WO2019109801A1

WO2019109801A1 - Method and device for adjusting photographing parameter, storage medium, and mobile terminal

Info

Publication number: WO2019109801A1
Application number: PCT/CN2018/116588
Authority: WO
Inventors: 刘耀勇; 陈岩
Original assignee: Oppo广东移动通信有限公司
Priority date: 2017-12-06
Filing date: 2018-11-21
Publication date: 2019-06-13
Also published as: CN107820020A

Abstract

Disclosed is a method for adjusting a photographing parameter, comprising: acquiring a first preview image of an object to be photographed; using a preset scene recognition model to recognize a scene in which the first preview image is captured; and if the scene is a preset scene, adjusting, according to a second photographing parameter corresponding to the preset scene, a first photographing parameter of a camera so as to photograph the object according to the second photographing parameter. Also disclosed are a device for adjusting a photographing parameter, a storage medium and a mobile terminal.

Description

Method, device, storage medium and mobile terminal for adjusting shooting parameters

The present application claims priority to Chinese Patent Application No. PCT Application No. No. No. No. No. No.

Technical field

The embodiment of the present invention relates to a mobile terminal technology, for example, to a method, an apparatus, a storage medium, and a mobile terminal for adjusting a shooting parameter.

Background technique

With the development of mobile terminal technology, there are more and more applications in mobile terminals such as mobile phones, and mobile terminals are becoming more and more popular. The functions of related mobile terminals have long been limited to the functions of making calls or watching videos, and shooting has become one of the common functions of most mobile terminals.

In order to be able to take high-quality images, the following two methods are used in the related art: one method is that the user can manually adjust the shooting parameters according to his own needs, but the adjustment method requires the user to have high professional skills and be skilled. Master the meaning of various shooting parameters and the effect of mutual cooperation, and frequent adjustment operations are cumbersome and time-consuming, and it is difficult to capture instantaneous scenes; another method is that the manufacturer of the user terminal stores in advance in the user terminal. The shooting mode, each shooting mode corresponds to a series of shooting parameter settings, the user can select the corresponding shooting mode, the camera module of the user terminal calls the corresponding parameter setting according to the shooting mode selected by the user, and automatically realizes the shooting parameters. Adjustment, however, this type of adjustment can only call a few limited shooting modes, which is relatively rigid, resulting in an image that is not satisfactory to the user.

Summary of the invention

The embodiment of the present application provides a method, a device, a storage medium, and a mobile terminal for adjusting a shooting parameter, which can provide an optimized shooting parameter adjustment scheme and improve the shooting effect of the mobile terminal.

In an embodiment, the embodiment of the present application provides a method for adjusting a shooting parameter, including:

Obtaining a first preview image of the object to be photographed, wherein the first preview image is a screen of the object to be photographed captured by the camera according to the first photographing parameter;

Identifying a shooting scene of the first preview image by a preset scene recognition model, wherein the scene recognition model is a deep learning model trained according to a picture sample set;

Adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, in the case that the shooting scene is a preset scene, to perform the object to be photographed according to the second shooting parameter. Shooting.

In an embodiment, the embodiment of the present application further provides a parameter adjustment device, where the device includes:

An image acquisition module, configured to acquire a first preview image of the object to be photographed, wherein the first preview image is a screen of the object to be photographed captured by the camera according to the first photographing parameter;

a scene recognition module, configured to identify a shooting scene of the first preview image by a preset scene recognition model, wherein the scene recognition model is a deep learning model trained according to a picture sample set;

a parameter adjustment module, configured to adjust a first shooting parameter of the camera according to a second shooting parameter corresponding to the preset scene, in a case that the shooting scene is a preset scene, according to the second shooting parameter pair The subject to be photographed is photographed.

In an embodiment, the embodiment of the present application further provides a computer readable storage medium, where the computer program is stored, and when the program is executed by the processor, the method for adjusting the shooting parameters as described above is implemented.

In an embodiment, the embodiment of the present application further provides another terminal, including a memory, a processor, and a computer program stored on the memory and executable by the processor, where the processor executes the computer program as described above. The method of adjusting the shooting parameters.

DRAWINGS

1 is a flowchart of a method for adjusting shooting parameters provided by an embodiment of the present application;

2 is a flowchart of another method for adjusting shooting parameters provided by an embodiment of the present application;

FIG. 3 is a flowchart of a user modifying a shooting parameter according to an embodiment of the present application; FIG.

4 is a flowchart of still another method for adjusting shooting parameters provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of an image display interface provided by an embodiment of the present application; FIG.

6 is a structural block diagram of an apparatus for adjusting shooting parameters according to an embodiment of the present application;

FIG. 7 is a structural block diagram of a mobile terminal according to an embodiment of the present application;

FIG. 8 is a structural block diagram of a smart phone according to an embodiment of the present application.

Detailed ways

The present application will be described below in conjunction with the accompanying drawings and embodiments. The embodiments described herein are merely illustrative of the present application and are not intended to be limiting. For the convenience of description, only some but not all of the structures related to the present application are shown in the drawings.

In the related art, some schemes for determining a scene in which a mobile terminal is located based on a light sensor, a barometric pressure sensor, or the like provided by the mobile terminal are provided. In addition, there are some Scale-Up Variant Features (SURF) algorithms or Scale-invariant feature transform (SIFT) to determine scene information. However, the above schemes all have accurate scene recognition. The problem is that the rate is not high, and the identifiable scene category is limited. To solve the above problem, the present application provides an adjustment scheme for shooting parameters, which can improve the accuracy of scene recognition, expand the identifiable scene type, and thereby effectively improve Shooting effect.

FIG. 1 is a flowchart of a method for adjusting shooting parameters according to an embodiment of the present application. The method can be performed by an adjustment device for the shooting parameters, wherein the device can be implemented by software and/or hardware, and can generally be integrated in a mobile terminal, such as a mobile terminal having a camera. As shown in Figure 1, the method includes:

Step 110: Acquire a first preview image of the object to be photographed.

