless communication. Wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (GSM for short), General Packet Radio Service (GPRS for short), Code Division Multiple Access (Code Division Multiple Access, referred to as CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, referred to as WCDMA), long-term evolution (Long Term Evolution, referred to as LTE), e-mail, short message service (Short Messaging Service , referred to as SMS) and so on. The memory 720 can be used to store software programs and modules, and the processor 780 executes various functional applications and data processing by running the software programs and modules stored in the memory 720 . The memory 720 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of the terminal (such as audio data, phonebook, etc.) and the like. In addition, the memory 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 720 may further include a memory controller to provide access to the memory 720 by the processor 780 and the input unit 730 .
输入单元730可用于接收输入的数字或字符信息，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。输入单元730可包括触敏表面731以及其他输入设备732。触敏表面731，也称为触摸显示屏或者触控板，可收集The input unit 730 can be used to receive input numbers or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. The input unit 730 may include a touch-sensitive surface 731 and other input devices 732 . A touch-sensitive surface 731, also known as a touch screen or trackpad, collects
用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触敏表面731上或在触敏表面731附近的操作)，并根据预先设定的程式驱动相应的连接装置。The user's touch operation on or near it (such as the user's operation on or near the touch-sensitive surface 731 using any suitable object or accessory such as a finger or a stylus), and drives the corresponding connection device.
可选的，触敏表面731可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给处理器780，并能接收处理器780发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触敏表面731。除了触敏表面731，输入单元730还可以包括其他输入设备732。Optionally, the touch-sensitive surface 731 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the to the processor 780, and can receive and execute commands sent by the processor 780. In addition, the touch-sensitive surface 731 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 731 , the input unit 730 may also include other input devices 732 .
其他输入设备732可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。Other input devices 732 may include, but are not limited to, one or more of physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, joysticks, and the like.
显示单元740可用于显示由用户输入的信息或提供给用户的信息以及终端的各种图形用户接口，这些图形用户接口可以由图形、文本、图标、视频和其任意组合来构成。显示单元740可包括显示面板741，可选的，可以采用液晶显示器、有机发光二极管等形式来配置显示面板741。进一步的，触敏表面731可覆盖显示面板741，当触敏表面731检测到在其上或附近的触摸操作后，传送给处理器780以确定触摸事件的类型，随后处理器780根据触摸事件的类型在显示面板741上提供相应的视觉输出。虽然在图7中，触敏表面731与显示面板741是作为两个独立的部件来实现输入和输入功能，但是在某些实施例中，可以将触敏表面731与显示面板741集成而实现输入和输出功能。The display unit 740 can be used to display information input by or provided to the user and various graphical user interfaces of the terminal. These graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. The display unit 740 may include a display panel 741. Optionally, the display panel 741 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. Further, the touch-sensitive surface 731 may cover the display panel 741, and when the touch-sensitive surface 731 detects a touch operation on or near it, the touch operation is sent to the processor 780 to determine the type of the touch event, and then the processor 780 determines the type of the touch event according to the type of the touch event. The type provides a corresponding visual output on the display panel 741 . Although in FIG. 7, the touch-sensitive surface 731 and the display panel 741 are used as two independent components to realize input and input functions, in some embodiments, the touch-sensitive surface 731 and the display panel 741 can be integrated to realize input. and output functions.
终端还可包括至少一种传感器750，比如光传感器、运动传感器以及其他传感器。光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示面板741的亮度，接近传感器可在终端移动到耳边时，关闭显示面板741和/或背光。作为运动传感器的一种，重力加速度传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于识别手机姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等；至于终端还可配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。The terminal may also include at least one sensor 750, such as a light sensor, a motion sensor, and other sensors. The light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 741 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 741 and/or the backlight when the terminal moves to the ear. As a kind of motion sensor, the gravitational acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is stationary, and can be used for applications that recognize the attitude of mobile phones (such as horizontal and vertical screen switching, related Games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tap), etc.; as for other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. repeat.
