WO2020038087A1

WO2020038087A1 - Method and apparatus for photographic control in super night scene mode and electronic device

Info

Publication number: WO2020038087A1
Application number: PCT/CN2019/091541
Authority: WO
Inventors: 王宇鹭
Original assignee: Oppo广东移动通信有限公司
Priority date: 2018-08-22
Filing date: 2019-06-17
Publication date: 2020-02-27
Also published as: CN109068058B; CN109068058A

Abstract

Disclosed are a method and apparatus for photographic control in a super night scene mode, and an electronic device. The method comprises: enabling a photographic scene detection function and acquiring a scene detection result corresponding to the current photographic scene; when the scene detection result is a night scene or a portrait night scene, starting a super night scene mode; in the super night scene mode, determining whether the brightness value of a preview image corresponding to the current photographic scene is greater than a preset threshold; if the brightness value is greater than the preset threshold, further determining whether jitter occurs; and if jitter does not occur, using a tripod photographic mode for photographing in a super night scene mode. By means of the method, the dynamic range and overall brightness for image photography in a night scene photographic mode can be improved, and the noise in image photography is effectively suppressed, thus improving the quality of an image photographed in a night scene and improving the user experience.

Description

Shooting control method, device and electronic equipment in super night scene mode

Cross-reference to related applications

This disclosure claims the priority of China Patent Application No. “201810962789.7”, submitted by OPPO Guangdong Mobile Communication Co., Ltd. on August 22, 2018, with the application name “Shot Control Method, Device and Electronic Equipment in Super Night Scene Mode”.

Technical field

The present disclosure relates to the field of imaging technology, and in particular, to a shooting control method, device, and electronic device in a super night scene mode.

Background technique

With the continuous development of imaging technology and terminal technology, more and more users use electronic devices to take pictures. In night scenes, because the brightness value of the surrounding environment is low, if the electronic device cannot correctly recognize the current shooting scene, it may result in poor imaging quality. Therefore, how to identify the night scene and adopt the corresponding shooting mode is very important.

Public content

The present disclosure provides a shooting control method, device, and electronic device in a super night scene mode, which are used to realize the improvement of the dynamic range and the overall brightness of a captured image in the night scene shooting mode, and effectively suppress the noise in the captured image and improve the night scene shooting. The quality of the image improves the user experience to solve the technical problem that the shooting parameters corresponding to the night scene mode in the prior art cannot be changed with different shooting scenes, and in some scenes, the quality of the captured images may be poor.

An embodiment of one aspect of the present disclosure provides a shooting control method in a super night scene mode, including:

Enable the shooting scene detection function and obtain the scene detection result corresponding to the current shooting scene;

When the scene detection result is a night scene or a portrait night scene, start a super night scene mode;

Determining whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold in the super night scene mode;

If the brightness value is greater than the preset threshold, further determining whether jitter is generated;

If no shake is generated, shooting is performed in the super night scene mode by using a tripod shooting mode.

According to the shooting control method in the super night scene mode of the embodiment of the present disclosure, by turning on the shooting scene detection function and obtaining the scene detection result corresponding to the current shooting scene, when the scene detection result is a night scene or a portrait night scene scene, start the super night scene mode, In the super night scene mode, determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold. If it is, then further determine whether shake occurs. If no shake occurs, use a tripod shooting mode to shoot in the super night scene mode. . In the present disclosure, when the current shooting scene is a night scene or a portrait night scene, according to the brightness value of the preview image and whether the imaging device shakes, it can be determined to shoot in the corresponding shooting mode in the shooting scene, which can improve the night scene shooting mode. The dynamic range and overall brightness of the captured image, and the noise in the captured image is effectively suppressed, the quality of the night scene captured image is improved, and the user experience is improved.

An embodiment of another aspect of the present disclosure provides a shooting control device in a super night scene mode, including:

An acquisition module for enabling a shooting scene detection function and obtaining a scene detection result corresponding to a current shooting scene;

A startup module, configured to start a super night scene mode when the scene detection result is a night scene or a portrait night scene;

A first determining module, configured to determine whether a brightness value of a preview image corresponding to the current shooting scene is greater than a preset threshold in the super night scene mode;

A second determining module, configured to further determine whether jitter occurs if the brightness value is greater than the preset threshold;

A photographing module is configured to perform photographing in the super night scene mode by using a tripod photographing mode if no shake is generated.

The shooting control device in the super night scene mode of the embodiment of the present disclosure starts the shooting scene detection function and obtains the scene detection result corresponding to the current shooting scene. When the scene detection result is a night scene or a portrait night scene scene, the super night scene mode is activated, In the super night scene mode, determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold. If it is, then further determine whether shake occurs. If no shake occurs, use a tripod shooting mode to shoot in the super night scene mode. . In the present disclosure, when the current shooting scene is a night scene or a portrait night scene, according to the brightness value of the preview image and whether the imaging device shakes, it can be determined to shoot in the corresponding shooting mode in the shooting scene, which can improve the night scene shooting mode. The dynamic range and overall brightness of the captured image, and the noise in the captured image is effectively suppressed, the quality of the night scene captured image is improved, and the user experience is improved.

