CN106231189A - Take pictures treating method and apparatus - Google Patents

Abstract

The embodiment of the invention discloses a photographing processing method and device, which relate to the technical field of image processing. Wherein, the method includes: identifying at least one reference focus object in the depth-of-field map generated in the photographing preview state, wherein the depth-of-field map corresponds to the photographing preview image displayed in the photographing preview interface; obtaining the selected target focusing object; Focusing on the photo preview image according to the target focusing object. The technical solution of the embodiment of the present invention achieves the technical effect of accurately focusing on the target focusing object according to the target focusing object selected by the user in at least one reference focusing object, so that the final focusing result is closer to the user's actual focusing needs. It optimizes the existing smart terminal camera technology and improves the user experience.

Description

Photo processing method and device

technical field

Embodiments of the present invention relate to image processing technologies, and in particular, to a photographing processing method and device.

Background technique

With the development of Internet, computer and communication technologies, the functions of smart terminals such as smart phones are becoming more and more powerful, and the user's dependence on smart terminals is also increasing, such as querying weather forecasts and taking photos.

Usually, when the user uses the smart terminal to shoot, the smart terminal will automatically complete the focusing according to the picture captured by the camera, and display the focused preview picture on the display interface.

However, in the process of realizing the present invention, the inventor found that the defect of the present invention is that: after the smart terminal finishes auto-focusing on the picture captured by the camera, the auto-focused picture may not be the picture that the user actually needs to take clearly, or, when the user When manually selecting the focus center point, there may be a certain deviation between the center point and the focus center point that the user actually wants, so that the focus image based on the center point does not meet the user's actual focus needs. For example, the user manually selects the center point of the subject as the focus center point. However, in the actual operation process, there is usually a certain deviation between the center point selected by the user and the actual center point of the subject. At this time, based on the center point selected by the user It is difficult to meet the user's actual focusing needs with a single-point focusing screen.

Contents of the invention

In view of this, the embodiments of the present invention provide a method and device for photographing processing, so as to solve the problem that the existing focusing technology of the smart terminal cannot meet the actual needs of the user.

In a first aspect, an embodiment of the present invention provides a photographing processing method, which includes:

Identifying at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface;

Get the selected target focus object;

Focusing on the photo preview image according to the target focusing object.

Further, obtaining the selected target focus object includes:

In the photo preview interface, the identified reference focus object is calibrated and prompted;

Obtain the target focusing object selected by the user according to the calibration prompt.

Optionally, the depth map generated in the photo preview state includes:

The photo preview is performed through dual cameras to obtain the depth of field map, and the photo preview image is presented in the photo preview interface.

Further, in the depth-of-field map generated in the photo preview state, identifying at least one reference focus object includes:

Obtaining the depth of field information of each image pixel in the depth of field map, wherein the depth of field information includes the distance information between the subject associated with the image pixel and the camera lens;

Collect the image pixels whose difference between the distance information satisfies the set threshold condition into the same pixel group;

Image pixel points with continuous image pixel coordinates in each pixel group are identified as reference focus objects.

Optionally, in the photo preview interface, prompting for calibration of the identified reference focus object includes:

Establishing an identity mark for the reference focusing object according to the number of identified reference focusing objects;

determining the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map;

determining a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photo preview interface;

At the marked position in the photo preview interface, an identity mark corresponding to the reference focus object is displayed.

Optionally, according to the image pixel coordinates of the reference focus object in the depth map, determining the position of the reference focus object in the photo preview interface includes:

Using the image pixel coordinates of the reference focus object in the depth map as the image pixel coordinates of the reference focus object in the photo preview image;

According to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image, obtain the screen pixel coordinates corresponding to the image pixel coordinates in the photo preview image in the photo preview interface, as the The position of the reference focus object in the photo preview interface.

Further, obtaining the target focusing object selected by the user according to the calibration prompt includes:

Obtain the voice information input by the user in real time;

If a keyword matching the calibration prompt is recognized in the voice information, a target focusing object corresponding to the calibration prompt is acquired.

Optionally, focusing on the photo preview image according to the target focusing object includes:

Determine the target distance information between the target focus object and the camera lens according to the depth-of-field map;

According to the pre-stored correspondence between the distance from the subject to the lens and the moving distance of the focus motor, and the target distance information, determine the adjusted moving position of the focus motor;

The focus motor is controlled to move according to the adjusted moving position, so as to focus on the photo preview image.

Further, according to the target focusing object, focusing on the photographing preview image includes:

Determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map;

In the pixel coordinates of the target screen, obtain the coordinates of the center pixel point as the focus point;

Focusing on the photo preview image according to the focusing point.

In a second aspect, an embodiment of the present invention provides a camera processing device, including:

The reference object recognition module is used to identify at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface;

A target acquisition module, configured to acquire a selected target focus object;

The focusing module is configured to focus on the photo preview image according to the target focusing object.

