WO2019213818A1

WO2019213818A1 - Photographing control method, and electronic device

Info

Publication number: WO2019213818A1
Application number: PCT/CN2018/085898
Authority: WO
Inventors: 王星泽
Original assignee: 合刃科技（武汉）有限公司
Priority date: 2018-05-07
Filing date: 2018-05-07
Publication date: 2019-11-14
Also published as: CN111279684A

Abstract

Provided is a photographing control method, comprising: acquiring a preview image; and using a preset model to analyze the preview image so as to obtain a photographing parameter to be used in a photographing operation. Also provided is an electronic device implementing the photographing control method. In the photographing control method and the electronic device of the present invention, a preview image is analyzed to determine a current photographing parameter. Since a photographing parameter can be timely determined according to a preview image, the photographing parameter can be used to timely capture a high quality image of a current scene of interest.

Description

Shooting control method and electronic device

Technical field

The present application relates to the field of electronic devices, and in particular, to a photographing control method for an electronic device and the electronic device.

Background technique

Now, with the improvement of people's living standards, taking pictures has become a common function that is not indispensable in life. Nowadays, whether it is a camera or an electronic device such as a mobile phone or a tablet computer with a camera function, pixels are getting higher and higher, and the quality of photographs is getting better and better. However, current electronic devices such as cameras and mobile phones often require the user to manually set shooting parameters or perform shooting parameters according to the current environment when performing photographing control. However, currently, the shooting parameters are manually set or according to the current environment. There are certain hysteresis in setting the shooting parameters, which leads to the flashing of the wonderful picture when the shooting parameters are set, which often leads to the regret of missing the wonderful picture.

Summary of the invention

The present application provides a shooting control method and an electronic device, which can set the shooting parameters in time, so that a wonderful moment can be captured in time with a high shooting quality.

In one aspect, a shooting control method is provided, the shooting control method comprising: acquiring a shooting preview screen; analyzing the shooting preview image with a preset model to obtain shooting parameters for shooting.

In another aspect, an electronic device is provided, the electronic device including a camera, a memory, and a processor. The memory is for storing program instructions. The processor is configured to execute the shooting control method by calling the program instruction, the shooting control method includes: acquiring a shooting preview image by using a camera; analyzing the shooting preview image by using a preset model to obtain shooting parameters for use in Shooting.

In still another aspect, a computer readable storage medium is provided, the computer readable storage medium storing program instructions for executing a shooting control method after the computer calls, the shooting control method comprising: acquiring a shooting Previewing the picture; analyzing the shooting preview picture with a preset model to obtain shooting parameters for shooting.

The shooting control method and the electronic device of the present application determine the current shooting parameters by analyzing the shooting preview screen, and can determine the shooting parameters in time according to the shooting preview screen, so that the shooting quality can be timely according to the shooting parameters when shooting is required. Capture the current moments.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some embodiments of the present application, Those skilled in the art can also obtain other obvious modifications according to these drawings without any creative work.

1 is a flow chart of a photographing control method in a first embodiment of the present application.

2 is a flowchart of a photographing control method in a second embodiment of the present application

FIG. 3 is a flowchart of a photographing control method in a third embodiment of the present application.

4 is a flow chart of a photographing control method in a fourth embodiment of the present application.

FIG. 5 is a flowchart of a photographing control method in a fifth embodiment of the present application.

6 is a flowchart of a photographing control method in a sixth embodiment of the present application

FIG. 7 is a flowchart of a photographing control method in a seventh embodiment of the present application.

FIG. 8 is a flowchart of a photographing control method in an eighth embodiment of the present application.

FIG. 9 is a flowchart of a photographing control method in a ninth embodiment of the present application.

FIG. 10 is a block diagram showing a schematic partial structure of an electronic device according to an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

The shooting control method of the present application can be applied to an electronic device. The electronic device can include a camera. The electronic device can acquire a shooting preview screen and display a shooting preview image through the camera, and the electronic device can perform photographing, continuous shooting, video shooting, etc. through the camera. . Among them, the camera includes a front camera and a rear camera, and the operations of photographing, continuous shooting, video shooting, etc. can be performed by a rear camera or a self-timer by a front camera.

Please refer to FIG. 1 , which is a flowchart of a shooting control method in a first embodiment of the present application. The shooting control method is applied to an electronic device. In the first embodiment, the photographing control method includes the following steps:

S11: Acquire a shooting preview screen.

In some embodiments, the operation of acquiring the shooting preview screen is performed by the camera in response to the operation of turning on the camera, that is, the shooting preview screen is acquired by the camera. The shooting preview screen is a framing screen when the camera is turned on for framing.

In some embodiments, the operation of turning on the camera is a click operation on the photographing application icon, that is, when the camera is turned on in response to a click operation on the photographing application icon, the shooting preview screen is acquired by the camera.

Alternatively, in other embodiments, the operation of turning on the camera is a specific operation of a physical button of the electronic device. For example, the electronic device includes a volume up button and a volume down button, and the operation of turning on the camera is to increase the volume and volume. Simultaneous pressing of small keys. Further, the operation of turning on the photographing application is an operation of pressing the volume up key and the volume down key in a preset time (for example, 2 seconds).

In other embodiments, the operation of turning on the camera may also be an operation of a preset touch gesture input in any display interface of the electronic device. For example, on the main interface of the electronic device, the user may input a circular touch track. Turn on the camera with a touch gesture.

In other embodiments, the operation of turning on the camera may also be an operation of a preset touch gesture input on the touch screen when the electronic device is in a black screen state.

In some embodiments, when the electronic device is a camera, the operation of turning on the camera is an operation that presses the shutter button/power button of the camera to trigger the camera to be in an activated state.

Optionally, in the present application, acquiring a shooting preview screen is to obtain a shooting preview screen in real time through a camera.

S13: The shooting preview image is analyzed by using a preset model to obtain shooting parameters for shooting.

The preset model may be a trained model or an untrained model.