An embodiment of yet another aspect of the present disclosure provides an electronic device including a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor configured to execute the foregoing implementation of the present application. The proposed shooting control method in the super night scene mode.

An embodiment of yet another aspect of the present disclosure provides a non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements shooting in a super night scene mode as proposed by the foregoing embodiment of the present application. Control Method.

Additional aspects and advantages of the present disclosure will be given in part in the following description, part of which will become apparent from the following description, or be learned through the practice of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions in the embodiments of the present disclosure more clearly, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present disclosure. Those of ordinary skill in the art can also obtain other drawings according to these drawings without paying creative labor.

FIG. 1 is a schematic flowchart of a shooting control method in a super night scene mode according to Embodiment 1 of the present disclosure; FIG.

2 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 2 of the present disclosure;

3 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 3 of the present disclosure;

4 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 4 of the present disclosure;

5 is a schematic structural diagram of a shooting control device in a super night scene mode provided in Embodiment 5 of the present disclosure;

6 is a schematic block diagram of an electronic device according to some embodiments of the present disclosure;

FIG. 7 is a schematic block diagram of an image processing circuit according to some embodiments of the present disclosure.

detailed description

Hereinafter, embodiments of the present disclosure will be described in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary, and are intended to explain the present disclosure, and should not be construed as limiting the present disclosure.

The present disclosure is mainly directed to the technical problem of poor shooting image quality in the prior art, and proposes a shooting control method in a super night scene mode.

The following describes a shooting control method, an apparatus, and an electronic device in a super night scene mode according to an embodiment of the present disclosure with reference to the drawings.

FIG. 1 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 1 of the present disclosure.

As shown in FIG. 1, the shooting control method in the super night scene mode may include the following steps:

Step 101: Enable a shooting scene detection function, and obtain a scene detection result corresponding to a current shooting scene.

In the embodiment of the present disclosure, when a function mutually exclusive with the night scene mode is turned off, a shooting scene detection function may be turned on. Specifically, a preview image corresponding to the current shooting scene can be obtained through the imaging device, and the scene detection result corresponding to the current shooting scene is determined according to the screen content of the preview image. The obtained scene detection result can be that the current shooting scene is a night scene, or the current shooting scene The scene is a portrait night scene, or the current shooting scene is a scene that is not a night scene and a scene that is not a portrait night scene. The portrait night scene may specifically refer to a group night scene.

Optionally, it may be determined whether the current shooting scene is a night scene according to the screen content of the preview image and / or the environmental brightness value of each area of the preview image. For example, when the picture content of the preview image includes a night sky or a night scene light source, etc., it can be determined that the current shooting scene is a night scene scene, or when the ambient brightness value in each area of the preview image matches the brightness distribution characteristics of the image in the night scene environment, Make sure the current shooting scene is a night scene.

Optionally, it may be determined whether the current shooting scene is a portrait night scene according to the screen content of the preview image and the environmental brightness value of each area of the preview image. For example, based on face recognition technology, it is possible to detect whether there are at least two faces in the screen content of the preview image. When there are at least two faces, it may further determine whether the current shooting scene is based on the ambient brightness values of each area of the preview image. It is a portrait night scene. For example, when the ambient brightness value is low, it indicates that the shooting environment is dark. At this time, it can be determined that the current shooting scene is a portrait night scene scene, or the ambient brightness value in each area except the portrait in the preview image. When the brightness distribution characteristics of the image in the night scene environment are met, it can be determined that the current shooting scene is a portrait night scene scene. Alternatively, it is also possible to extract each imaging object in the preview image based on the edge feature detection technology, so that it can be determined whether the current shooting scene is a portrait night scene according to the environmental brightness value of each imaging object and each area of the preview image. When it is determined that there are at least two persons in the extracted imaging object, the current shooting scene may be further determined as a night scene of a portrait according to the environmental brightness values of each area of the preview image. Among them, commonly used face recognition algorithms may include: feature-based recognition algorithms (feature-based recognition algorithms), recognition algorithms based on entire face images (appearance-based recognition algorithms), and template-based recognition algorithms ( Template-based recognition algorithms, recognition algorithms using neural networks (Recognition algorithms, neural networks), and so on.

Step 102: When the scene detection result is a night scene or a portrait night scene, start a super night scene mode.

As a possible implementation manner, when a scene detection result is a night scene or a portrait night scene, a super night scene mode may be automatically activated, thereby eliminating the need for a user to operate and improving the user ’s experience in shooting night scenes.