Optionally, the target acquisition module includes:

The calibration prompting sub-module is used to provide a calibration prompt for the identified reference focus object in the photo preview interface;

The target selection sub-module is configured to acquire the target focusing object selected by the user according to the calibration prompt.

Further, the reference object identification module includes:

The depth map acquisition sub-module is used to preview the photo through the dual cameras to obtain the depth map, and present the photo preview image in the photo preview interface;

The identification submodule is used to identify at least one reference focus object in the depth map, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface.

Optionally, the reference object recognition module includes:

The depth of field information acquisition sub-module is used to obtain the depth of field information of each image pixel in the depth of field map, wherein the depth of field information includes the distance information between the subject associated with the image pixel and the camera lens;

The pixel grouping sub-module is used for grouping the image pixel points whose difference between the distance information satisfies the set threshold condition into the same pixel grouping;

The reference object identification sub-module is used to identify the image pixel points with continuous image pixel coordinates in each pixel group as the reference focus object.

Further, the calibration prompt submodule includes:

An identity identification establishing unit, configured to establish an identity identification for the reference focusing object according to the number of identified reference focusing objects;

A reference position determination unit, configured to determine the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map;

A calibration position determination unit, configured to determine a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photographing preview interface;

The ID display unit is configured to display the ID corresponding to the reference focus object at the marked position in the photo preview interface.

Optionally, the reference position determination unit includes:

A coordinate determining subunit, configured to use the image pixel coordinates of the reference focus object in the depth map as the image pixel coordinates of the reference focus object in the photo preview image;

The position determination subunit is used to obtain the correspondence between the image pixel coordinates in the photo preview interface and the photo preview image according to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image The screen pixel coordinates are used as the position of the reference focus object in the photo preview interface.

Further, the target selection submodule includes:

A voice information acquisition unit, configured to acquire voice information input by the user in real time;

A target determining unit, configured to acquire a target focusing object corresponding to the marking prompt if a keyword matching the marking prompt is recognized in the voice information.

Optionally, the focusing module includes:

A target distance determination submodule, configured to determine target distance information between the target focus object and the camera lens according to the depth-of-field map;

The moving position determination sub-module is used to determine the adjusted moving position of the focus motor according to the pre-stored correspondence between the distance from the subject to the lens and the movement distance of the focus motor, and the target distance information;

The focus motor moving sub-module is used to control the focus motor to move according to the adjusted moving position, so as to focus on the preview image for taking pictures.

Further, the focusing module includes:

The target screen pixel coordinate determination submodule is used to determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map;

The focus point determination submodule is used to obtain the coordinates of the central pixel point in the pixel coordinates of the target screen as the focus point;

The focusing realization sub-module is used to focus on the photo preview image according to the focusing point.

The photographing processing method and device provided by the embodiments of the present invention identify at least one reference focus object in the depth map generated in the photographing preview state, and focus on the photographing preview image according to the acquired selected target focus object. The technical means of focusing on the photo preview image by acquiring the selected target focus object can achieve precise focusing on the target focus object according to the target focus object selected by the user in at least one reference focus object, so that the final focus result The technical effect that is closer to the user's actual focusing needs optimizes the existing smart terminal camera technology and improves the user experience.

Description of drawings

FIG. 1 is a flow chart of a photographing processing method provided by Embodiment 1 of the present invention;

FIG. 2a is a flow chart of a photographing processing method provided in Embodiment 2 of the present invention;

Fig. 2b is a flow chart of a calibration prompt method provided by Embodiment 2 of the present invention;

FIG. 2c is a flow chart of a method for determining the position of a reference focus object provided by Embodiment 2 of the present invention;

FIG. 2d is a flow chart of a voice input method provided by Embodiment 2 of the present invention;

Fig. 2e is a schematic diagram showing the first photo preview interface provided by the second embodiment of the present invention;

Fig. 2f is a schematic diagram of displaying a second photo preview interface provided by Embodiment 2 of the present invention;

FIG. 3 is a flow chart of a photographing processing method provided by Embodiment 3 of the present invention;

FIG. 4 is a flow chart of a photographing processing method provided in Embodiment 4 of the present invention;

FIG. 5 is a schematic structural diagram of a camera processing device provided in Embodiment 5 of the present invention.

detailed description

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processing, many of the steps may be performed in parallel, concurrently, or simultaneously. Additionally, the order of steps may be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure. The processing may correspond to a method, function, procedure, subroutine, subroutine, or the like.

Embodiment one

FIG. 1 is a flow chart of a method for processing photos provided by Embodiment 1 of the present invention. The method can be executed by a device for processing photos. The device can be implemented by software and/or hardware, and can generally be integrated into a smart terminal. As shown in Figure 1, the method includes:

Step 110: Identify at least one reference focus object in the depth map generated in the photo preview state, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface.