In an embodiment, the first preview image is a picture of the object to be captured captured by the camera according to the first shooting parameter. The first preview image may include a screen captured by a camera displayed in a shooting interface of the mobile terminal before the user presses the photo button. The first preview image in this embodiment includes, but is not limited to, a character class image, a natural landscape class image, and a human architecture class image. The first shooting parameter may be a default parameter of the camera application or other application software having a shooting function when shooting. Alternatively, the first shooting parameter may also be a parameter corresponding to a shooting mode selected by the user, and the like.

In the embodiment of the present application, the acquiring operation of the first preview image by the mobile terminal may be performed by a system of the mobile terminal, or performed by any application software that includes a shooting function in the mobile terminal, and the operation of acquiring the first preview image may be performed by the user. The operating instructions are executed by the system or application software. For example, the user can directly open the camera function in the mobile terminal system to take pictures of the person, or use the camera option of the application software to take pictures of the building.

In an embodiment, the first preview image may be obtained by projecting an optical image of the object onto the photosensitive chip through a lens in the camera, and converting the optical image signal into an electrical signal by the photosensitive chip, and passing through a series of settings After the fixed transformation or processing, the first preview image is obtained, and the first preview image is sent to the Image Processor Processor (ISP) for processing through a dedicated interface Mobile Industry Processor Interface (MIPI). Finally, it is converted into a format that can be displayed on the display screen of the mobile terminal, and displayed on the display screen of the mobile terminal.

Step 120: Identify a shooting scene of the first preview image by using a preset scene recognition model.

In an embodiment, the scene recognition model is a deep learning model trained according to a set of picture samples. The scene recognition model can be used to quickly and accurately identify the shooting scene of the first preview image after inputting the first preview image. The shooting scene may be a category label obtained by classifying the shooting object according to the set target object, including but not limited to a gourmet scene, a green scene, a sports scene, a building scene, a character scene, and a night scene.

In an embodiment, the scene recognition model may be a model obtained by training a preset deep learning model by using a machine learning algorithm based on a set of image samples, wherein the scene recognition model may be a convolutional neural network model. In an embodiment, the foregoing training process may be performed by a server, and may also be performed by a mobile terminal, which is not limited in this embodiment. The image sample set includes image samples for location marking of the target object in multiple scene types, including but not limited to network pictures in the network platform and user pictures in the mobile terminal picture library. The network picture can be downloaded from the network platform by the web crawler, and the specific target object in the network picture is manually marked to obtain a first picture sample, and the first picture sample is stored in the picture sample set. In an embodiment, the target object can be used to distinguish shooting scenes. The marking of the target object may be by manually marking the location of the target object, including but not limited to marking the pixels representing the target object. For example, to mark the dish of the dish, the outline of the dish can be marked, and the pixels in the outline are used as the corresponding pixels of the dish. For another example, if the grass is to be marked, the outline of the grass can be marked, and the pixels in the outline are used as the pixels corresponding to the grass.

In an embodiment, the user picture in the picture library (or album) of the mobile terminal may be obtained, and a specific target object in the network picture is manually marked to obtain a second picture sample, and the second picture sample is stored. In the image sample set.

In an embodiment, the server acquires the user permission before acquiring the user picture from the mobile terminal album. Therefore, when the server first acquires the user picture from the mobile terminal album, the mobile terminal displays the inquiry information in the form of a dialog box to ask whether to grant The server's access to the album. The user's input instruction is obtained, and if the user inputs a positive information, the server is given permission to access the album.

In an embodiment, the set machine learning algorithm includes, but is not limited to, a forward propagation algorithm and a backward propagation algorithm.

In the embodiment of the present application, the scene recognition model may be configured by setting a preset number of hidden layers and a number of nodes in each of the input layer, the hidden layer, and the output layer, and initializing a first parameter of the convolutional neural network, where The first parameter includes the offset value of each layer and the weight of the edge, and the deep learning model is initially obtained. Then, using the picture sample set, the deep learning model is trained in two stages of forward propagation and backward propagation; when the error calculated by the backward propagation training reaches the expected error value, the training ends and the scene recognition model is obtained. After the training ends, the server sends a scene recognition model to the mobile terminal in response to the request of the mobile terminal. Therefore, the mobile terminal acquires a scene recognition model sent by the server and is configured locally on the mobile terminal. Since the scene recognition model learns effective features from a large number of image samples containing different scene categories, the types of identifiable scenes can be increased, and the accuracy of scene recognition is improved.

In the embodiment of the present application, network parameters such as the number of layers of the neural network model, the number of neurons, the convolution kernel, and/or the weight are not limited.

In the embodiment of the present application, the first preview image is input into a pre-configured scene recognition model, and the probability that the first preview image belongs to the scene specified in the scene recognition model is analyzed by the scene recognition model, and the scene recognition model is output. The scene with the highest probability is taken as the shooting scene of the first preview image.

Step 130: When the shooting scene is a preset scene, adjust a first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, to shoot the object to be photographed according to the second shooting parameter. .

In the embodiment of the present application, the preset scene may be a category label configured with a preset of the shooting parameters, and the preset scene may be stored in a preset scene library. In an embodiment, the association relationship between the captured scene and the shooting parameters may be obtained by the server by analyzing historical shooting data of different shooting scenes of the target user group (which may be a professional photographer or the like), according to the association. The relationship constitutes a preset scene library. After the scenario library is built, the server may deliver the scenario library to the mobile terminal according to the request of the mobile terminal. The historical shooting data includes a picture and a corresponding camera parameter. When the picture captured by the camera is saved, the camera parameter when the picture is acquired is saved, and the historical shooting data is formed by the picture and the corresponding camera parameter. It can be understood that the scenario library can be constructed by the mobile terminal based on the historical shooting data of different scenarios, which is not limited in the embodiment of the present application.