Optionally, in some embodiments, the preset model is a trained neural network model, and the shooting preview image is analyzed by using a preset model to obtain shooting parameters for shooting, including: taking all the pixels of the preview image as Input, calculated by the neural network model and output shooting parameters for shooting.

Optionally, in other embodiments, the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes the trained target object feature model, and the preset preview model is used to analyze the captured preview image. Obtaining shooting parameters for shooting, comprising: using an image recognition technology to analyze a target object in the captured preview image to generate a corresponding target object feature vector; according to the trained target object feature model and the target object feature corresponding to the captured preview image The vector obtains an analysis result; the shooting parameters are determined for the shooting based on the analysis result.

Optionally, in an implementation manner, the analysis result is obtained according to the trained target object feature model and the target object feature vector corresponding to the captured preview image, including: the target object model that has been trained and the target corresponding to the captured preview image The object feature vector calculates the analysis result of the target object feature corresponding to the captured preview screen.

In an implementation manner, determining the shooting parameters for the shooting according to the analysis result includes: determining, according to the correspondence between the preset target object features and the shooting parameters, the shooting parameters corresponding to the obtained target object features.

Optionally, in another implementation manner, the preset model is a trained image processing algorithm model, and when the trained image processing algorithm model includes the trained target object feature model, the preset model is used to capture the preview image. The imaging parameters are obtained for the imaging, including: taking the target object feature vector corresponding to the captured preview image as the input information of the trained target object feature model, and obtaining the shooting parameters through the trained target object feature model.

In some embodiments, in the present application, the analysis result is that the analysis result is obtained according to the real-time acquired shooting preview screen. In other embodiments, the shooting preview screen is analyzed by using a preset model to obtain shooting parameters: the currently acquired shooting preview screen is analyzed every time by a preset time (for example, 0.2 seconds) to obtain shooting parameters.

In the present application, the target object may be a hand, a face, a specific scene, etc.; the target object feature model includes a gesture feature model, an expression feature model, and a scene feature model, etc., and the analyzed target object feature vector may include a gesture. The feature vector, the expression feature vector, the scene feature vector, and the like, and the analyzed target object features may also include gesture features, expression features, and scene features.

The shooting parameters include, but are not limited to, at least one of a shutter time, an aperture size, a sensitivity, and the like.

Therefore, in the present application, by determining the current shooting parameters by analyzing the shooting preview screen, the shooting parameters can be determined in time according to the shooting preview screen, so that the current exciting moment can be captured in time with a higher shooting quality according to the shooting parameters when shooting is required.

Please refer to FIG. 2 , which is a flowchart of a shooting control method in a second embodiment of the present application. In the second embodiment, the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes the trained target object feature model, and the shooting control method includes the following steps:

S21: Acquire a shooting preview screen.

S23: analyzing the target object in the shooting preview image by using image recognition technology, generating a corresponding target object feature vector, and obtaining an analysis result according to the trained target object feature model and the target object feature vector corresponding to the captured preview image.

The target object may include an object such as a hand, a face, and a specific scene. The target object feature model may include a gesture feature model, an expression feature model, a scene feature model, etc., and the analyzed target object feature vector may include laughing and angry. Expression eigenvectors such as yawning, or gesture feature vectors such as "OK" gestures, "V-shaped", or landscape feature vectors such as flowers, birds, and mountains. The analyzed target features may also include laughter, anger, yawning, etc. Emoticon features, or "OK" gestures, "V-shaped" and other gesture features, or landscape features such as flowers, birds, mountains.

Taking the target object as the hand and the target object feature model as the gesture feature model as an example, using the preset model to analyze the captured preview image and obtaining the analysis result may further specifically include: using the image recognition technology to perform the gesture in the captured preview image. The analysis generates a corresponding gesture feature vector; and obtains an analysis result according to the gesture feature model and the gesture feature vector corresponding to the captured preview image.

Further, in an implementation manner, the analysis result is obtained according to the gesture feature model and the gesture feature vector corresponding to the captured preview image, including: calculating a shooting preview by using the trained gesture feature model and the target object feature vector corresponding to the captured preview image The analysis result of the gesture feature corresponding to the picture.

In some embodiments, the trained target object feature model includes a plurality of reference images and a reference target object feature vector of the plurality of reference images, the target corresponding to the captured target object feature model and the captured preview image The object feature vector calculates an analysis result of the target object feature corresponding to the captured preview image, including: the target object feature vector corresponding to the captured preview image and the reference target object in the plurality of reference images by the trained target object feature model The feature vectors are compared, a reference image corresponding to the reference object feature vector with the highest similarity is determined, and the target object feature is derived from the reference image. For example, after the reference image is determined, the target object feature is determined based on the label of the reference image.

S25: The shooting parameters are determined according to the analysis result for shooting.

In some embodiments, when the analysis result is a target object feature obtained according to the trained target object feature model, determining a shooting parameter for the shooting according to the analysis result, including: according to the preset target object feature and the shooting parameter Corresponding relationship determines the shooting parameters corresponding to the target object features.

Optionally, it may be set in advance that the target object feature is used to determine the shooting parameter, for example, the corresponding relationship between the shutter time and/or the aperture size and the target object feature is preset. For example, if the shooting parameters include the shutter time and/or the aperture size, and the target object feature may be an expression feature, a gesture feature, a scene feature, etc., the corresponding relationship between the shutter time and/or the aperture size and the expression feature is preset, or preset There is a correspondence between the shutter time and/or the aperture size and the gesture feature, or a correspondence between the shutter time and/or the aperture size and the specific scene feature is preset.

In particular, when the target object feature is a gesture feature, a correspondence relationship between the shutter time and/or the aperture size and the gesture feature of the thumb and the index finger distance may be preset, wherein the shutter time may be logarithmically related to the distance between the thumb and the index finger. . Therefore, when the gesture feature of the distance between the thumb and the index finger is obtained according to the analysis result, the shutter time can be determined according to a preset correspondence relationship between the shutter time and/or the aperture size and the gesture feature of the thumb and the index finger distance. The shooting parameters such as the aperture size and/or the aperture size are controlled to achieve exposure intensity and/or shooting depth of field.