音频电路760、扬声器761，传声器762可提供用户与终端之间的音频接口。音频电路760可将接收到的音频数据转换后的电信号，传输到扬声器761，由扬声器761转换为声音信号输出；另一方面，传声器762将收集的声音信号转换为电信号，由音频电路760接收后转换为音频数据，再将音频数据输出处理器180处理后，经RF电路710以发送给比如另一终端设备，或者将音频数据输出至存储器720以便进一步处理。音频电路760还可能包括耳塞插孔，以提供外设耳机与终端的通信。The audio circuit 760, the speaker 761, and the microphone 762 can provide an audio interface between the user and the terminal. The audio circuit 760 can transmit the electrical signal converted from the received audio data to the speaker 761, and the speaker 761 converts it into an audio signal for output; After being received, it is converted into audio data, and then the audio data is processed by the output processor 180, and then sent to another terminal device through the RF circuit 710, or the audio data is output to the memory 720 for further processing. The audio circuit 760 may also include an earphone jack to provide communication between an external earphone and the terminal.
为了实现无线通信，该终端设备上可以配置有无线通信单元770，该无线通信单元770可以为WiFi模块。WiFi属于短距离无线传输技术，终端通过无线通信单元770可以帮助用户收发电子邮件、浏览网页和访问流式媒体等，它为用户提供了无线的宽带互联网访问。虽然图7示出了无线通信单元770，但是可以理解的是，其并不属于终端的必须构成，完全可以根据需要在不改变发明的本质的范围内而省略。In order to realize wireless communication, a wireless communication unit 770 may be configured on the terminal device, and the wireless communication unit 770 may be a WiFi module. WiFi is a short-distance wireless transmission technology. Through the wireless communication unit 770, the terminal can help users send and receive emails, browse web pages, and access streaming media. It provides users with wireless broadband Internet access. Although FIG. 7 shows a wireless communication unit 770, it can be understood that it is not an essential component of the terminal, and can be completely omitted as required without changing the essence of the invention.
处理器780是终端的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在存储器720内的软件程序和/或模块，以及调用存储在存储器720内的数据，执行终端的各种功能和处理数据，从而对手机进行整体监控。可选的，处理器780可包括一个或多个处理核心；优选的，处理器780可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器780中。The processor 780 is the control center of the terminal. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and/or modules stored in the memory 720, and calling data stored in the memory 720, execution Various functions and processing data of the terminal, so as to monitor the mobile phone as a whole. Optionally, the processor 780 may include one or more processing cores; preferably, the processor 780 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc. , the modem processor mainly handles wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 780 .
终端还包括给各个部件供电的电源790(比如电池)，优选的，电源可以通过电源管理系统与处理器780逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源790还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。The terminal also includes a power supply 790 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 780 through the power management system, so that functions such as charging, discharging, and power consumption management can be implemented through the power management system. The power supply 790 may also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.
尽管未示出，终端还可以包括摄像头、蓝牙模块等，在此不再赘述。Although not shown, the terminal may also include a camera, a Bluetooth module, etc., which will not be repeated here.
在本实施例中，终端设备的显示单元是触摸屏显示器，终端设备还包括有存储器，以及一个或者一个以上的程序，其中一个或者一个以上程序存储于存储器中，且经配置以由一个或者一个以上处理器执行一个或者一个以上程序包含用于进行以下操作的指令：In this embodiment, the display unit of the terminal device is a touch screen display, and the terminal device also includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be used by one or more The processor executes one or more programs containing instructions for:
在对场景拍摄时，实时地获取图像帧；When shooting the scene, the image frame is acquired in real time;
将当前获取的上述图像帧实时地与上述场景对应的模板图像进行匹配；以及Matching the above-mentioned image frame currently acquired with the template image corresponding to the above-mentioned scene in real time; and
实时地输出匹配得到的匹配度。The matching degree obtained by matching is output in real time.
将上述图像帧实时地与上述模板图像进行匹配包括：获取上述模板图像的第一特征点；获取上述图像帧的第二特征点；使用上述第一特征点与上述第二特征点实时地进行匹配得到上述匹配度。这是本发明关键点，还应写具体一点Matching the image frame with the template image in real time includes: acquiring the first feature point of the template image; acquiring the second feature point of the image frame; using the first feature point to match the second feature point in real time Get the matching degree above. This is the key point of the present invention, and it should also be written in detail
获取上述第一特征点和上述第二特征点包括：分别对上述图像帧和上述模板图像提取轮廓特征；在提取的轮廓特征中，删除长度小于第一阈值的轮廓特征和响应小于第二阈值的图像角点；将执行删除操作后的轮廓特征和角点确定为特征点；对特征点进行筛选处理，直至特征点均衡分布，并确定各特征点邻域内的边缘方向，得到最终特征点。Obtaining the above-mentioned first feature point and the above-mentioned second feature point includes: extracting contour features from the above-mentioned image frame and the above-mentioned template image respectively; among the extracted contour features, deleting the contour features whose length is less than the first threshold and whose response is less than the second threshold Image corner points; the contour features and corner points after the deletion operation are determined as feature points; the feature points are screened until the feature points are evenly distributed, and the edge direction in the neighborhood of each feature point is determined to obtain the final feature point.