In an embodiment, the first shooting parameter and the second shooting parameter may be related parameters of the camera at the time of shooting, including but not limited to aperture, shutter, exposure compensation, focal length, sensitivity, and white balance.

In the embodiment of the present application, after the shooting scene of the first preview image is identified according to the scene recognition model, the shooting scene may be matched with the preset scene according to the shooting scene; and the preset scene successfully matched with the shooting scene is determined, and the Determining a second shooting parameter corresponding to the preset scene, and replacing the first shooting parameter according to the second shooting parameter. For example, the preset scene library may be queried according to the shooting scene to determine whether the preset scene is the same as the shooting scene. If yes, the shooting scene is determined to be a preset scene. Otherwise, it is determined that the shooting scene does not belong to the preset scene. Set the scene library. If the shooting scene is a preset scene, the second shooting parameter corresponding to the preset scene is obtained, and the difference parameter between the second shooting parameter and the first shooting parameter may be determined, and the corresponding parameter is used to replace the corresponding one of the first shooting parameters. The parameters, in this way, can be photographed according to the second shooting parameter to obtain a picture that conforms to the professional shooting rules, thereby improving the shooting effect. Exemplarily, after comparing the second shooting parameter with the first shooting parameter, if it is determined that the exposure compensation and the shutter are different parameters, the exposure compensation and the value of the shutter in the second shooting parameter are used to replace the corresponding exposure in the first shooting parameter. Compensation and shutter.

The technical solution of the present embodiment is to obtain a first preview image of the object to be photographed; to identify the shooting scene of the first preview image by using a preset scene recognition model; and when the shooting scene belongs to the preset scene, corresponding to the preset scene The second shooting parameter adjusts the first shooting parameter of the camera, which can effectively improve the shooting effect of the mobile terminal. By adopting the above technical solution, the scene recognition based on the scene recognition model can improve the accuracy of the scene recognition and expand the type of the scene recognition, thereby automatically adjusting the shooting parameters of the camera according to the shooting scene, thereby improving the shooting effect.

FIG. 2 is a flowchart of another method for adjusting shooting parameters provided by an embodiment of the present application. The method includes:

Step 210: Acquire a first preview image of the object to be photographed.

The first preview image is a picture of the object to be photographed captured by the camera according to the first shooting parameter. The method for obtaining the first preview image is similar to the description of the above example, and details are not described herein again.

Step 220: Identify a shooting scene of the first preview image by using a preset scene recognition model.

The scene recognition model is a deep learning model trained according to a picture sample set.

In an embodiment, the scene recognition model is preset in the mobile terminal, and may be sending an acquisition request to the server, and acquiring the scene recognition model by the server. The scene recognition model is a deep learning model trained by the server according to the picture sample set, and the picture sample set includes a picture sample for performing location tagging on the target object.

The scene recognition operation is similar to the description of the above example, and will not be described here.

Step 230: Match the shooting scene with a preset scene in a preset scene library.

Step 240: Determine a preset scene that is successfully matched with the shooting scene, acquire a second shooting parameter corresponding to the preset scene, and replace the first shooting parameter according to the second shooting parameter.

The steps of parameter adjustment are similar to those in the above examples, and are not described herein again. The first shooting parameter is replaced by the second shooting parameter, and the shooting object is photographed according to the second shooting parameter, so that the shooting effect can be improved.

Step 250: Obtain a parameter correction operation.

In an embodiment, the parameter correction operation is a correction operation of the shooting parameter input by the user, including but not limited to adjusting the aperture, the shutter, the exposure compensation, the focal length, the sensitivity, and the range of the white balance. In some cases, the user may take a different shooting parameter than the current shooting scene for the artistic effect. At this time, the user will artificially modify the shooting parameters.

Exemplarily, FIG. 3 provides a flowchart for modifying a shooting parameter by a user. As shown in FIG. 3, after the user clicks on the preview image 310 displayed in the current display area, the shooting parameter modification interface 320 may be popped up in the form of a dialog box. The shooting parameter modification interface 320 displays shooting parameters such as aperture, shutter, exposure compensation, focal length, sensitivity, white balance, etc., and obtains modification information such as a correction value input by the user or a position of the slider.

In the embodiment of the present application, the system detects a modification operation of the shooting parameter input by the user, including detecting a click operation of the control corresponding to the one or more shooting parameters, and a modified value input in the control. It may also be a sliding operation of detecting a slider control corresponding to one or more shooting parameters.

In the display interface of the second preview image, the system acquires a parameter correction operation input by the user, including which parameter is modified, and what the parameter value is.

Step 260: Adjust the second shooting parameter according to the parameter correction operation to obtain a third shooting parameter, and perform a shooting operation by using the third shooting parameter.

In an embodiment, the parameter correction operation includes the modified parameters as well as the parameter data. Based on this, the parameter corresponding to the parameter correction operation in the second shooting parameter can be modified correspondingly. As shown in FIG. 3, if the parameter correction operation is an operation corresponding to the shutter, and the correction data is to change the focal length from x ₁ mm to x ₂ mm, the range of the shutter value in the second shooting parameter is adjusted to obtain the first Three shooting parameters. The shooting parameter is modified according to the modification information, and then the operation information about the preview button is acquired, and the preview interface is displayed in response to the operation information, so that the user can view the shooting effect of the captured image corresponding to the modified shooting parameter.

Step 270: Record the number of times of shooting using the third shooting parameter in the set time interval.

The photographing operation is performed using the third photographing parameter, and the number of times the photographing is performed using the third photographing parameter is incremented by one. Obtain the number of times the third shooting parameter is used for shooting within the set time interval since the first shooting with the third shooting parameter. The set time interval may be a system default time, including but not limited to one week or one month. That is, a survey period is set in advance. If the user often takes a third photographing parameter to take a photograph in a certain shooting scene, it proves that the user is not accustomed to adopting a preset corresponding to the shooting scene in the shooting scene. Shooting parameters, but accustomed to shooting with the third shooting parameters.

Step 280: Determine whether the number of times exceeds the set number threshold. If yes, execute step 290; otherwise, perform step 2100.