For another example, when the target object feature is an expression feature, a corresponding relationship between a shooting parameter such as a shutter time and/or a aperture size and a different expression feature, such as setting a shutter time and/or a aperture size, and smiling, laughing, and angry may be set. The corresponding relationship between the expression features such as crying, yawning, and the like, and corresponding expression features are obtained according to the analysis result, and the corresponding shooting parameters can be determined according to the correspondence between the shooting parameters and the different expression features and the obtained expression features.

In other embodiments, when the analysis result is an analysis result including a shooting parameter obtained by the trained target object feature model, the shooting parameter is determined according to the analysis result for shooting, including: according to the trained target object feature model The resulting analysis results including the shooting parameters, and the shooting parameters are determined for shooting.

In some embodiments, the target object feature model may be a model completed by the following training steps: using an image or face recognition technique to analyze a target object in each photo in the initial training set to generate a corresponding target object feature vector. And establishing a training sample set based on the generated target object feature vector and the similarity label between the corresponding photo and the reference picture; and using the sample set for training learning, obtaining the trained target object feature model.

Therefore, in the present application, the shooting parameters can be determined according to the target object in the shooting preview screen, and the shooting parameters corresponding to the target object can be set in time and more reasonably, and the shooting quality can be improved and the setting of the shooting parameters can be completed in time.

The foregoing correspondence may be a correspondence table stored in a memory of the electronic device.

The step S21 corresponds to the step S11 in FIG. 1 . For more specific description, reference may be made to the related description of FIG. 1 , and details are not described herein again. Steps S23 to S25 correspond to step S13 in FIG. 1, and related descriptions can be referred to each other.

Please refer to FIG. 3 , which is a flowchart of a shooting control method in a third embodiment of the present application. In the third embodiment, the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes the trained target object feature model, and the shooting control method includes the following steps:

S301: Acquire a shooting preview screen.

S303: Analyze a target object in the preview image by using an image recognition technology to generate a corresponding target object feature vector.

S305: The target object feature vector corresponding to the captured preview image is taken as the input information of the trained target object feature model, and the captured target object feature model is used to obtain the shooting parameters for shooting.

The target object may include an object such as a hand, a face, and a specific scene. The target object feature model may include a gesture feature model, an expression feature model, a scene feature model, and the like, and the analyzed target object feature vector may include a laugh. Expression eigenvectors such as anger, yawning, etc., or gesture feature vectors such as "OK" gestures, "V-shaped", or vector features such as flowers, birds, mountains, etc., and the analyzed target features may also include laughing, angry, playing Yawns and other expression features, or "OK" gestures, "V-shaped" and other gesture features, or flowers, birds, mountains and other features.

Taking the target object as the hand and the target object feature model as the gesture feature model, taking the target object feature vector corresponding to the captured preview image as the input information of the trained target object feature model, and passing the trained target The object feature model obtains the shooting parameters for the shooting, and may include: taking the gesture feature vector corresponding to the shooting preview image as the input information of the trained gesture feature model, and obtaining the corresponding shooting parameter by using the trained gesture feature model. Used for shooting.

The step S301 corresponds to the step S11 in FIG. 1 . For a more specific description, reference may be made to the related description in FIG. 1 , and details are not described herein again. Steps S303 to S305 correspond to step S13 in FIG. 1, and related descriptions can be referred to each other. Steps S303 and S305 also have a certain correspondence with steps S203 and S205 in FIG. 2, and related features may also be referred to each other.

Please refer to FIG. 4 , which is a flowchart of a shooting control method in a fourth embodiment of the present application. In the fourth embodiment, the preset model is a trained neural network algorithm model, and the shooting control method includes the following steps:

S31: Acquire a shooting preview screen.

S33: Taking all the pixels of the preview image as input, the calculation is performed by the trained neural network model, and the shooting parameters are output for shooting.

That is, in some embodiments, the shooting parameters can be directly calculated by the trained neural network model by taking all pixels of the preview image as input information of the trained neural network model.

The steps S31 to S33 correspond to the steps S11 to S13 in FIG. 1 , and the description relationship between the upper and lower positions is mutually related, and the related descriptions can refer to each other.

Please refer to FIG. 5 , which is a flowchart of a shooting control method in a fifth embodiment of the present application. The difference from the first embodiment is that, in the fifth embodiment, it is further determined whether the shooting condition is currently satisfied. In the fifth embodiment, the photographing control method includes:

S41: Acquire a shooting preview screen.

S43: The shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is currently satisfied. If yes, go to step S45, otherwise go back to step S43 or the process ends.

In some embodiments, when the preset model is a trained neural network model; analyzing the captured preview image by using the preset model to determine whether the shooting condition is currently satisfied, and further comprising: capturing a preview image by using the trained neural network model The analysis is performed to obtain an analysis result including satisfaction; and based on the analysis result, it is determined whether the shooting condition is currently satisfied. Specifically, in some embodiments, when it is determined that the satisfaction exceeds the satisfaction preset threshold, it is determined that the shooting condition is currently satisfied. Among them, the satisfaction degree is that the neural network model outputs an analysis result including the satisfaction degree by processing all the pixels of the preview image and processing according to the pre-trained model. The satisfaction preset threshold may be 80%, 90%, and the like.

That is, in some embodiments, when the shooting preview screen is analyzed by using the preset model, not only the shooting parameters are analyzed, but also the analysis result including the satisfaction is analyzed to determine whether the shooting conditions are satisfied.

Optionally, in another embodiment, when the preset model is a trained image processing algorithm model, the preset preview model is used to analyze the captured preview image to determine whether the shooting condition is currently met, including: using the trained image processing. The algorithm model compares the shot preview screen with the reference picture, analyzes the analysis result including the similarity between the preview picture and the reference picture, and determines whether the current shooting condition is satisfied according to the analysis result. The determining whether the current shooting condition is met according to the analysis result includes: determining that the shooting condition is currently satisfied when determining that the similarity exceeds the similarity preset threshold. The similarity preset threshold may be 80%, 90%, and the like.