As another possible implementation manner, when the scene detection result is a night scene or a portrait night scene, a prompt may also be displayed on the display interface of the electronic device, and the user initiates the super night scene mode, thereby guiding the user to shoot at night , Use the super night scene shooting function to increase user engagement and improve user experience.

It should be noted that when the current shooting scene is different, the shooting parameters corresponding to the super night scene mode may be different. For example, for a night scene scene, the shooting parameters corresponding to the super night scene mode may be different from the portrait night scene scene. Therefore, it is possible to set shooting parameters with better shooting effects for different shooting scenes, which can improve the imaging quality and improve the user's shooting experience.

Step 103: In the super night scene mode, determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold.

In the embodiment of the present disclosure, the preset threshold may be preset by a built-in program of the electronic device, or the preset threshold may be set by a user, which is not limited. The preset threshold may be preset according to a night scene, for example, the preset threshold may be 410.

In the embodiment of the present disclosure, the brightness value of the preset image corresponding to the current shooting scene can be obtained by metering the center area of the preview image, and the brightness value is marked as Lux_index. It should be noted that the brightness value Lux_index of the preset image and the current shooting scene The environment brightness value of the camera is inversely proportional. When the environment brightness value of the current shooting scene is higher, the preset image brightness value Lux_index is lower, and when the environment brightness value of the current shooting scene is lower, the preset image brightness value Lux_index is lower. The higher.

Optionally, after the brightness value of the preview image is obtained through metering in the center area of the preview image, the brightness value may be compared with a preset threshold value. When the brightness value is greater than the preset threshold value, it indicates that the current environment brightness is low. At this time, Step 104 may be triggered.

In step 104, if the brightness value is greater than a preset threshold, it is further determined whether jitter is generated.

In the embodiment of the present disclosure, when the brightness value is greater than a preset threshold, it can be determined whether the imaging device shakes. Optionally, the displacement information provided by the imaging device can be used to collect the displacement information of the imaging device during shooting, and then determine whether the imaging device generates a shake based on the obtained displacement information.

For example, the current gyro sensor information of the electronic device can be used to determine whether the imaging device shakes and the current degree of shake of the imaging device.

Among them, the gyroscope is also called angular velocity sensor, which can measure the rotational angular velocity when the physical quantity is deflected and tilted. In the imaging equipment, the gyroscope can measure the movements of rotation and deflection very well, so that it can accurately analyze and judge the actual movement of the user. The gyroscope information (gyro information) of the electronic device may include the motion information of the imaging device in three dimensions in the three-dimensional space, and the three dimensions of the three-dimensional space may be expressed as the three directions of the X-axis, Y-axis, and Z-axis, respectively. , X-axis, Y-axis, and Z-axis are perpendicular to each other.

Therefore, in the embodiments of the present disclosure, it can be determined whether the imaging device shakes and the current degree of shake of the imaging device according to the current gyro information of the electronic device. The greater the absolute value of the gyro movement of the electronic device in the three directions, the greater the degree of jitter of the imaging device. Specifically, the absolute value threshold of the gyro motion in the three directions can be preset, and the relationship between the absolute value of the currently acquired gyro motion in the three directions and the preset threshold is used to determine the imaging device's The current degree of jitter.

For example, suppose the preset thresholds are the first threshold A, the second threshold B, and the third threshold C, and A <B <C. The sum of the absolute values of the gyro motion in the three directions currently obtained is S . If S <A, then determine the current jitter of the imaging device as “no jitter”; if A <S <B, you can determine the current jitter of the imaging device as “slight jitter”; if B <S <C, you can It is determined that the current jitter level of the imaging device is "small jitter"; if S> C, it can be determined that the current jitter level of the imaging device is "large jitter".

It should be noted that the above examples are merely exemplary and cannot be regarded as limiting the present disclosure. In actual use, the number of thresholds and specific values of each threshold can be preset according to actual needs, and the mapping relationship between the gyro information and the degree of jitter of the imaging device can be preset according to the relationship between the gyro information and each threshold.

In step 105, if jitter is not generated, shooting is performed in a super night scene mode by using a tripod shooting mode.

In the embodiment of the present disclosure, when the imaging device does not shake, it indicates that the current imaging device is in a stable state to capture an image, and therefore, a tripod shooting mode can be used for shooting in a super night scene mode. In the tripod shooting mode, the shooting time is longer, which can improve the dynamic range and overall brightness of the captured image, and effectively suppress the noise in the captured image, improve the quality of the night scene captured image, and improve the user experience.

According to the shooting control method in the super night scene mode of the embodiment of the present disclosure, by turning on the shooting scene detection function and obtaining the scene detection result corresponding to the current shooting scene, when the scene detection result is a night scene or portrait night scene scene, start the super night scene mode In the super night scene mode, determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold. If it is, then further determine whether shake occurs. If no shake occurs, use a tripod shooting mode to shoot in the super night scene mode. . In the present disclosure, when the current shooting scene is a night scene or a portrait night scene, according to the brightness value of the preview image and whether the imaging device shakes, it can be determined to shoot in the corresponding shooting mode in the shooting scene, which can improve the night scene shooting mode. The dynamic range and overall brightness of the captured image, and the noise in the captured image is effectively suppressed, the quality of the night scene captured image is improved, and the user experience is improved.