In this embodiment, the depth map can be acquired through the camera of the smart terminal. Wherein, the smart terminal may be a smart device held by a user such as a smart phone, a tablet computer, or a camera and having a shooting function.

Specifically, the depth of field refers to the distance range of an object measured by the axis of the imager that can obtain a clear image at the front of the camera lens or other imager. A depth map refers to a picture with a depth of field effect. Through the depth of field map, not only the image pixel coordinates of the subject in the depth of field map can be obtained, but also the depth of field information can be obtained, where the depth of field information can include the distance information between the subject and the camera lens, and the distance range information of the focus.

More specifically, the depth-of-field map may be generated from the shooting images acquired by the camera in the photo preview state. Wherein, the photographing preview state is a state in which the photographing picture can be previewed through the photographing preview interface after the photographing function of the smart terminal is turned on, but before a photographing instruction is received from the user. The specific manner of generating the depth map is not limited in this embodiment. The photo preview interface is an interface used to display images acquired by the camera in the display interface.

Further, after acquiring the depth-of-field image, at least one reference focus object in the depth-of-field image is identified. Wherein, the reference focusing object is an object that can be focused in the depth of field map.

Among them, the specific identification method can be based on the image pixels in the depth map, for example, determine the distance information between the subject and the camera lens associated with each image pixel, and make the distance information difference satisfy the set threshold condition (For example: 1cm or 2cm, etc.) and image pixels with similar image pixel coordinates are identified as reference focus objects. Image pixels with similar coordinates are identified as reference focus objects.

Optionally, a photo preview image is displayed in the photo preview interface of the display interface of the smart terminal. Wherein, the photographing preview image is an image frame without a depth of field effect, and the photographing preview image displayed in real time corresponds to the generated depth of field map. It can also be understood that the depth-of-field image is a picture generated by adding a depth-of-field effect to the photo preview image.

Optionally, the depth map generated in the photo preview state can be optimized to: perform photo preview through dual cameras to obtain the depth map, and present a photo preview image in the photo preview interface.

Specifically, the smart terminal is equipped with dual cameras, and after the camera function is turned on, the dual cameras are used to preview photos, and the preview images obtained by the dual cameras without depth of field effects are displayed in the photo preview interface, and a depth map is generated based on the images obtained by the dual cameras . The shooting principle of the dual cameras and the specific rules for generating the depth-of-field map are not limited in this embodiment.

Step 120, acquire the selected target focus object.

Specifically, the target focus object is the object where the focus point is located when the image is captured.

Optionally, after at least one reference focus object is identified in the depth-of-field map, the corresponding at least one reference focus object can be marked in the photo preview interface, so that the user can identify at least one reference focus object.

Exemplarily, a target focus object is selected from at least one reference focus object. Wherein, the selection of the target focus object may be automatically selected by the smart terminal, or may be selected by the user.

For example, when the smart terminal automatically selects, the reference focusing object closest to the camera lens can be selected as the target focusing object, or the reference focusing object occupying the largest screen area in the depth of field map can be selected as the target focusing object.

For another example, when the user makes a selection, at least one reference focus object can be marked in the photo preview interface, and the user can make a selection according to the mark, and the specific mark rules are not limited in this embodiment.

Optionally, the user selects the target focus object. Among them, the user can select the target focusing object by clicking a specific area of the display interface, clicking a specific button, and voice input.

Further, after the camera function is turned on, the smart terminal can monitor in real time whether the selection of the target focus object is confirmed, and obtain the selected target focus object when the selection of the target focus object is confirmed.

Step 130 , focus on the preview image for shooting according to the target focus object.

Exemplarily, according to the target focusing object, focus on the photo preview image displayed in the photo preview interface. At this point, what the user watches is the preview image of the camera after focusing.

Further, after receiving the photographing instruction, perform the photographing operation, and display the photographed image in the photographing preview interface. Wherein, the captured image adopts the above-mentioned determined focusing manner.

Optionally, after focusing on the photo preview image and displaying the focused photo preview image in the photo preview interface, if the user feels that the photo preview image at this time does not match the picture the user expects to shoot, he can re-select Target focus object. At this point, the photographing processing device may return to the operation of obtaining the selected target focus object, and focus on the photograph preview image according to the selected target focus object.

In the photographing processing method provided by the embodiment of the present invention, at least one reference focus object is identified in the depth map generated in the photograph preview state, and the photograph preview image is focused according to the acquired and selected target focus object. The technical means of focusing on the photo preview image by acquiring the selected target focus object can achieve precise focusing on the target focus object according to the target focus object selected by the user in at least one reference focus object, so that the final focus result The technical effect that is closer to the user's actual focusing needs optimizes the existing smart terminal camera technology and improves the user experience. For example, when the default auto-focus mode is implemented so that the preview image after focusing does not meet the actual needs of the user, the user can obtain an ideal preview image after focusing without adjusting the shooting angle by using the method provided in this embodiment.