The reference picture may be a standard picture preset by the user with a specific expression such as smiling, laughing, sad, angry, yawning, or a standard picture with gestures such as an "OK" gesture or a "V-shaped" gesture. It can also be a standard picture with flowers, birds, mountains and other scenery.

That is, in some embodiments, when the preview image is analyzed by using the preset model, not only the shooting parameters are analyzed, but also the similarity with the reference image is analyzed to determine whether the shooting condition is satisfied.

Further, the trained image processing algorithm model includes the trained target object feature model, and the trained image processing algorithm model is used to compare the captured preview image with the reference image, and the similarity between the captured preview image and the reference image is analyzed, including The image recognition technology is used to analyze the target object in the preview image, and the corresponding target object feature vector is generated. The captured preview image and the reference image are calculated according to the trained target object feature model and the target object feature vector corresponding to the captured preview image. Similarity.

In some embodiments, the similarity between the captured preview image and the reference image is calculated according to the trained target object feature model and the target object feature vector corresponding to the captured preview image, including: taking the target object feature vector corresponding to the captured preview image as The input information of the target object model of the training is calculated, and the similarity between the shooting preview picture and the reference picture is calculated by the target object feature model.

In other embodiments, the captured image processing algorithm model is used to compare the shooting preview image with the reference image, and the similarity between the shooting preview image and the reference image is analyzed, including: acquiring pixel information of the shooting preview image; The pixel information of the screen is compared with the pixel information of the reference picture, and the similarity between the shooting preview picture and the reference picture is analyzed. That is, in other embodiments, the similarity between the captured preview picture and the reference picture is obtained by comparing the pixel information such as the pixel grayscale value of the two images.

In another embodiment, determining the current shooting condition by analyzing the shooting preview image by using the preset model, including: analyzing the target object in the shooting preview image by using an image recognition technology, and generating a corresponding target object feature vector; The target object feature vector is used as input information of the image processing algorithm model, and an analysis result including identification information indicating whether the shooting condition is currently satisfied is obtained; and whether the shooting condition is satisfied is determined according to the analysis result. For example, the identification information may be an identifier of 1, 0, etc., which identifies whether the analysis result of the shooting condition is currently satisfied. More specifically, when the identification information is 1, the identification satisfies the shooting condition, and when the identification information is 0, the identification does not satisfy the shooting condition. Determining whether the photographing condition is satisfied according to the analysis result includes: determining that the photographing condition is currently satisfied when the analysis result includes identifying the identifier information that currently meets the photographing condition; and when the analysis result includes identifying the identifier information that does not satisfy the photographing condition at present, Make sure that the shooting conditions are not currently met.

The target object may include an object such as a face, a hand, and a specific scene. The target object feature model may include an expression feature model, a gesture feature model, a scene feature model, and the like, and the analyzed target object feature vector may include the foregoing. Emoticon, angry, yawning and other expression vector, or "OK" gesture, "V-shaped" and other gesture feature vectors, or flower, bird, mountain and other scene feature vectors.

In some embodiments, taking the expression feature model as an example, the trained expression feature model is completed by training: providing multiple photos with different expression faces in the initial training set; using face recognition technology, The characters in the multiple photos provided in the initial training set perform facial expression analysis to generate a corresponding expression feature vector Xi. For example, X1 represents the size of the eye opening, X2 represents the degree of the mouth angle rising, and X3 represents the size of the mouth opening; The expression feature vector and the similarity label between the corresponding photo and the reference picture establish a training sample set; and then use the sample set to perform training learning, and obtain the trained expression feature model.

The similarity between the shooting preview screen and the reference picture may be style similarity, color similarity, element layout similarity, grayscale similarity, and the like.

S45: The shooting preview parameter is analyzed by using a preset model to determine shooting parameters.

S47: Perform a shooting operation according to the shooting parameter control.

In some implementations, the photographing operation is a photographing operation, and the photographing operation is performed according to the photographing parameter control, including: performing a photographing operation according to the photographing parameter control, and obtaining a photograph corresponding to the current photographing preview screen.

In other implementations, the photographing operation is a continuous shooting operation, and the photographing operation is performed according to the photographing parameter control, including: controlling to perform the continuous shooting operation, and obtaining a plurality of photographs including the photograph corresponding to the current photographing preview screen. Optionally, after performing the continuous shooting operation, further steps may be further included: analyzing a plurality of photos obtained by the continuous shooting operation to determine the best photo; and retaining the best photo, and performing the continuous shooting operation Get other photos to delete.

In other implementations, the photographing operation is a video photographing operation, and the photographing operation is performed according to the photographing parameter control, including: performing a photographing operation according to the photographing parameter control, and obtaining a video file that uses the current photographed preview screen as a starting video frame frame. Optionally, after the video recording operation is performed to obtain the video file, the method may further include: after the video file is captured, the plurality of video frame frames in the captured video file may be compared to determine an optimal screen. Frame; and intercept the best picture frame to save as a photo.

Therefore, in the present application, by analyzing the shooting preview screen to determine whether the shooting condition is currently satisfied, whether or not the user desires to take the picture can be determined according to the content in the shooting preview screen, so that the current exciting moment can be captured in time, and also according to the shooting. The content in the preview screen automatically determines the shooting parameters, and the shooting operation can be performed in accordance with the shooting parameters of the current shooting preview screen, ensuring high shooting quality.

The step S41 corresponds to the step S11 in FIG. 1 . For a specific description, reference may be made to the related description of step S11 in FIG. 1 . Step S45 corresponds to step S13 in FIG. 1 and steps S23, S25 and the like in FIG. 2. For specific introduction, reference may be made to step S13 in FIG. 1, step S23, S25 in FIG. 2, and the like.