The set number threshold is the default value set by the system or the value set by the user according to his own needs.

Step 290: Associate the third shooting parameter with the preset scene in a preset scene library.

It can be understood that the association relationship between the preset scene and the shooting parameter is stored in the preset scene library. In this embodiment, the preset scene may be a shooting scene corresponding to the shooting screen of the parameter correction operation.

In the embodiment of the present application, the third shooting parameter is stored in the preset scene database in association with the preset scene, and the preset scene is used as the search keyword, the scene library is queried, and the second shooting parameter corresponding to the preset scene is determined. Then, the second shooting parameter is replaced by the third shooting parameter, so that the scene library is more in line with the user's shooting habits, and a personalized scene library is provided.

In an embodiment, storing the third shooting parameter in the preset scene library in association with the preset scene may also be establishing an association relationship between the third shooting parameter and the preset scene, and adding a preset scene and a scene in the scene library. Recording of the third shooting parameter. At this time, there are cases in the scene library that the same preset scene corresponds to at least two sets of shooting parameters. For example, a certain preset scene is associated with both the second shooting parameter and the third shooting parameter.

Step 2100: Display a preview image in the display area.

If the number of times of shooting using the third shooting parameter in the set time interval is less than the set number threshold, when the mobile terminal that has enabled the scene recognition function is detected again, the first preview image is recognized by the scene recognition model. Shoot the scene. The first shooting parameter is adjusted according to the second shooting parameter corresponding to the shooting scene, and the second preview image corresponding to the second shooting parameter is displayed in the display area.

In an embodiment, if the number of times of shooting using the third shooting parameter exceeds the set number threshold in the set time interval, when the mobile terminal with the scene recognition function enabled is detected again, the scene recognition model is recognized by the scene recognition model. A shooting scene of the first preview image is displayed, and the shooting scene is a scene corresponding to the third shooting parameter. The first shooting parameter is adjusted according to the third shooting parameter corresponding to the shooting scene, and a new preview image corresponding to the third shooting parameter is displayed in the display area.

In an embodiment, if the number of times of shooting using the third shooting parameter exceeds the set number threshold in the set time interval, when the mobile terminal with the scene recognition function enabled is detected again, the scene recognition model is recognized by the scene recognition model. The shooting scene of the first preview image. Obtaining a second shooting parameter and a third shooting parameter corresponding to the shooting scene, and adjusting shooting parameters of the camera according to the second shooting parameter and the third shooting parameter respectively. Then, the camera acquires two frame preview images according to the second shooting parameter and the third shooting parameter respectively, and displays the preview image in the display area of the display screen for the user to select a satisfactory preview image for shooting. In an embodiment, a preview image corresponding to the second shooting parameter is displayed in the first area of the display area, and a preview image corresponding to the third shooting parameter is displayed in the second area of the display screen, so as to simultaneously display a preview corresponding to different shooting parameters. The image is convenient for the user to compare the difference between the two images and select a preview image that satisfies the shooting requirements for shooting.

The technical solution of the embodiment, after adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, performing an acquiring parameter correcting operation, and adjusting the second shooting parameter according to the parameter correcting operation, Obtaining a third shooting parameter, recording the number of times of shooting using the third shooting parameter in the set time interval, and if the number of times exceeds the set number of times threshold, the third shooting parameter and the preset The scene association is stored in the preset scene library, and the scene library is updated according to the user's shooting habits, so that the shooting parameters corresponding to the shooting scene in the scene library are more in line with the user's personal shooting habits.

FIG. 4 is a flowchart of still another method for adjusting shooting parameters according to an embodiment of the present application. This method is suitable for the user to set the camera's shooting parameters according to their own shooting habits or to take some artistic effect. As shown in FIG. 4, the method includes:

Step 410: Acquire a first preview image of the object to be photographed.

The first preview image is a screen of the photographic subject captured by the camera according to the first shooting parameter, and the first shooting parameter may be set by the user according to his own shooting habits. It can be understood that the first shooting parameter may also be a parameter of the camera set by the user for capturing a photo with certain artistic effect. For example, in order to capture a photo with a slow shutter effect, the user manually sets parameters such as shutter speed and aperture, and it is not appropriate to automatically adjust the shooting parameters according to the shooting scene.

Step 420: Identify a shooting scene of the first preview image by using a preset scene recognition model.

Step 430: Match the shooting scene with a preset scene in a preset scene library.

Step 440: Determine a preset scene that is successfully matched with the shooting scene, acquire a second shooting parameter corresponding to the preset scene, and replace the first shooting parameter according to the second shooting parameter.

Step 450: Acquire a second preview image of the object to be captured captured by the camera according to the second shooting parameter.

In the embodiment of the present application, the camera is adjusted according to the second shooting parameter, and then the optical image of the object is projected onto the photosensitive chip by the adjusted camera, and the optical image signal is converted into an electrical signal by the photosensitive chip, and after a series of settings. After the transformation or processing, a second preview image is obtained, and the second preview image is sent to the ISP for processing through the MIPI interface.

Step 460: Control the first preview image to be displayed in a preset first area, and display the second preview image in a preset second area.

In an embodiment, the area of the first area is smaller than the area of the display area of the display screen, and the area of the second area is also smaller than the area of the display area of the display screen, which may be spliced by the first area and the second area to form a display screen. Display area.