将上述图像帧实时地与上述模板图像进行匹配包括：通过图像纹理分析，分别将上述图像帧和上述模板图像划分为多个纹理单一的区域；对于上述图像帧和上述模板图像中划分后的各块区域，逐块进行匹配。Matching the above-mentioned image frame with the above-mentioned template image in real time includes: respectively dividing the above-mentioned image frame and the above-mentioned template image into a plurality of regions with single texture through image texture analysis; The block area, which is matched block by block.
在将上述图像帧实时地与上述模板图像进行匹配之前，还包括：响应用户操作，设置上述模板图像各个选择区域的匹配权重；将上述图像帧实时地与上述模板图像进行匹配包括：根据上述匹配权重确定上述匹配度。Before matching the above-mentioned image frame with the above-mentioned template image in real time, it also includes: responding to user operation, setting the matching weight of each selected area of the above-mentioned template image; matching the above-mentioned image frame with the above-mentioned template image in real time includes: according to the above-mentioned matching The weights determine the degree of matching described above.
上述指令还可以包括：在上述终端针对上述场景第一次拍照后，将得到的照片确定为上述模板图像；从上述终端针对上述场景第二次拍照开始，在每次拍照后，将当前拍摄得到的所有照片求平均，获取平均后的照片，确定为上述模板图像。The above instruction may also include: after the above-mentioned terminal takes a photo of the above-mentioned scene for the first time, determine the obtained photo as the above-mentioned template image; from the above-mentioned terminal to take a second photo of the above-mentioned scene, after each photo, the current photo is obtained All the photos of are averaged, and the averaged photos are obtained and determined as the above-mentioned template image.
在实时地获取图像帧之前，还可以包括：对上述模板图像进行处理，得到拍摄参考图像，其中，上述拍摄参考图像为从上述模板图像中获取的第一特征点，或者上述拍摄参考图像为半透明的上述模板图像；将上述拍摄参考图像与上述终端实时拍摄的图像叠加。Before acquiring the image frame in real time, it may also include: processing the above-mentioned template image to obtain a shooting reference image, wherein the above-mentioned shooting reference image is the first feature point obtained from the above-mentioned template image, or the above-mentioned shooting reference image is half The above-mentioned template image is transparent; the above-mentioned shooting reference image is superimposed with the image captured by the above-mentioned terminal in real time.
在输出匹配得到的上述匹配度时，还包括：通过特征点匹配，获取将上述图像帧变换至上述模板图像的变换矩阵；采用上述变换矩阵对上述当前的图像帧进行变换处理，以变换到上述模板图像的姿态。When outputting the above-mentioned matching degree obtained by matching, it also includes: obtaining a transformation matrix for transforming the above-mentioned image frame into the above-mentioned template image through feature point matching; using the above-mentioned transformation matrix to perform transformation processing on the above-mentioned current image frame to transform to the above-mentioned The pose of the template image.
综上所述，借助本发明提供的实施例，终端不同时间多次拍摄同一场景时，无需固定该终端，实时给出与模板图像的匹配度，引导用户将终端调整到最佳位置，或者使用特征点匹配技术，找到当前图像向模板图像的变换矩阵，将当前图像变换到模板姿态。进而辅助用户获取被拍摄对象的位置和姿态基本一致的多张照片。此外，为了更好地辅助用户得到与模板图像中被拍摄对象的位置和姿态更为接近的照片，在实时拍摄的图像上叠加拍摄参考图像，引导用户将终端调整到最佳位置，进一步提高了用户体验。To sum up, with the help of the embodiment provided by the present invention, when the terminal shoots the same scene multiple times at different times, the terminal does not need to be fixed, and the matching degree with the template image is given in real time to guide the user to adjust the terminal to the best position, or use The feature point matching technology finds the transformation matrix from the current image to the template image, and transforms the current image to the template pose. Further, the user is assisted in obtaining multiple photos in which the positions and postures of the photographed objects are basically the same. In addition, in order to better assist users to obtain photos that are closer to the position and posture of the subject in the template image, a reference image is superimposed on the real-time captured image to guide the user to adjust the terminal to the best position, further improving the user experience.