Wherein, in some embodiments, step S43 is performed before step S45, that is, determining that the shooting parameters including the shutter time or the aperture size are performed after determining that the shooting condition is satisfied, and the shooting preview screen is performed after the determined shooting condition is satisfied. Analysis determines the shooting parameters, thus avoiding the determination of shooting parameters every time, avoiding the waste of computing resources.

In some embodiments, step S43 and step S45 are performed simultaneously, that is, the shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is met and the shooting parameters are determined according to the analysis result, and the preset model is adopted. When analyzing the shooting preview screen, it is analyzed at the same time to determine whether the shooting conditions and shooting parameters are satisfied.

In some embodiments, when the preset model is an image processing algorithm model, the target object and the target object feature model for determining whether the shooting condition is satisfied may be the same as the target object and the target object feature model for determining the shooting parameters.

For example, the target object is a facial expression, and the target object feature model is an expression feature model. The analysis of the captured preview image by using the preset model may include: using the image recognition technology to perform the facial expression in the captured preview image. Analyzing, generating a corresponding expression feature vector; obtaining similarity with the reference image according to the expression feature model and the expression feature vector corresponding to the preview image, or directly obtaining identification information indicating whether the shooting condition is satisfied, and according to the expression feature model and the shooting preview screen The corresponding emoticon vector obtains the emoticon feature or directly obtains the shooting parameters.

That is, according to the facial expression in the shooting preview screen, it is possible to simultaneously determine whether the shooting condition is satisfied and determine the shooting parameter.

In other embodiments, when the preset model is an image processing algorithm model, the target object and the target object feature model for determining whether the shooting condition is satisfied may be different from the target object and the target object feature model for determining the shooting parameters. For example, the target object and the target object feature model for determining whether the shooting condition is satisfied are the first target object and the first target object feature model, respectively, and the target object and the target object feature model for determining the shooting parameter are respectively the second target object. And a second target object feature model.

In a more specific example, the target object and the target object feature model for determining whether the shooting condition is satisfied are a face and an expression feature model, respectively, and the target object and the target object feature model for determining the shooting parameters are gestures and gesture features, respectively. model. The analysis result obtained by analyzing the shooting preview screen by using the preset model may include: analyzing the facial expression in the shooting preview image by using the image recognition technology, generating a corresponding expression feature vector, and using the image recognition technology to capture the preview image. The gesture is analyzed to obtain a gesture feature vector; the similarity with the reference image is obtained according to the expression feature model and the expression feature vector corresponding to the preview image, or the identification information that directly identifies whether the shooting condition is satisfied; and the gesture feature model and the shooting preview screen are obtained according to the gesture feature model The corresponding emoticon vector obtains a gesture feature or directly obtains a shooting parameter.

That is, the shooting parameters are determined according to whether the facial expression in the shooting preview screen satisfies the shooting condition and the gesture in the shooting preview screen.

Please refer to FIG. 6 , which is a flowchart of a shooting control method in a sixth embodiment of the present application. In the sixth embodiment, the photographing control method includes:

S51: Acquire a shooting preview screen.

Step S51 corresponds to step S11 in FIG. 1. For a specific description, reference may be made to the related description of step S11 in FIG. 1.

S53: The shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is currently satisfied and the shooting parameters for shooting are determined.

In some embodiments, when the trained model is a trained neural network model, step S53 includes: calculating whether the output includes the shooting condition by using the neural network model by taking all pixels of the preview image as input of the neural network model And information such as shooting parameters.

In some embodiments, when the trained model is a trained image processing algorithm model, taking the trained image processing algorithm model including the trained expression feature model and the trained gesture feature model as an example, step S53 includes: Determining the expression similarity according to the trained expression feature model and the expression feature vector corresponding to the captured preview image, and determining the gesture feature corresponding to the captured preview image according to the trained gesture feature model and the gesture feature vector corresponding to the captured preview image. Determining that the shooting condition is satisfied when determining that the expression similarity is greater than the similarity preset threshold; determining the gesture feature according to the gesture feature model and the gesture feature vector corresponding to the captured preview image, for example, obtaining the distance between the index finger and the thumb, and predefining The corresponding relationship between the gesture feature and the shooting parameter determines the shooting parameter corresponding to the obtained gesture feature, for example, the shutter time is determined according to the correspondence between the gesture feature of the index finger and the thumb and the shutter time.

In other embodiments, taking the trained image processing algorithm model including the trained expression feature model and the trained gesture feature model as an example, step S53 may further include: using the expression feature vector corresponding to the captured preview image as an expression feature. The input information of the model, and the identification information identifying whether the shooting condition is satisfied is obtained by the trained expression feature model, and the gesture feature vector corresponding to the shooting preview image is used as the input information of the trained gesture feature model, and the trained The gesture feature model obtains the shooting parameters, thereby obtaining information including the identification information that identifies whether the shooting condition is satisfied and the shooting parameters; and the identification information obtained according to the trained expression feature model to satisfy the shooting condition and the basis The shooting parameters derived from the trained gesture feature model determine whether the shooting conditions are met and the shooting parameters are determined.

S55: When it is determined that the shooting condition is currently satisfied, the shooting operation is performed according to the shooting parameter control.

Step S55 corresponds to step S47 in FIG. 5. For a specific description, reference may be made to the related description of step S47 in FIG. 5. Step S53 - has a certain correspondence with steps S43 - S45 in FIG. 5 , and specifically determines whether the current shooting condition and the shooting parameters are obtained according to the analysis result, and may further refer to the description of steps S43 to S45 in FIG. 5 .

Therefore, in the sixth embodiment, the shooting preview screen can be analyzed while determining whether the shooting condition and the shooting parameters are satisfied, and when the shooting condition is satisfied, the shooting operation is performed with the shooting parameters, and the shooting parameters can be quickly performed with better shooting parameters. Shooting, you can capture the moments in time with high shooting quality.

Please refer to FIG. 7 , which is a flowchart of a shooting control method in a seventh embodiment of the present application. In the seventh embodiment, the photographing control method includes:

S61: Acquire a shooting preview screen.