Illustratively, a new layer can be created as the first layer. The first preview image is acquired by the ISP, and a backup image of the first preview image is saved, and then the image is reduced by the image of the first preview image to obtain a third preview image. The size of the third preview image is the same as the size of the first area. Then, a third preview image is drawn on the first area of the first layer by a graphics processing unit (GPU), so that the first area is filled with a frame of the third preview image. In an embodiment, the first preview image may be subjected to image reduction processing using a nearest neighbor interpolation method, a bilinear interpolation method, or a cubic convolution method. The reduced preview first preview image is drawn on the first region of the first layer. Also, create a new layer as the second layer. Acquiring a second preview image through the ISP, and saving a backup image of the second preview image, and then performing image reduction processing on the second preview image to obtain a fourth preview image. The size of the fourth preview image is the same as the size of the second area. Then, the fourth preview image is drawn by the image processor GPU in the second region of the second layer, so that the second region is filled with the fourth preview image. The first layer and the second layer are synthesized by the image processor GPU to obtain a picture to be displayed. The to-be-displayed screen is displayed on the display screen of the mobile terminal according to the set refresh rate. In an embodiment, the third layer corresponding to the first area of the second layer is a transparent layer. Thereby, the first preview image and the second preview image after the reduction processing are simultaneously displayed in the display area of the display screen. FIG. 5 is a schematic diagram of an image display interface provided by an embodiment of the present application. As shown in FIG. 5, the first layer 510 includes a first area 511, and the area of the first area 511 is smaller than the area of the first layer 510, and the reduced image of the first preview image is drawn in the first area 511, ie, Three preview images 512. The second layer 520 includes a second area 521, and the area of the second area 521 is smaller than the area of the second layer 520, and the reduced image of the second preview image, that is, the fourth preview image 522 is drawn in the second area 521. In an embodiment, in order to simultaneously display the third preview image 512 and the fourth preview image 522 in the synthesized picture to be displayed, the third layer 520 corresponds to the first area 511 of the first layer 510. Area 523 is a transparent layer. Therefore, after the first layer 510 and the second layer 520 are synthesized, the first region 511 is displayed with the reduced first preview image, and the second region 521 is displayed with the reduced second preview image.

Step 470: Acquire a user operation for the preview image.

In an embodiment, the preview image may be a third preview image or a fourth preview image. The user operation includes a user's touch operation for the mobile terminal display screen, a user's pressing operation for setting the physical button (eg, by pressing the sound key +, selecting the third preview image of the first area, and pressing the sound key - selecting A fourth preview image of the second area), a setting gesture, a voice indication, and the like. The touch operation includes a click operation on the display screen, including but not limited to selecting a third preview image of the first area by clicking an arbitrary position of the display screen, and selecting a fourth area of the second area by double-clicking any position of the display screen. Preview the image. The touch operation may also be a touch gesture acting on the display screen, and the touch gesture includes, but is not limited to, drawing a Z on the display screen to select a third preview image of the first area, and drawing a V on the display screen to indicate that the second area is selected. Four preview images. The setting gesture includes a spatial gesture including, but not limited to, an indoor preview image in which the first region is selected by the mobile phone in the space drawing C, and a fourth preview image in the second region is selected by the mobile phone in the space drawing O.

The above description of the user's gesture is merely an example and is not limited. For example, the touch operation may also be a click operation acting in the first area, indicating that the third preview image is selected; and a click operation acting on the second area, indicating that the fourth preview image is selected. As another example, the touch operation may also be a sliding operation (including a sliding operation that slides from the inside of the first area to the outside) in the first area, indicating that the third preview image is discarded.

Step 480: Acquire a first preview image or a second preview image according to the user operation, and display the first preview image or the second preview image in a display area of the display screen.

In an embodiment, the first preview image and the second preview image are shot images that are not subjected to image reduction processing, and may be acquired by an ISP, and may be a backup image of the first preview image or a second preview image. Backup image.

In an embodiment, the association relationship between the user operation, the preview image, and the processing operation is established in advance, and the association relationship is stored in the operation whitelist. For example, the user operation, the preview image, and the processing operation are stored in the white list in the following association record: draw Z on the display screen - the third preview image - select the first preview image; draw O on the display screen - a fourth preview image - selecting the second preview image; clicking the display - the third preview image - selecting the first preview image; double clicking on the display - the fourth preview image - selecting the second preview image; pressing Volume + key - third preview image - select the first preview image; press volume - key - fourth preview image - select the second preview image; in the first area, enter the third preview image to the right - a third preview image - discarding the first preview image; sliding the fourth preview image to the right in the second region - the fourth preview image - discarding the second preview image and the like. The above description of the relationship between the user operation, the preview image, and the processing operation is merely an example, and is not limited thereto, and the association relationship may be stored in a key value pair or a mapping manner.

When the user operation is detected, the object operated by the user and the processing operation are determined according to the operation gesture and the operation position of the user operation. For example, if the user operation is a click operation acting on the first area, the object of the operation is a third preview image, and the processing operation is to select the first preview image. If the user operation is to draw O on the display screen, the operation object is the fourth preview image, and the processing operation is to select the second preview image and the like. In response to the user operation, a captured image is acquired according to the processing operation, and the captured image is displayed on the display area. For example, in response to a user operation of the user drawing O on the display screen, a backup image of the second preview image is acquired by the ISP, and the second preview image is displayed in the display area.

Step 490: Perform a photographing operation for the first preview image or the second preview image when the photographing instruction is acquired.

It can be understood that the shooting instruction may be an operation instruction triggered by the user pressing the shooting button, or may be an operation instruction triggered by the user pressing the setting object button, or may be an operation instruction triggered by the user's setting gesture.

In the case that the shooting instruction is detected, the mobile terminal saves the preview image displayed on the current display screen, realizes the shooting operation on the shooting object, obtains the captured picture, and can store the captured picture in the picture library or the album. The preview image currently displayed may be the first preview image or the second preview image.

In the technical solution of the embodiment, the first preview image corresponding to the first shooting parameter and the second preview image corresponding to the second shooting parameter are respectively acquired, and the first preview image is displayed in the first region, in the second region. Displaying the second preview image, the first preview image and the second preview image are simultaneously displayed in the display area of the display screen, so that the user selects a preview image that conforms to his own shooting habits, and the shooting parameters that are automatically adjusted according to the scene are not consistent with the user's shooting. Habits occur and improve human-computer interaction performance.