In order to clearly explain the foregoing embodiment, the present disclosure provides another shooting control method in a super night scene mode. FIG. 2 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 2 of the present disclosure.

As shown in FIG. 2, the shooting control method in the super night scene mode may include the following steps:

Step 201: Turn on a shooting scene detection function, and obtain a scene detection result corresponding to a current shooting scene.

Step 202: When the scene detection result is a night scene or a portrait night scene, start a super night scene mode.

Step 203: In the super night scene mode, determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold. If yes, go to step 205; if not, go to step 204.

In step 204, shooting is performed in an HDR shooting mode.

In the embodiment of the present disclosure, when the brightness value of the preview image corresponding to the current shooting scene is less than or equal to a preset threshold, it indicates that the brightness of the current shooting environment is bright. At this time, the HDR shooting mode can be used for shooting. Therefore, it is possible to avoid turning on the night scene mode during the day, and to improve the imaging quality and imaging effect.

Specifically, the long exposure time can be used to control the imaging device to acquire a long exposure image, the medium exposure time can be used to control the imaging device to acquire a medium exposure image, and the short exposure time can be used to control the imaging device to acquire a short exposure image, Then, the long exposure image, the middle exposure image, and the short exposure image are combined to obtain a target image.

In step 205, it is determined whether jitter is generated. If yes, go to step 207, and if no, go to step 206.

Step 206: Use a tripod shooting mode to shoot in the super night scene mode.

Optionally, the number of image frames to be acquired in the tripod shooting mode and the exposure compensation value corresponding to the images to be acquired in each frame can be set in advance. For example, the number of image frames to be acquired in the tripod shooting mode may be 17 frames, and the range of EV values of the exposure compensation values corresponding to the images to be acquired in each frame may be: -6 to +2.

It should be noted that EV + 1 exposure compensation refers to an increase of one exposure relative to the exposure amount corresponding to the metering data of the imaging device, that is, the actual exposure amount is twice the exposure amount corresponding to the metering data. EV-1 refers to Reduce the exposure by one stop, that is, the exposure amount is 0.5 times the exposure amount corresponding to the metering data.

In step 207, it is determined whether there is a region of interest in the face in the preview image. If yes, step 208 is performed, and if no, step 209 is performed.

In the embodiment of the present disclosure, when the imaging device shakes, it indicates that the current imaging device is not in a stable state to capture images. At this time, it is not suitable to use a relatively stable tripod shooting mode. It can be further judged whether a region of interest in the face exists in the preview image. Optionally, it can be determined whether a region of interest in the face exists in the preview image based on the face recognition technology. When the region of interest of the face exists in the preview image, step 208 may be triggered, and when the region of interest of the face does not exist in the preview image, step 209 may be triggered.

Step 208: Use the portrait shooting mode to shoot in the super night scene mode.

In the embodiment of the present disclosure, when the imaging device shakes and a region of interest of a human face exists in the preview image, the portrait shooting mode can be used to shoot in the super night scene mode. In the portrait shooting mode, the shooting time is short, and targeted image processing can be performed for portrait night scenes to improve the quality of night scene shot images.

Optionally, the number of image frames to be acquired in the portrait shooting mode and the exposure compensation value corresponding to the images to be acquired in each frame may be set in advance. For example, the number of image frames to be acquired in the portrait shooting mode may be 7 frames, and the range of EV values of the exposure compensation values corresponding to the images to be acquired in each frame may be: -6 to +0.

It should be noted that when the degree of jitter of the imaging device is different, the shooting parameters corresponding to the portrait shooting mode may be different. For example, when the degree of jitter of the imaging device is "no jitter", the range of EV values of the exposure compensation values corresponding to the images to be acquired for each frame is preset to -6 to +0, and the difference between adjacent EV values Is 0.5; the jitter level of the imaging device is "slightly jittered", the EV value range of the exposure compensation value corresponding to each frame of the image to be acquired is preset to -5 to -1, and the difference between adjacent EV values is 1, wait.

Step 209: Use the handheld shooting mode to shoot in the super night scene mode.

In the embodiment of the present disclosure, when the imaging device shakes and there is no region of interest in the face in the preview image, the handheld shooting mode can be used to shoot in the super night scene mode. In the handheld shooting mode, the shooting time is short, which can improve the dynamic range and overall brightness of the captured image, and effectively suppress the noise in the captured image, improve the quality of the night scene captured image, and improve the user experience.