Step S61 corresponds to step S11 in FIG. 1. For a specific description, reference may be made to the related description of step S11 in FIG. 1.

S63: The shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is currently satisfied and the shooting parameters for shooting are determined.

S65: When it is determined that the shooting condition is currently satisfied, the continuous shooting operation is performed according to the shooting parameter control, and a plurality of photos including the photo corresponding to the current photo preview screen are obtained.

In some embodiments, step S65 includes: determining that the shooting condition is satisfied when the similarity between the shooting preview screen and the reference picture exceeds the similarity preset threshold, and controlling to perform the continuous shooting operation.

In other embodiments, when the analysis result of the satisfaction is obtained by the trained neural network model, step S65 may further include: when the satisfaction exceeds the satisfaction preset threshold, determining that the shooting condition is satisfied, and controlling to perform continuous shooting operating.

The requirement of the shooting condition when performing the continuous shooting operation may be slightly lower than the requirement when the photographing operation is performed. Specifically, the comparison similarity preset threshold or the satisfaction preset threshold may be slightly lower than the execution of the photographing when performing the continuous shooting operation. The similarity preset threshold or satisfaction preset threshold of the operation comparison.

For example, the similarity preset threshold or the satisfaction preset threshold when performing the continuous shooting operation may be 70%, which is lower than the similarity preset threshold or the satisfaction preset threshold of 80% or higher in performing the photographing operation comparison. .

Thus, continuous shooting is achieved when the best shooting effect is about to be achieved, and a photograph of the best shooting effect in continuous shooting can be ensured. For example, the reference picture is a picture with a laughing expression, and the contrast expression vector is an expression feature vector X2 indicating the degree of the mouth angle rising, and the continuous shooting operation is controlled when it is determined that the mouth angle rises to 70% of the reference picture. The user continues to smile for a short period of time, and the user's smile reaches the maximum level. This expression will be captured by the continuous shooting operation, and the photo that ensures the best shooting effect can be ensured by the continuous shooting operation.

Steps S61 to S65 correspond to steps S51 to S55 in FIG. 6, respectively. For a more specific description, reference may be made to the related descriptions of steps S51 to S55 in FIG. 6.

As shown in FIG. 7, the seventh embodiment shown in FIG. 7 may further include the following steps:

S67: Analyze a plurality of photos obtained by the continuous shooting operation to determine the best photo.

Optionally, in an implementation manner, step S67 may include: analyzing the plurality of photos by using the trained neural network model to obtain satisfaction, and determining the photo with the highest satisfaction as the best photo.

Optionally, in another implementation manner, step S67 may include: comparing a plurality of photos obtained by continuous shooting with a reference picture, and determining a photo with the highest similarity with the reference picture as the best photo.

Optionally, as shown in FIG. 7, the shooting control method may further include:

S69: Keep the best photos and delete other photos obtained by the continuous shooting operation.

In some embodiments, the electronic device includes a memory in which a plurality of albums are created, "preserve the best photos" to store the best photos in a certain album, such as in a camera album. Among them, by deleting other photos, it can effectively avoid occupying too much storage space.

Please refer to FIG. 8 , which is a flowchart of a shooting control method in an eighth embodiment of the present application. In the eighth embodiment, the photographing control method includes:

S71: Acquire a shooting preview screen.

Step S71 corresponds to step S11 in FIG. 1. For a specific description, reference may be made to the related description of step S11 in FIG. 1.

S73: The shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is currently satisfied and the shooting parameters for shooting are determined.

S75: When it is determined that the shooting condition is currently satisfied, the video shooting operation is performed according to the shooting parameter control, and the video file with the current shooting preview picture as the starting video picture frame is obtained.

The requirement of the shooting condition when performing the video shooting operation may also be slightly lower than the requirement when the photographing operation is performed. Specifically, the comparison similarity preset threshold or the satisfaction preset threshold may be slightly lower than the execution when performing the continuous shooting operation. The similarity preset threshold or the satisfaction preset threshold of the photographing operation comparison.

Thus, video shooting is performed when the best shooting effect is about to be achieved, and the video frame frame including the best shooting effect in the video file can be ensured.

The steps S71-S75 correspond to the steps S61-S65 in the seventh embodiment shown in FIG. 7, respectively. For a more specific introduction, reference may be made to the related description of FIG. For example, step S77 may include: when the similarity between the shooting preview screen and the reference picture exceeds the similarity preset threshold, determining that the shooting condition is satisfied, and controlling to perform the video shooting operation. Optionally, in step S77, the method may further include: when the satisfaction exceeds the satisfaction preset threshold, determining that the shooting condition is met, and controlling to perform the video shooting operation.

As shown in FIG. 8, the eighth embodiment shown in FIG. 8 may further include the following steps:

S77: Compare multiple video picture frames in the captured video file to determine an optimal picture frame.

Optionally, in an implementation manner, step S77 may include: analyzing the plurality of video picture frames by using the trained neural network model to obtain satisfaction, and determining a video frame frame with the highest satisfaction as the optimal picture. frame.

Optionally, in another implementation manner, step S77 may include: comparing a plurality of video picture frames in the video file with the reference picture, and determining a video picture frame with the highest similarity with the reference picture as the optimal picture frame. .

Optionally, as shown in FIG. 8, the shooting control method may further include:

S79: The best picture frame is intercepted and saved as a photo.

In some embodiments, the electronic device includes a memory in which a plurality of albums are created, and “the best picture frame is truncated to be saved as a photo” to store the best picture frame in a photo/photo format in an album. , for example, stored in a camera album.

Please refer to FIG. 9 , which is a flowchart of a shooting control method in a ninth embodiment of the present application. As shown in FIG. 9, in the ninth embodiment, the photographing control method may include the following steps:

S81: Acquire a shooting preview screen.

S83: analyzing the shooting preview screen by using a preset model to determine whether the shooting condition is currently satisfied and determining a shooting parameter for shooting

S85: When it is determined that the shooting condition is currently satisfied, the shooting operation is performed according to the shooting parameter control.