本领域普通技术人员可以理解上述实施例方法中的全部或部分处理是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中。Those skilled in the art can understand that all or part of the processing in the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium.
本领域普通技术人员可以理解上述方法实施例中的全部或部分处理是可以通过程序指令相关的硬件完成，前述的程序可以存储于一种计算机可读取存储介质中，该程序在执行时，执行包括前述方法实施例的步骤，而前述的存储介质包括：ROM、RAM、磁碟或光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the processing in the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the The steps of the foregoing method embodiments are included, and the foregoing storage medium includes various media capable of storing program codes such as ROM, RAM, magnetic disk or optical disk.
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410302630.4ACN104135609B (en) | 2014-06-27 | 2014-06-27 | Auxiliary photo-taking method, apparatus and terminal |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410302630.4ACN104135609B (en) | 2014-06-27 | 2014-06-27 | Auxiliary photo-taking method, apparatus and terminal |
| Publication Number | Publication Date |
|---|---|
| CN104135609Atrue CN104135609A (en) | 2014-11-05 |
| CN104135609B CN104135609B (en) | 2018-02-23 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410302630.4AExpired - Fee RelatedCN104135609B (en) | 2014-06-27 | 2014-06-27 | Auxiliary photo-taking method, apparatus and terminal |
| Country | Link |
|---|---|
| CN (1) | CN104135609B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104333696A (en)* | 2014-11-19 | 2015-02-04 | 北京奇虎科技有限公司 | View-finding processing method, view-finding processing device and client |
| CN105488756A (en)* | 2015-11-26 | 2016-04-13 | 努比亚技术有限公司 | Picture synthesizing method and device |
| CN105827930A (en)* | 2015-05-27 | 2016-08-03 | 广东维沃软件技术有限公司 | A method and device for assisting photography |
| CN107018333A (en)* | 2017-05-27 | 2017-08-04 | 北京小米移动软件有限公司 | Shoot template and recommend method, device and capture apparatus |
| CN107197153A (en)* | 2017-06-19 | 2017-09-22 | 上海传英信息技术有限公司 | The image pickup method and filming apparatus of a kind of photo |
| WO2018000299A1 (en)* | 2016-06-30 | 2018-01-04 | Orange | Method for assisting acquisition of picture by device |
| CN107580182A (en)* | 2017-08-28 | 2018-01-12 | 维沃移动通信有限公司 | A snapshot method, mobile terminal and computer-readable storage medium |
| CN108111752A (en)* | 2017-12-12 | 2018-06-01 | 北京达佳互联信息技术有限公司 | video capture method, device and mobile terminal |
| CN108108268A (en)* | 2017-11-28 | 2018-06-01 | 北京川上科技有限公司 | Reboot process method and apparatus are exited in a kind of video record application |
| CN109257541A (en)* | 2018-11-20 | 2019-01-22 | 厦门盈趣科技股份有限公司 | Householder method of photographing and device |
| CN110113523A (en)* | 2019-03-15 | 2019-08-09 | 深圳壹账通智能科技有限公司 | Intelligent photographing method, device, computer equipment and storage medium |
| CN110223366A (en)* | 2019-04-28 | 2019-09-10 | 深圳传音控股股份有限公司 | Image processing method, picture processing unit and readable storage medium storing program for executing |
| CN110266958A (en)* | 2019-07-12 | 2019-09-20 | 北京小米移动软件有限公司 | A shooting method, device and system |
| CN110493517A (en)* | 2019-08-14 | 2019-11-22 | 广州三星通信技术研究有限公司 | The auxiliary shooting method and image capture apparatus of image capture apparatus |
| CN111131702A (en)* | 2019-12-25 | 2020-05-08 | 航天信息股份有限公司 | Method and device for acquiring image, storage medium and electronic equipment |
| WO2020133204A1 (en)* | 2018-12-28 | 2020-07-02 | Qualcomm Incorporated | Apparatus and method to correct the angle and location of the camera |
| CN111770276A (en)* | 2020-07-07 | 2020-10-13 | 上海掌门科技有限公司 | Camera AI intelligent auxiliary photographing method, equipment and computer readable medium |
| CN112199547A (en)* | 2019-07-08 | 2021-01-08 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