Optionally, the number of image frames to be acquired and the exposure compensation value corresponding to the images to be acquired in each frame can be set in advance. For example, the number of image frames to be acquired in the handheld shooting mode may be 7 frames, and the EV value range of the exposure compensation value corresponding to the image to be acquired in each frame may be: -6 to +1.

It should be noted that when the shaking degree of the imaging device is different, the shooting parameters corresponding to the handheld shooting mode may be different. For example, when the degree of jitter of the imaging device is "no jitter", the range of EV values of the exposure compensation values corresponding to the images to be acquired for each frame is preset to -6 to +1, and the difference between adjacent EV values Is 0.5; the jitter level of the imaging device is "slight jitter", the EV value range of the exposure compensation value corresponding to each frame of the image to be acquired is preset to -5 to +0, and the difference between adjacent EV values is 1, wait.

According to the shooting control method in the super night scene mode of the embodiment of the present disclosure, by determining the shooting mode corresponding to the shooting scene according to the brightness value of the preview image and whether the imaging device shakes, the shooting of the image in the night scene shooting mode can be improved. Dynamic range and overall brightness, and effectively suppress the noise in the captured image, improve the quality of the night scene captured image, and improve the user experience.

In the prior art, the current shooting scene is determined by the ISO value and exposure time of the captured image. Specifically, by setting the exposure time to be fixed, when the ISO value is larger, it indicates that the current shooting scene is darker. At this time, the current shooting scene can be determined. The scene is in night mode.

In this way, for some more complicated scenes, it is easy to cause the problem of low accuracy of the recognition result. For example, when a neon light, a large screen, or the direct light of the light causes the lens to flush, it is easy to cause misrecognition.

In the embodiment of the present disclosure, in order to improve the accuracy of the scene detection result, the current shooting scene may be identified based on a machine learning manner. The above process is described in detail below with reference to FIG. 2.

FIG. 3 is a schematic flowchart of a shooting control method in a super night scene mode provided in Embodiment 3 of the present disclosure.

As shown in FIG. 3, step 101 may specifically include the following sub-steps:

Step 301: Obtain a preview image corresponding to the current shooting scene, and extract image features of the preview image.

In the embodiment of the present disclosure, a preview image corresponding to a current shooting scene may be obtained through an imaging device, and then image features of the preview image may be extracted based on technologies such as image feature extraction technology and key point recognition.

Step 302: Input image features into a pre-established scene recognition model to identify a scene detection result corresponding to the current shooting scene.

In the embodiment of the present disclosure, the scene recognition model is a trained model.

As a possible implementation manner, sample images corresponding to different shooting scenes can be collected in advance, and then the shooting scenes of the sample images are labeled. Using the labeled sample images, the scene recognition model is trained to obtain a trained scene. Identify the model. Therefore, after obtaining the image features of the preview image, the image features of the preview image can be input to the trained scene recognition model, and the scene detection result corresponding to the current shooting scene can be obtained.

As another possible implementation manner, sample scene information can be collected, and the scene sample information can be characterized and defined, and then the feature description and the defined scene sample information can be input to a deep neural network for training, and scene recognition can be generated. model. Therefore, after obtaining the image features of the preview image, the image features of the preview image can be input to the trained scene recognition model, and the scene detection result corresponding to the current shooting scene can be obtained.

The shooting control method in the super night scene mode according to the embodiment of the present disclosure can improve the accuracy of the scene detection result by determining the current shooting scene based on the method of machine learning.

As a possible implementation manner, referring to FIG. 4, after shooting in the super night scene mode, the shooting control method in the super night scene mode may further include the following steps:

In step 401, multiple frames of RAW images are captured and acquired.

In the embodiment of the present disclosure, multiple frames of original RAW images can be acquired by an image sensor.

Step 402: Use the image processor ISP to process multiple frames of RAW images to generate a captured image.

In the embodiment of the present disclosure, after obtaining multiple frames of RAW images, an image processor may be used to process the multiple frames of RAW images. For example, in order to improve the quality of captured images, multiple frames of RAW images may be processed for alignment processing, Noise reduction processing, etc., and then based on a preset weight value corresponding to each frame of RAW image, synthesis processing is performed on the processed multiple frames of RAW image to obtain a captured image.

In order to implement the above embodiments, the present disclosure also proposes a shooting control device in a super night scene mode.

FIG. 5 is a schematic structural diagram of a shooting control device in a super night scene mode provided in Embodiment 5 of the present disclosure.

As shown in FIG. 5, the shooting control device 100 in the super night scene mode may include: an acquisition module 101, a startup module 102, a first determination module 103, a second determination module 104, and a photography module 105.

The obtaining module 101 is configured to enable a shooting scene detection function and obtain a scene detection result corresponding to a current shooting scene.

As a possible implementation manner, the obtaining module 101 is specifically configured to: obtain a preview image corresponding to the current shooting scene, and extract image features of the preview image; input the image features into a pre-established scene recognition model to identify the current shooting Scene detection result corresponding to the scene.