The steps S51 to S55 in FIG. 6 and the steps S51 to S55 in FIG. 6 respectively correspond to the flowcharts in the other embodiments corresponding to FIG. 7. For specific implementation, refer to steps S51 to S55 in FIG. 6 and other embodiments. A description of the relevant steps in .

S87: Acquire the user's satisfaction feedback information about the automatic shooting.

Optionally, in an implementation manner, after the automatic photographing is completed, the user may be prompted to perform satisfaction evaluation on the automatic photographing by generating prompt information, for example, generating a prompt box including “satisfactory” and “unsatisfactory” options. For the user to select, and according to the user's choice, the satisfaction feedback information of the automatic photographing is obtained.

Optionally, in another embodiment, the user's satisfaction with the automatic shooting is obtained by detecting the user's operation on the photo or video obtained by the automatic shooting. For example, if it is detected that the user deletes the photo or video obtained by the automatic shooting, it is determined that the user is not satisfied with the automatic shooting, and the satisfaction feedback information that is unsatisfactory is obtained. For example, if it is detected that the user has set a photo or video obtained by the automatic shooting to a favorite or favorite type setting operation or a sharing operation, it is determined that the user is satisfied with the automatic shooting, and obtains I got feedback on satisfaction with satisfaction.

S89: Output the satisfaction feedback information of the user to the current automatic shooting to the currently used model, so that the currently used model uses the satisfaction feedback information for optimal training.

Therefore, in the present application, by collecting user satisfaction feedback information for automatic shooting, the training of the model can be optimized, and the model is continuously optimized, so that the automatic shooting in subsequent use can be more accurate.

Among them, the currently used model may be a model that has been confirmed by training, or a model that has not been trained yet. When it is confirmed that the training is completed, the model can be further optimized. When the model is not yet trained, the training can be better achieved.

As described above, the preset model in any of the embodiments 1 to 9 may also be an untrained model, and the automatic shooting is performed according to the model after the user initiates the automatic shooting function or the model is automatically started. And optimize and train the current model based on the feedback feedback from the user feedback.

In some embodiments, when the preset model is an untrained model, the untrained model automatically acquires a picture each time the user performs shooting, and performs training as a positive sample, or further acquires shooting parameters at the time of shooting. Training together as a positive sample, or sampling the frame frame when the user does not manually control the shooting as a reverse sample by using a preset rule, and gradually optimizing the preset model until the number of training reaches a preset number of times or satisfaction of subsequent user feedback If the degree of satisfaction is greater than the preset ratio, the training is completed. In this way, since the user himself trains the model without using another person's model, personalization can be better achieved.

Please refer to FIG. 10 , which is a block diagram showing a schematic partial structure of an electronic device 100 according to an embodiment of the present application. As shown in FIG. 10, the electronic device 100 includes a processor 10, a memory 20, and a camera 30. The camera 30 includes at least a rear camera 31 and a front camera 32. The rear camera 31 is used to capture an image behind the electronic device 100, and can be used for a user to take a shooting operation such as a person. The front camera 32 is used to capture an image in front of the electronic device 100, and can be used to perform a self-photographing and the like.

In some embodiments, the models in FIGS. 1-9 may be programs such as specific algorithm functions running in processor 10, such as neural network algorithm functions, image processing algorithm functions, and the like. In other embodiments, the electronic device 100 may further include a model processor that is independent of the processor 10. The models in FIGS. 1-9 are in the operation and model processors, and the processor 10 may generate corresponding instructions as needed. The trigger model processor runs the corresponding model, and the output result of the model is output to the processor 10 through the model processor for use by the processor 10, and control such as a shooting operation is performed.

Program instructions are stored in the memory 20.

The processor 10 is configured to call a program instruction stored in the memory 20 to execute the photographing control method in any of the embodiments shown in FIGS.

For example, the processor 10 is configured to call a program instruction stored in the memory 20 to execute the following shooting control method:

The shooting preview screen is acquired by the camera 30; the shooting preview screen is analyzed by using a preset model to obtain shooting parameters for shooting.

In some embodiments, the operation of acquiring the shooting preview screen is performed by the camera in response to the operation of turning on the camera, that is, the shooting preview screen is acquired by the camera.

In some embodiments, the preset model may be a trained model or an untrained model.

Optionally, in other embodiments, the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes the trained target object feature model, and the preset preview model is used to analyze the captured preview image. The shooting parameters are obtained for shooting, including: using image recognition technology to analyze the target object in the shooting preview image, generating a corresponding target object feature vector; and analyzing according to the target object feature model and the target object feature vector corresponding to the shooting preview image. Results; the shooting parameters are determined for the shooting based on the analysis results.

Optionally, in an implementation manner, the analysis result is obtained according to the target object feature model and the target object feature vector corresponding to the captured preview image, including: the target object feature model corresponding to the trained target object feature model and the captured preview image The analysis result of the target object feature corresponding to the shooting preview screen is calculated.

In the present application, the target object may be a hand, a face, a specific scene, etc.; the target object feature model includes a gesture feature model, an expression feature model, and a scene feature model, etc., and the analyzed target object feature vector may include a gesture. Feature vectors, emoticon feature vectors, and police feature vectors.

Therefore, in the present application, by determining the current shooting parameters by analyzing the shooting preview screen, the shooting parameters can be determined in time according to the shooting preview screen, so that the current exciting moment can be captured in time with high shooting quality according to the shooting parameters when shooting is required.

The processor 10 can be a microcontroller, a microprocessor, a single chip microcomputer, a digital signal processor, or the like.

The memory 20 can be any storage device that can store information such as a memory card, a solid state memory, a micro hard disk, an optical disk, or the like.

As shown in FIG. 10, the electronic device 100 further includes an input unit 40 and an output unit 50. The input unit 40 may include a touch panel, a mouse, a microphone, a physical button including a power key, a volume key, and the like. The output unit 50 can include a display screen, a speaker, and the like. In some embodiments, the touch panel of the input unit 40 and the display screen of the output unit 50 are integrated to form a touch screen while providing the functionality of touch input and display output.