| CN113301259A (en)* | 2018-02-15 | 2021-08-24 | 奥多比公司 | Intelligent guidance for capturing digital images aligned with a target image model |
| CN113784039A (en)* | 2021-08-03 | 2021-12-10 | 北京达佳互联信息技术有限公司 | Head portrait processing method and device, electronic equipment and computer readable storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090256933A1 (en)* | 2008-03-24 | 2009-10-15 | Sony Corporation | Imaging apparatus, control method thereof, and program |
| CN101690164A (en)* | 2007-07-11 | 2010-03-31 | 索尼爱立信移动通讯股份有限公司 | Enhanced image capturing functionality |
| CN101996308A (en)* | 2009-08-19 | 2011-03-30 | 北京中星微电子有限公司 | Human face identification method and system and human face model training method and system |
| CN102074001A (en)* | 2010-11-25 | 2011-05-25 | 上海合合信息科技发展有限公司 | Method and system for stitching text images |
| CN102814006A (en)* | 2011-06-10 | 2012-12-12 | 三菱电机株式会社 | Image contrast device, patient positioning device and image contrast method |
| CN103366374A (en)* | 2013-07-12 | 2013-10-23 | 重庆大学 | Fire fighting access obstacle detection method based on image matching |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690164A (en)* | 2007-07-11 | 2010-03-31 | 索尼爱立信移动通讯股份有限公司 | Enhanced image capturing functionality |
| US20090256933A1 (en)* | 2008-03-24 | 2009-10-15 | Sony Corporation | Imaging apparatus, control method thereof, and program |
| CN101996308A (en)* | 2009-08-19 | 2011-03-30 | 北京中星微电子有限公司 | Human face identification method and system and human face model training method and system |
| CN102074001A (en)* | 2010-11-25 | 2011-05-25 | 上海合合信息科技发展有限公司 | Method and system for stitching text images |
| CN102814006A (en)* | 2011-06-10 | 2012-12-12 | 三菱电机株式会社 | Image contrast device, patient positioning device and image contrast method |
| CN103366374A (en)* | 2013-07-12 | 2013-10-23 | 重庆大学 | Fire fighting access obstacle detection method based on image matching |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104333696A (en)* | 2014-11-19 | 2015-02-04 | 北京奇虎科技有限公司 | View-finding processing method, view-finding processing device and client |
| CN105827930A (en)* | 2015-05-27 | 2016-08-03 | 广东维沃软件技术有限公司 | A method and device for assisting photography |
| CN105488756B (en)* | 2015-11-26 | 2019-03-29 | 努比亚技术有限公司 | Picture synthetic method and device |
| CN105488756A (en)* | 2015-11-26 | 2016-04-13 | 努比亚技术有限公司 | Picture synthesizing method and device |
| WO2018000299A1 (en)* | 2016-06-30 | 2018-01-04 | Orange | Method for assisting acquisition of picture by device |
| CN107018333A (en)* | 2017-05-27 | 2017-08-04 | 北京小米移动软件有限公司 | Shoot template and recommend method, device and capture apparatus |
| CN107197153A (en)* | 2017-06-19 | 2017-09-22 | 上海传英信息技术有限公司 | The image pickup method and filming apparatus of a kind of photo |
| CN107197153B (en)* | 2017-06-19 | 2024-03-15 | 上海传英信息技术有限公司 | Shooting method and shooting device for photo |
| CN107580182A (en)* | 2017-08-28 | 2018-01-12 | 维沃移动通信有限公司 | A snapshot method, mobile terminal and computer-readable storage medium |
| CN108108268A (en)* | 2017-11-28 | 2018-06-01 | 北京川上科技有限公司 | Reboot process method and apparatus are exited in a kind of video record application |
| CN108111752A (en)* | 2017-12-12 | 2018-06-01 | 北京达佳互联信息技术有限公司 | video capture method, device and mobile terminal |
| CN113301259B (en)* | 2018-02-15 | 2023-05-30 | 奥多比公司 | Computer readable medium, system and method for guiding a user to capture a digital image |
| CN113301259A (en)* | 2018-02-15 | 2021-08-24 | 奥多比公司 | Intelligent guidance for capturing digital images aligned with a target image model |
| CN109257541A (en)* | 2018-11-20 | 2019-01-22 | 厦门盈趣科技股份有限公司 | Householder method of photographing and device |
| WO2020133204A1 (en)* | 2018-12-28 | 2020-07-02 | Qualcomm Incorporated | Apparatus and method to correct the angle and location of the camera |