A starting module 102 is configured to start a super night scene mode when a scene detection result is a night scene or a portrait night scene.

The first determining module 103 is configured to determine whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold in the super night scene mode.

As a possible implementation manner, the brightness value of the preview image corresponding to the current shooting scene is inversely proportional to the environment brightness value of the current shooting scene.

The second determination module 104 is configured to further determine whether jitter is generated if the brightness value is greater than a preset threshold.

The shooting module 105 is configured to use a tripod shooting mode to shoot in a super night scene mode if no shake occurs.

As a possible implementation manner, the shooting module 105 is further configured to: if the brightness value is less than a preset threshold, use the HDR shooting mode to shoot in the super night scene mode.

As another possible implementation manner, the shooting module 105 is further configured to: if there is no region of interest of the human face, use the handheld shooting mode to shoot in the super night scene mode.

As a possible implementation manner, the shooting control apparatus 100 in the super night scene mode may further include:

A third determining module is configured to further determine whether a region of interest of a human face exists in the preview image if jitter occurs.

The shooting module 105 is further configured to use a portrait shooting mode to shoot in a super night scene mode if there is an area of interest in the human face.

The first acquisition module is configured to collect scene sample information, and describe and define the scene sample information.

A first training module is configured to input feature description and defined scene sample information to a deep neural network for training, and generate a scene recognition model.

The second acquisition module is configured to acquire sample images corresponding to different shooting scenes.

The labeling module is used for labeling the shooting scene of the sample image.

The second training module is used to train the scene recognition model using the labeled sample images to obtain a trained scene recognition model.

An output module is configured to capture multiple frames of RAW images after shooting in the super night scene mode, and use the image processor ISP to process the multiple frames of RAW images to generate captured images.

It should be noted that the foregoing explanation of the embodiment of the method for shooting control in the super night scene mode is also applicable to the shooting control device 100 in the super night scene mode in this embodiment, and details are not described herein.

In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. Shooting control method in night scene mode.

Referring to FIG. 6, the present disclosure also provides another electronic device 200. The electronic device 200 includes a memory 50 and a processor 60. The memory 50 stores computer-readable instructions. When the computer-readable instructions are executed by the memory 50, the processor 60 is caused to execute the shooting control method in the super night scene mode according to any one of the foregoing embodiments.

FIG. 6 is a schematic diagram of the internal structure of the electronic device 200 in one embodiment. The electronic device 200 includes a processor 60, a memory 50 (for example, a non-volatile storage medium), an internal memory 82, a display screen 83, and an input device 84 connected through a system bus 81. The memory 50 of the electronic device 200 stores an operating system and computer-readable instructions. The computer-readable instructions can be executed by the processor 60 to implement a shooting control method in a super night scene mode according to an embodiment of the present disclosure. The processor 60 is used to provide computing and control capabilities to support the operation of the entire electronic device 200. The internal memory 50 of the electronic device 200 provides an environment for execution of computer-readable instructions in the memory 52. The display screen 83 of the electronic device 200 may be a liquid crystal display or an electronic ink display. The input device 84 may be a touch layer covered on the display screen 83, or may be a button, a trackball, or a touch button provided on the housing of the electronic device 200. Board, which can also be an external keyboard, trackpad, or mouse. The electronic device 200 may be a mobile phone, a tablet computer, a notebook computer, a personal digital assistant, or a wearable device (such as a smart bracelet, a smart watch, a smart helmet, a smart glasses), and the like. Those skilled in the art can understand that the structure shown in FIG. 6 is only a schematic diagram of a part of the structure related to the solution of the present disclosure, and does not constitute a limitation on the electronic device 200 to which the solution of the present disclosure is applied. 200 may include more or fewer components than shown in the figure, or some components may be combined, or have different component arrangements.

Referring to FIG. 7, the electronic device 200 according to the embodiment of the present disclosure includes an image processing circuit 90. The image processing circuit 90 may be implemented by using hardware and / or software components, including various types of defining an ISP (Image Signal Processing) pipeline Processing unit. FIG. 7 is a schematic diagram of an image processing circuit 90 in one embodiment. As shown in FIG. 7, for convenience of explanation, only various aspects of the image processing technology related to the embodiments of the present disclosure are shown.

As shown in FIG. 7, the image processing circuit 90 includes an ISP processor 91 (the ISP processor 91 may be the processor 60) and a control logic 92. The image data captured by the camera 93 is first processed by the ISP processor 91. The ISP processor 91 analyzes the image data to capture image statistical information that can be used to determine one or more control parameters of the camera 93. The camera 93 may include one or more lenses 932 and an image sensor 934. The image sensor 934 may include a color filter array (such as a Bayer filter). The image sensor 934 may obtain light intensity and wavelength information captured by each imaging pixel, and provide a set of raw image data that can be processed by the ISP processor 91. The sensor 94 (such as a gyroscope) may provide parameters (such as image stabilization parameters) of the acquired image processing to the ISP processor 91 based on the interface type of the sensor 94. The sensor 94 interface may be a SMIA (Standard Mobile Imaging Architecture) interface, other serial or parallel camera interfaces, or a combination of the foregoing interfaces.