FIG. 6 is a structural block diagram of an apparatus for adjusting shooting parameters according to an embodiment of the present application. The device may be implemented by software and/or hardware, and may be integrated into the mobile terminal and configured to perform the adjustment method of the shooting parameters provided by the embodiment of the present application. As shown in Figure 6, the device includes:

The image obtaining module 610 is configured to acquire a first preview image of the object to be photographed, wherein the first preview image is a screen of the object to be photographed captured by the camera according to the first photographing parameter;

The scene recognition module 620 is configured to identify a shooting scene of the first preview image by using a preset scene recognition model, wherein the scene recognition model is a deep learning model trained according to a picture sample set;

The parameter adjustment module 630 is configured to adjust, according to the second shooting parameter corresponding to the preset scene, the first shooting parameter of the camera according to the second shooting parameter, in the case that the shooting scene is a preset scene. Tell the subject to shoot.

The technical solution of the embodiment provides an adjustment device for shooting parameters, and performs scene recognition based on the scene recognition model, which can improve the accuracy of scene recognition and expand the type of scene recognition, thereby automatically adjusting the shooting parameters of the camera according to the shooting scene. Improve the shooting effect.

In an embodiment, the apparatus further comprises:

a model obtaining module, configured to acquire a scene recognition model sent by the server, wherein the scene recognition model is a deep learning model trained by the server according to the image sample set, and the image sample set includes a target object for identifying a shooting scene A sample image of the location marker.

In an embodiment, the parameter adjustment module 630 is configured to:

Matching the shooting scene with a preset scene in a preset scene library;

Determining a preset scene that is successfully matched with the shooting scene, acquiring a second shooting parameter corresponding to the preset scene, and replacing the first shooting parameter according to the second shooting parameter.

In an embodiment, the apparatus further comprises:

The scene library update module is configured to: after adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, acquiring a parameter correcting operation; adjusting the second shooting parameter according to the parameter correcting operation, to obtain a Three shooting parameters are taken, and the shooting operation is performed using the third shooting parameters.

In an embodiment, the scene library update module is further configured to: record a number of times of shooting using the third shooting parameter within a set time interval; and if the number of times exceeds a set number of times threshold, The third shooting parameter is stored in the preset scene library in association with the preset scene.

In an embodiment, the apparatus further comprises:

a first image display module configured to acquire a second preview image after the first shooting parameter is replaced according to the second shooting parameter, wherein the second preview image is captured by the camera according to the second shooting parameter a screen of the object to be photographed; controlling the first preview image to be displayed in a preset first area, and displaying the second preview image in a preset second area, wherein the first area The display area of the display screen is formed with the second area.

In an embodiment, the first image display module is configured to:

Create the first layer;

Obtaining the first preview image, and performing image reduction processing on the first preview image to obtain a third preview image;

Drawing the third preview image in a first area of the first layer, wherein an area of the first area is smaller than an area of the first layer;

Create a second layer;

Obtaining the second preview image, and performing image reduction processing on the second preview image to obtain a fourth preview image;

Drawing the fourth preview image in a second region of the second layer, wherein an area of the second region is smaller than an area of the second layer, and the second layer is in the second layer The third area corresponding to the first area of a layer is a transparent layer;

The first layer and the second layer are synthesized to obtain a picture to be displayed, and the picture to be displayed is displayed.

In an embodiment, the apparatus further comprises:

a second image display module, configured to acquire a user operation for the third preview image or the fourth preview image after displaying the to-be-displayed image; acquiring the first preview image or the second preview image according to the user operation, And displaying the first preview image or the second preview image in a display area of the display screen;

The image capturing module is configured to perform a photographing operation for the first preview image or the second preview image in a case where a photographing instruction is acquired.

In an embodiment, the second image display module is further configured to: pre-establish an association relationship between the user operation, the third preview image and the fourth preview image, and a processing operation, and associate the association The relationship is stored in an operation whitelist; wherein the processing operation is a processing operation on the first preview image or the second preview image.

Embodiments of the present application also provide a storage medium including computer executable instructions for performing an adjustment method of a shooting parameter of any of the above embodiments when executed by a computer processor.

Storage media - any type of storage device or storage device. The term "storage medium" is intended to include: a mounting medium such as a Compact Disc Read-Only Memory (CD-ROM), a floppy disk or a tape device; a computer system memory or a random access memory such as a dynamic random access memory; (Dynamic Random Access Memory, DRAM), (Double Data Rate Random Access Memory, DDR RAM), Static Random Access Memory (SRAM), Extended Data Output Random Access Memory (Extended Data Output Random Access Memory) , EDO RAM), Rambus Random Access Memory (Rambus RAM), etc.; non-volatile memory such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory components Wait. The storage medium may also include other types of memory or a combination thereof. Additionally, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system, the second computer system being coupled to the first computer system via a network, such as the Internet. The second computer system can provide program instructions to the first computer for execution. The term "storage medium" can include two or more storage media that can reside in different locations (eg, in different computer systems connected through a network). A storage medium may store program instructions (eg, a computer program) executable by one or more processors.

Of course, the storage medium including the computer executable instructions provided by the embodiment of the present application is not limited to the adjustment operation of the shooting parameters as described above, and may also perform the shooting parameters provided by any embodiment of the present application. Related operations in the adjustment method.

An embodiment of the present application provides a mobile terminal, where the mobile terminal has an operating system, and the adjustment device of the shooting parameters provided by the embodiment of the present application can be integrated into the mobile terminal. The mobile terminal can be a smart phone, a portable device (PAD), a smart wearable device, or the like. FIG. 7 is a structural block diagram of a mobile terminal according to an embodiment of the present application. As shown in FIG. 7, the mobile terminal can include a memory 710 and a processor 720. The memory 710 is configured to store a computer program, a scene recognition model, a preset scene library, and the like; the central processing unit 720 reads and executes a computer program stored in the memory 710. The processor 720 implements the method of any of the above embodiments when executing the computer program.