| CN110113523A (en)* | 2019-03-15 | 2019-08-09 | 深圳壹账通智能科技有限公司 | Intelligent photographing method, device, computer equipment and storage medium |
| CN110223366A (en)* | 2019-04-28 | 2019-09-10 | 深圳传音控股股份有限公司 | Image processing method, picture processing unit and readable storage medium storing program for executing |
| CN112199547A (en)* | 2019-07-08 | 2021-01-08 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
| CN110266958B (en)* | 2019-07-12 | 2022-03-01 | 北京小米移动软件有限公司 | Shooting method, device and system |
| CN110266958A (en)* | 2019-07-12 | 2019-09-20 | 北京小米移动软件有限公司 | A shooting method, device and system |
| CN110493517A (en)* | 2019-08-14 | 2019-11-22 | 广州三星通信技术研究有限公司 | The auxiliary shooting method and image capture apparatus of image capture apparatus |
| CN111131702A (en)* | 2019-12-25 | 2020-05-08 | 航天信息股份有限公司 | Method and device for acquiring image, storage medium and electronic equipment |
| CN111770276A (en)* | 2020-07-07 | 2020-10-13 | 上海掌门科技有限公司 | Camera AI intelligent auxiliary photographing method, equipment and computer readable medium |
| CN113784039A (en)* | 2021-08-03 | 2021-12-10 | 北京达佳互联信息技术有限公司 | Head portrait processing method and device, electronic equipment and computer readable storage medium |
| CN113784039B (en)* | 2021-08-03 | 2023-07-11 | 北京达佳互联信息技术有限公司 | Head portrait processing method, head portrait processing device, electronic equipment and computer readable storage medium |
| Publication number | Publication date |
|---|---|
| CN104135609B (en) | 2018-02-23 |
| Publication | Publication Date | Title |
|---|---|---|
| CN104135609B (en) | Auxiliary photo-taking method, apparatus and terminal | |
| CN107038681B (en) | Image blurring method and device, computer readable storage medium and computer device | |
| CN113507558B (en) | Method, device, terminal equipment and storage medium for removing image glare | |
| CN111353946B (en) | Image restoration method, device, equipment and storage medium | |
| CN106296617B (en) | The processing method and processing device of facial image | |
| CN107589963B (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
| CN107169939A (en) | Image processing method and related product | |
| CN109743504B (en) | Auxiliary photographing method, mobile terminal and storage medium | |
| CN108924414B (en) | A shooting method and terminal equipment | |
| EP3640732A1 (en) | Method and terminal for acquire panoramic image | |
| CN106657791A (en) | Method and device for generating synthetic image | |
| CN107749046B (en) | Image processing method and mobile terminal | |
| CN108459799B (en) | Picture processing method, mobile terminal and computer readable storage medium | |
| CN106161931A (en) | Image preview method and device | |
| CN108307110A (en) | A kind of image weakening method and mobile terminal | |
| CN105635553B (en) | Image shooting method and device | |
| CN107330867B (en) | Image synthesis method, apparatus, computer-readable storage medium, and computer device | |
| CN109739414B (en) | Picture processing method, mobile terminal and computer readable storage medium | |
| CN105513098B (en) | Image processing method and device | |
| CN106210514A (en) | Method, device and smart device for taking pictures and focusing | |
| CN111556248B (en) | Shooting method, shooting device, storage medium and mobile terminal | |
| CN111046215B (en) | Image processing method and device, storage medium and mobile terminal | |
| CN107704292A (en) | Picture method to set up and mobile terminal in a kind of application program | |
| CN108829600B (en) | Test method, device, storage medium and electronic device for algorithm library | |
| US9900516B2 (en) | Method and electronic device for generating thumbnail image |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20180223 | |
| CF01 | Termination of patent right due to non-payment of annual fee |