In addition, the image sensor 934 may also send the original image data to the sensor 94. The sensor 94 may provide the original image data to the ISP processor 91 based on the interface type of the sensor 94, or the sensor 94 stores the original image data into the image memory 95.

The ISP processor 91 processes the original image data pixel by pixel in a variety of formats. For example, each image pixel may have a bit depth of 8, 10, 12, or 14 bits, and the ISP processor 91 may perform one or more image processing operations on the original image data and collect statistical information about the image data. The image processing operations may be performed with the same or different bit depth accuracy.

The ISP processor 91 may also receive image data from the image memory 95. For example, the sensor 94 interface sends the original image data to the image memory 95, and the original image data in the image memory 95 is then provided to the ISP processor 91 for processing. The image memory 95 may be an independent dedicated memory in the memory 50, a part of the memory 50, a storage device, or an electronic device, and may include a DMA (Direct Memory Access) feature.

When receiving raw image data from the image sensor 934 interface or from the sensor 94 interface or from the image memory 95, the ISP processor 91 may perform one or more image processing operations, such as time-domain filtering. The processed image data may be sent to the image memory 95 for further processing before being displayed. The ISP processor 91 receives processing data from the image memory 95, and performs processing on the processing data of the image data in the original domain and in the RGB and YCbCr color spaces. The image data processed by the ISP processor 91 may be output to a display 97 (the display 97 may include a display screen 83) for viewing by a user and / or further processing by a graphics engine or a GPU (Graphics Processing Unit). In addition, the output of the ISP processor 91 can also be sent to the image memory 95, and the display 97 can read image data from the image memory 95. In one embodiment, the image memory 95 may be configured to implement one or more frame buffers. In addition, the output of the ISP processor 91 may be sent to an encoder / decoder 96 to encode / decode image data. The encoded image data can be saved and decompressed before being displayed on the display 97 device. The encoder / decoder 96 may be implemented by a CPU or a GPU or a coprocessor.

The statistical data determined by the ISP processor 91 may be sent to the control logic unit 92. For example, the statistical data may include image sensor 934 statistical information such as auto exposure, auto white balance, auto focus, flicker detection, black level compensation, and lens 932 shading correction. The control logic 92 may include a processing element and / or a microcontroller that executes one or more routines (such as firmware). The one or more routines may determine the control parameters of the camera 93 and the ISP processor according to the received statistical data. 91 control parameters. For example, the control parameters of the camera 93 may include sensor 94 control parameters (such as gain, integration time for exposure control, anti-shake parameters, etc.), camera flash control parameters, lens 932 control parameters (such as focus distance for focusing or zooming), or these parameters The combination. The ISP control parameters may include gain levels and color correction matrices for automatic white balance and color adjustment (eg, during RGB processing), and lens 932 shading correction parameters.

The following are the steps of using the image processing technology in Figure 7 to implement the shooting control method in the super night scene mode:

In order to implement the above embodiments, the present disclosure also proposes a computer-readable storage medium on which a computer program is stored, which is characterized in that when the program is executed by a processor, the implementation in the super night scene mode according to the above embodiment is implemented Shooting control method.

In the description of this specification, the description with reference to the terms “one embodiment”, “some embodiments”, “examples”, “specific examples”, or “some examples” and the like means specific features described in conjunction with the embodiments or examples , Structure, material, or characteristic is included in at least one embodiment or example of the present disclosure. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Moreover, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples described in the present specification and features of the different embodiments or examples without conflicting one another.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "a plurality" is at least two, for example, two, three, etc., unless it is specifically and specifically defined otherwise.

Any process or method description in a flowchart or otherwise described herein can be understood as representing a module, fragment, or portion of code that includes one or more executable instructions for implementing steps of a custom logic function or process And, the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present disclosure belong.

Logic and / or steps represented in a flowchart or otherwise described herein, for example, a sequenced list of executable instructions that may be considered to implement a logical function, may be embodied in any computer-readable medium, For use by, or in combination with, an instruction execution system, device, or device (such as a computer-based system, a system that includes a processor, or another system that can fetch and execute instructions from an instruction execution system, device, or device) Or equipment. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connections (electronic devices) with one or more wirings, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable means if necessary Process to obtain the program electronically and then store it in computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it may be implemented using any one or a combination of the following techniques known in the art: Discrete logic circuits with logic gates for implementing logic functions on data signals Logic circuits, ASICs with suitable combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods in the foregoing embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium. Including one or a combination of steps of a method embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing module, or each unit may exist separately physically, or two or more units may be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

The aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present disclosure. Those skilled in the art can understand the above within the scope of the present disclosure. Embodiments are subject to change, modification, substitution, and modification.