The memory and processor listed in the above examples are all components of the mobile terminal, and the mobile terminal may further include other components. Taking a smart phone as an example, the possible structure of the above mobile terminal will be described. FIG. 8 is a structural block diagram of a smart phone according to an embodiment of the present application. As shown in FIG. 8, the smart phone may include: a memory 80l, a central processing unit (CPU) 802 (also referred to as a processor, hereinafter referred to as a CPU), a peripheral interface 803, and a radio frequency (RF) circuit. 805, audio circuit 806, speaker 811, display 812, camera 813, graphics processing unit (GPU) 814, power management chip 808, input / output (I / O) subsystem 809, other inputs / Control device 810 and external port 804, these components communicate via one or more communication buses or signal lines 807.

The illustrated smartphone 800 is merely one example of a mobile terminal, and the smartphone 800 can have more or fewer components than those shown in the figures, two or more components can be combined, or can have different Component configuration. Each of the components shown in the figures can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The smart phone integrated with the adjustment parameter of the shooting parameter provided in the embodiment will be described in detail below.

The memory 801 can be accessed by the CPU 802, the peripheral interface 803, etc., and the memory 801 can include a high speed random access memory, and can also include a non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices. Or other volatile solid-state storage devices. The computer program is stored in the memory 811, and the scene recognition model, the preset scene library, the operation white list, the backup image of the first preview image, the backup image of the second preview image, and the like may also be stored.

Peripheral interface 803, which can connect the input and output peripherals of the device to CPU 802 and memory 801.

I/O subsystem 809, which can connect input and output peripherals on the device, such as display screen 812 and other input/control devices 810, to peripheral interface 803. The I/O subsystem 809 can include a display controller 8091 and one or more input controllers 8092 for controlling other input/control devices 810. Wherein, one or more input controllers 8092 receive electrical signals from other input/control devices 810 or transmit electrical signals to other input/control devices 810, and other input/control devices 810 may include physical buttons (press buttons, rocker buttons, etc.) ), dial, slide switch, joystick, click wheel. In an embodiment, the input controller 8092 can be connected to any of the following: a keyboard, an infrared port, a Universal Serial Bus (USB) interface, and a pointing device such as a mouse.

A display screen 812 is an input interface and an output interface between the user terminal and the user, and displays the visual output to the user. The visual output may include graphics, text, icons, video, and the like.

The camera 813 acquires an optical image of the object to be photographed, and converts the optical image into an electrical signal, which is input to the image processor 814 through the peripheral interface 803. In addition, the camera 813 acquires shooting parameters from the CPU 802 through the peripheral interface 803, and updates its own shooting parameters accordingly.

The image processor 814 is configured to acquire an electrical signal of the captured image, draw a captured image according to the electrical signal, and the drawn captured image is sent to the display 812 for display by the I/O subsystem 809.

Display controller 8081 in I/O subsystem 809 receives an electrical signal from display 812 or an electrical signal to display 812. Display 812 detects contact on the display screen and display controller 8091 converts the detected contact into interaction with a user interface object displayed on display screen 812, i.e., enables human-computer interaction, a user interface displayed on display screen 812. The object can be an icon that runs the game, an icon that is networked to the corresponding network, and the like. In an embodiment, the device may also include a light mouse, which is a touch sensitive surface that does not display a visual output, or an extension of a touch sensitive surface formed by the display screen.

The RF circuit 805 is configured to establish communication between the mobile phone and the wireless network (ie, the network side) to implement data reception and transmission between the mobile phone and the wireless network. For example, sending and receiving short messages, emails, and the like. In one embodiment, RF circuit 805 receives and transmits an RF signal, also referred to as an electromagnetic signal, and RF circuit 805 converts the electrical signal into an electromagnetic signal or converts the electromagnetic signal into an electrical signal, and through the electromagnetic signal and communication network And other devices to communicate. RF circuitry 805 may include known circuitry for performing these functions including, but not limited to, an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a codec CODER-DECoder (CODEC) chipset, Subscriber Identity Module (SIM), etc.

The audio circuit 806 is arranged to receive audio data from the peripheral interface 803, convert the audio data into an electrical signal, and transmit the electrical signal to the speaker 811.

The speaker 811 is arranged to restore the voice signal received by the mobile phone from the wireless network through the RF circuit 805 to sound and play the sound to the user.

The power management chip 808 is configured to provide power and power management for the hardware connected to the CPU 802, the I/O subsystem, and the peripheral interface.

The mobile terminal provided by the embodiment of the present invention can perform shooting scene recognition based on the scene recognition model, and automatically adjust the shooting parameters of the camera according to the shooting scene, thereby improving the accuracy of the scene recognition, expanding the type of the scene recognition, and improving the shooting effect.

The adjusting device, the storage medium and the mobile terminal provided in the above embodiments can perform the adjustment method of the shooting parameters provided by any embodiment of the present application, and have the corresponding functional modules and effects for executing the method. For the technical details that are not described in detail in the above embodiments, reference may be made to the method for adjusting the shooting parameters provided by any embodiment of the present application.

Claims

A method for adjusting shooting parameters, including:

Obtaining a first preview image of the object to be photographed, wherein the first preview image is a screen of the object to be photographed captured by the camera according to the first photographing parameter;

Identifying a shooting scene of the first preview image by a preset scene recognition model, wherein the scene recognition model is a deep learning model trained according to a picture sample set;

Adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, in the case that the shooting scene is a preset scene, to perform the object to be photographed according to the second shooting parameter. Shooting.
The method of claim 1 further comprising:

Acquiring a scene recognition model sent by the server, wherein the scene recognition model is a deep learning model trained by the server according to the picture sample set, and the picture sample set includes a picture sample for performing position marking on the target object for identifying the shooting scene .
The method of claim 1, wherein, in the case that the shooting scene is a preset scene, adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene comprises:

Matching the shooting scene with a preset scene in a preset scene library;