The electronic device 100 can be a portable electronic device having a camera 30, such as a mobile phone, a tablet computer, or a notebook computer, and can also be a camera device such as a camera or a video camera.

In some embodiments, the present application further provides a computer readable storage medium, where a plurality of program instructions are stored in the computer readable storage medium, and the program instructions are executed by the main processing unit 20, and executed as shown in FIG. All or part of the steps in any of the shooting control methods. In some embodiments, the computer storage medium is the memory 20, and may be any storage device that can store information such as a memory card, a solid state memory, a micro hard disk, an optical disk, or the like.

The photographing control method and the electronic device 100 of the present application can automatically determine whether the photographing condition is satisfied according to the photographing preview screen, and perform photographing when the photographing condition is satisfied, and can capture the highlight moment including the content corresponding to the current photographing preview screen in time.

Although the present invention has been described herein in connection with the embodiments of the present invention, those skilled in the art can understand and implement the disclosure by the drawings, the disclosure, and the appended claims. Other variations of the embodiments. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill several of the functions recited in the claims. Certain measures are recited in mutually different dependent claims, but this does not mean that the measures are not combined to produce a good effect.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, apparatus (device), or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code. The computer program is stored/distributed in a suitable medium, provided with other hardware or as part of the hardware, or in other distributed forms, such as over the Internet or other wired or wireless telecommunication systems.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of the methods, apparatus, and computer program products of the embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The above disclosure is only an embodiment of the present application, and of course, the scope of the application should not be limited thereto, and those skilled in the art can understand all or part of the process of implementing the above embodiments, and according to the claims of the present application. The equivalent change is still within the scope of the application.

Claims

A shooting control method, characterized in that the shooting control method comprises:

Get a preview of the shot;

The shooting preview screen is analyzed using a preset model to obtain shooting parameters for shooting.
The photographing control method according to claim 1, wherein the preset model is a trained neural network model, and the photographing preview image is analyzed by using a preset model to obtain shooting parameters for photographing. ,include:

All the pixels of the preview image are taken as inputs, and the shooting parameters are output by the neural network model for shooting.
The photographing control method according to claim 1, wherein the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes a trained target object feature model, and a preset is adopted. The model analyzes the shooting preview screen to obtain shooting parameters for shooting, including:

Using the image recognition technology to analyze the target object in the preview image to generate a corresponding target object feature vector;

Obtaining an analysis result according to the trained target object feature model and the target object feature vector corresponding to the captured preview image;

The shooting parameters are determined for the shooting based on the analysis results.
The photographing control method according to claim 3, wherein the obtaining the analysis result according to the target object feature model and the target object feature vector corresponding to the shot preview screen comprises: passing the trained target object feature model The analysis result of the target object feature corresponding to the captured preview screen is calculated by the target object feature vector corresponding to the captured preview screen;

Determining the shooting parameters for shooting according to the analysis result, including:

The shooting parameters corresponding to the obtained target object features are determined according to the correspondence between the preset target object features and the shooting parameters.
[Correct according to Rule 26 17.07.2018]
The photographing control method according to claim 1, wherein the preset model is a trained image processing algorithm model, and the trained image processing algorithm model includes a trained target object feature model, and the adopting The preset model analyzes the shooting preview image to obtain shooting parameters for shooting, including: using a target object feature vector corresponding to the shooting preview image as input information of the trained target object feature model, by using the The trained target object feature model derives shooting parameters for shooting.
The photographing control method according to any one of claims 3-5, wherein the target object is a hand, the target object feature model is a gesture feature model, and the target object feature vector is a gesture feature vector.
The photographing control method according to claim 1, wherein the photographing control screen is acquired, the photographing control method further comprising:

The shooting preview screen is analyzed by using a preset model to determine whether the shooting condition is currently satisfied;

After the shooting preview image is analyzed by using the preset model to obtain the shooting parameters, the shooting control method further includes:

When it is determined that the shooting condition is satisfied, shooting is performed according to the shooting parameters.
The photographing control method according to claim 7, wherein the analyzing the photographing preview screen by using a preset model to determine whether the photographing condition is currently satisfied, further comprising:

The captured preview image is analyzed by the trained neural network model, and the analysis result of satisfaction is obtained;

When it is determined that the satisfaction exceeds the satisfaction preset threshold, it is determined that the shooting condition is currently satisfied.
The photographing control method according to claim 7, wherein the photographing preview screen is analyzed by using a preset model to determine whether the photographing condition is currently satisfied, and further includes:

The trained image processing algorithm model is used to compare the shooting preview image with the reference image, and analyze the analysis result of the similarity between the shooting preview image and the reference image;

When it is determined that the similarity exceeds the similarity preset threshold, it is determined that the shooting condition is currently satisfied.
The photographing control method according to claim 7, wherein the analyzing the photographing preview screen by using a preset model to determine whether the photographing condition is currently met comprises:

Using the image recognition technology to analyze the target object in the preview image to generate a corresponding target object feature vector;

Using the target object feature vector as the input information of the trained image processing algorithm model, and obtaining an analysis result including the identification information that identifies whether the shooting condition is currently satisfied;

When the identification information identifies that the shooting condition is currently satisfied, it is determined that the shooting condition is currently satisfied.
The photographing control method according to any one of claims 7 to 10, wherein the method further comprises:

Obtaining satisfaction feedback information that the user gives feedback on the photos or videos obtained by performing the shooting operation;

And outputting the satisfaction feedback information to the preset model, so that the preset model performs optimization training by using the satisfaction feedback information.
An electronic device, the electronic device comprising:

camera;

a memory for storing program instructions;

a processor for invoking the program instruction to perform the photographing control method according to any one of claims 1-11.
A computer readable storage medium, wherein the computer readable storage medium stores program instructions for performing a shooting control according to any one of claims 1 to 11 after being invoked by a computer method.