Claims

A shooting control method in a super night scene mode, which includes:

Enable the shooting scene detection function and obtain the scene detection result corresponding to the current shooting scene;

When the scene detection result is a night scene or a portrait night scene, start a super night scene mode;

Determining whether the brightness value of the preview image corresponding to the current shooting scene is greater than a preset threshold in the super night scene mode;

If the brightness value is greater than the preset threshold, further determining whether jitter is generated;

If no shake is generated, shooting is performed in the super night scene mode by using a tripod shooting mode.
The method of claim 1, further comprising:

If the brightness value is less than the preset threshold, shooting is performed in an HDR shooting mode.
The method according to claim 1 or 2, further comprising:

If jitter occurs, further determining whether a region of interest of a face exists in the preview image;

If the region of interest of the human face exists, the portrait shooting mode is used to shoot in the super night scene mode.
The method according to claim 3, further comprising:

If the region of interest of the human face does not exist, shooting is performed in the super night scene mode by using a handheld shooting mode.
The method according to any one of claims 1-4, wherein enabling a shooting scene detection function and obtaining a scene detection result corresponding to a current shooting scene comprises:

Acquiring a preview image corresponding to the current shooting scene, and extracting image characteristics of the preview image;

The image features are input to a pre-established scene recognition model to identify a scene detection result corresponding to the current shooting scene.
The method according to claim 5, further comprising:

Collecting shooting scene sample information, and characterizing and defining the scene sample information;

The scene description information after the feature description and definition is input to a deep neural network for training, and the scene recognition model is generated.
The method according to claim 5, further comprising:

Collect sample images corresponding to different shooting scenes;

Marking the shooting scene of the sample image;

Using the labeled sample images, the scene recognition model is trained to obtain a trained scene recognition model.
The method according to any one of claims 1-7, wherein after shooting in the super night scene mode, further comprising:

Capture multiple frames of RAW images;

An image processor ISP is used to process the multi-frame RAW images to generate a captured image.
The method according to any one of claims 1 to 8, wherein a brightness value of a preview image corresponding to the current shooting scene is inversely proportional to an environment brightness value of the current shooting scene.
A shooting control device in a super night scene mode, which includes:

An acquisition module for enabling a shooting scene detection function and obtaining a scene detection result corresponding to a current shooting scene;

A startup module, configured to start a super night scene mode when the scene detection result is a night scene or a portrait night scene;

A first determining module, configured to determine whether a brightness value of a preview image corresponding to the current shooting scene is greater than a preset threshold in the super night scene mode;

A second determining module, configured to further determine whether jitter occurs if the brightness value is greater than the preset threshold;

A photographing module is configured to perform photographing in the super night scene mode by using a tripod photographing mode if no shake is generated.
The device according to claim 10, wherein the photographing module is further configured to:

If the brightness value is less than the preset threshold, shooting is performed in the super night scene mode using an HDR shooting mode.
The device according to claim 10 or 11, further comprising:

A third determining module, configured to further determine whether a region of interest of a face exists in the preview image if jitter occurs;

The shooting module is further configured to use a portrait shooting mode to shoot in the super night scene mode if the region of interest of the face exists.
The apparatus according to claim 12, wherein the photographing module is further configured to:

If the region of interest of the human face does not exist, shooting is performed in the super night scene mode by using a handheld shooting mode.
The device according to any one of claims 10-13, wherein the obtaining module is specifically configured to:

Acquiring a preview image corresponding to the current shooting scene, and extracting image characteristics of the preview image;

The image features are input to a pre-established scene recognition model to identify a scene detection result corresponding to the current shooting scene.
The apparatus according to claim 14, further comprising:

A first acquisition module, configured to collect sample scene information and describe and define the scene sample information;

A first training module is configured to input feature description and defined scene sample information to a deep neural network for training, and generate the scene recognition model.
The apparatus according to claim 14, further comprising:

A second acquisition module, configured to acquire sample images corresponding to different shooting scenes;

A labeling module, configured to label the shooting scene of the sample image;

A second training module is configured to use the labeled sample images to train the scene recognition model to obtain a trained scene recognition model.
The device according to any one of claims 10-16, further comprising:

An output module is configured to capture multiple frames of RAW images after shooting in the super night scene mode, and use an image processor ISP to process the multiple frames of RAW images to generate captured images.
The device according to any one of claims 10 to 17, wherein a brightness value of a preview image corresponding to the current shooting scene is inversely proportional to an environment brightness value of the current shooting scene.
An electronic device includes a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor is configured to execute the super night scene according to any one of claims 1-9 Shooting control method in mode.
A non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements a shooting control method in a super night scene mode according to any one of claims 1-9.