Determining a preset scene that is successfully matched with the shooting scene, acquiring a second shooting parameter corresponding to the preset scene, and replacing the first shooting parameter according to the second shooting parameter.
The method according to any one of claims 1 to 3, after adjusting the first shooting parameter of the camera according to the second shooting parameter corresponding to the preset scene, the method further includes:

Get the parameter correction operation;

Adjusting the second shooting parameter according to the parameter correction operation to obtain a third shooting parameter, and performing a shooting operation by using the third shooting parameter.
The method of claim 4 further comprising:

Recording the number of times of shooting using the third shooting parameter within a set time interval;

And the third shooting parameter is stored in the preset scene library in association with the preset scene when the number of times exceeds the set number of times threshold.
The method according to any one of claims 1 to 3, after replacing the first shooting parameter according to the second shooting parameter, further comprising:

Acquiring a second preview image, wherein the second preview image is a picture of the object to be photographed captured by the camera according to the second shooting parameter;

Controlling the first preview image to be displayed in a preset first area, and displaying the second preview image in a preset second area, wherein the first area and the second area constitute a display of a display screen region.
The method according to claim 6, wherein controlling the first preview image to be displayed in a preset first area and displaying the second preview image in a preset second area comprises:

Create the first layer;

Obtaining the first preview image, and performing image reduction processing on the first preview image to obtain a third preview image;

Drawing the third preview image in a first area of the first layer, wherein an area of the first area is smaller than an area of the first layer;

Create a second layer;

Obtaining the second preview image, and performing image reduction processing on the second preview image to obtain a fourth preview image;

Drawing the fourth preview image in a second region of the second layer, wherein an area of the second region is smaller than an area of the second layer, and the second layer is in the second layer The third area corresponding to the first area of a layer is a transparent layer;

The first layer and the second layer are synthesized to obtain a picture to be displayed, and the picture to be displayed is displayed.
The method of claim 7, after displaying the to-be-displayed screen, further comprising:

Obtaining a user operation for the third preview image or the fourth preview image;

Acquiring the first preview image or the second preview image according to the user operation, and displaying the first preview image or the second preview image in a display area of the display screen;

In the case where the photographing instruction is acquired, a photographing operation for the first preview image or the second preview image is performed.
The method of claim 8 further comprising:

Establishing an association relationship between the user operation, the third preview image and the fourth preview image, and a processing operation, and storing the association relationship in an operation whitelist; wherein the processing operation is A processing operation of the first preview image or the second preview image.
An adjustment device for shooting parameters, comprising:

An image acquisition module, configured to acquire a first preview image of the object to be photographed, wherein the first preview image is a screen of the object to be photographed captured by the camera according to the first photographing parameter;

a scene recognition module, configured to identify a shooting scene of the first preview image by a preset scene recognition model, wherein the scene recognition model is a deep learning model trained according to a picture sample set;

a parameter adjustment module, configured to adjust a first shooting parameter of the camera according to a second shooting parameter corresponding to the preset scene, in a case that the shooting scene is a preset scene, according to the second shooting parameter pair The subject to be photographed is photographed.
The apparatus of claim 10 further comprising:

a model obtaining module, configured to acquire a scene recognition model sent by the server, wherein the scene recognition model is a deep learning model trained by the server according to the image sample set, and the image sample set includes a target object for identifying a shooting scene A sample image of the location marker.
The apparatus of claim 10 wherein said parameter adjustment module is configured to:

Matching the shooting scene with a preset scene in a preset scene library;

Determining a preset scene that is successfully matched with the shooting scene, acquiring a second shooting parameter corresponding to the preset scene, and replacing the first shooting parameter according to the second shooting parameter.
The apparatus of any of claims 10-12, further comprising:

The scene library update module is configured to acquire a parameter correction operation; and adjust the second shooting parameter according to the parameter correction operation to obtain a third shooting parameter, and perform a shooting operation by using the third shooting parameter.
The apparatus according to claim 13, wherein the scene library updating module is further configured to: record a number of times of shooting with the third shooting parameter within a set time interval; and when the number of times exceeds a set number of times threshold The third shooting parameter is stored in the preset scene library in association with the preset scene.
The apparatus of any of claims 10-12, further comprising:

a first image display module configured to acquire a second preview image, wherein the second preview image is a screen of the object to be photographed captured by the camera according to the second shooting parameter;

Controlling the first preview image to be displayed in a preset first area, and displaying the second preview image in a preset second area, wherein the first area and the second area constitute a display of a display screen region.
The apparatus of claim 15 wherein said first image display module is configured to:

Create the first layer;

Obtaining the first preview image, and performing image reduction processing on the first preview image to obtain a third preview image;

Drawing the third preview image in a first area of the first layer, wherein an area of the first area is smaller than an area of the first layer;

Create a second layer;

Obtaining the second preview image, and performing image reduction processing on the second preview image to obtain a fourth preview image;

Drawing the fourth preview image in a second region of the second layer, wherein an area of the second region is smaller than an area of the second layer, and the second layer is in the second layer The third area corresponding to the first area of a layer is a transparent layer;

The first layer and the second layer are synthesized to obtain a picture to be displayed, and the picture to be displayed is displayed.
The apparatus of claim 16 further comprising:

a second image display module configured to acquire a user operation for the third preview image or the fourth preview image; and acquire the first preview image or the second preview image according to the user operation, and The display area of the display screen displays the first preview image or the second preview image;

The image capturing module is configured to perform a photographing operation for the first preview image or the second preview image in a case where a photographing instruction is acquired.
The apparatus according to claim 17, wherein the second image display module is further configured to: pre-establish an association relationship between the user operation, the third preview image and the fourth preview image, and a processing operation, And storing the association relationship in an operation whitelist; wherein the processing operation is a processing operation on the first preview image or the second preview image.
A computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements a method of adjusting shooting parameters as claimed in any one of claims 1-9.
A mobile terminal comprising a memory, a processor, and a computer program stored on the memory and operable by the processor, the processor executing the computer program to perform the shooting according to any one of claims 1-9 The method of adjusting the parameters.