Embodiment two

FIG. 2a is a flow chart of a method for processing photographs provided by Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiments. In this embodiment, obtaining the selected target focus object specifically includes: in the photographing preview interface, providing a calibration prompt for the identified reference focus object; acquiring the target focus object selected by the user according to the calibration prompt. Referring to Figure 2a, the method provided in this embodiment specifically includes:

Step 210: Identify at least one reference focus object in the depth map generated in the photo preview state, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface.

Step 220 , in the photographing preview interface, provide a calibration prompt for the identified reference focus object.

In this embodiment, considering the selection instruction issued by the user when selecting the target focus object, the smart terminal may not be able to accurately identify the scene of the target focus object. In order to enable the smart terminal to recognize the target focus object selected by the user, a calibration prompt may be given to at least one identified reference focus object in the photo preview interface.

Wherein, the calibration prompt is a prompt that can distinguish at least one reference focus object, that is, each reference focus object has a unique calibration prompt. The specific content of the calibration prompt may be numbers, letters, or words. For example, if three reference focus objects are identified in the depth-of-field map, then the three reference focus objects can be calibrated in the photo preview interface, and the specific content of the calibration prompts is 1, 2, and 3 in sequence. At this point, the corresponding target focusing object can be determined according to the user's selection of 1, 2 or 3.

Specifically, FIG. 2b is a flow chart of a calibration prompt method provided by Embodiment 2 of the present invention. Referring to FIG. 2b, step 220 may specifically include:

Step 221: Establish an identity for the reference focus object according to the number of the identified reference focus objects.

Exemplarily, the number of reference focusing objects recognized in the depth-of-field map is determined, and an identity mark is established for the participating focusing objects according to the number of reference focusing objects. Wherein, the specific content form of the identity mark is not limited in this embodiment.

For example, if two reference focus objects are identified, the identity marks established for the two reference focus objects may be the first object and the second object respectively. Wherein, when the identity mark of one reference focus object is the first object, the identity mark of the other reference focus object is the second object. The specific identification of which reference focus object is set as the first object is not specifically limited in this embodiment.

For another example, if it is recognized that the number of reference focus objects is 3, then the identities established for the 3 reference focus objects may be a, b, and c, respectively.

It should be noted that this embodiment does not limit the determination rules of the identity mark, but any identity mark setting rule that can distinguish reference focus objects is applicable to this embodiment.

Step 222: Determine the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map.

Exemplarily, since at least one reference focus object is identified in the depth-of-field map, but the identity of the reference focus object needs to be displayed in the photo preview interface, the position of the reference focus object needs to be determined in the photo preview interface.

Further, it may be to determine the image pixel coordinates of the reference focused object in the depth of field map, and determine the screen of the reference focused object in the photo preview interface according to the corresponding relationship between the image pixel coordinates of the depth of field map and the screen pixel coordinates of the photo preview interface. Pixel coordinates, and then determine the position of the reference focus object in the photo preview interface.

Specifically, FIG. 2c is a flow chart of a method for determining the position of a reference focus object provided by Embodiment 2 of the present invention. Referring to FIG. 2c, step 222 may specifically include:

Step 2221: Use the image pixel coordinates of the reference focused object in the depth map as the image pixel coordinates of the reference focused object in the photo preview image.

Exemplarily, since the depth map and the photo preview image correspond to each other, and the image resolution of the depth map and the photo preview image is the same, the image pixel coordinate range of the depth map is the same as the image pixel coordinate range of the photo preview image, And the position of the image pixel coordinates with the same value in the depth map is the same as the position in the photo preview image. For example, the image pixel coordinate range of the depth of field map is (0,0) to (959,719), then the image pixel coordinate range of the photo preview image is also (0,0) to (959,719), and each image pixel coordinate point is within the depth of field The positions in the picture are the same as in the photo preview image.

Further, after the reference focus object is identified, the image pixel coordinates of the reference focus object in the depth map are determined, and the image pixel coordinates are used as the image pixel coordinates of the reference focus object in the photo preview image.

Step 2222, according to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image, obtain the screen pixel coordinates in the photo preview interface corresponding to the image pixel coordinates in the photo preview image , as the position of the reference focus object in the photo preview interface.

Specifically, since the screen resolution of the photo preview interface is preset and related to the screen resolution of the display interface, for example, the screen resolution of the photo preview interface may be 1024×768 or 1024×720, etc. At the same time, the image resolution of the photo preview image is also preset and is related to the resolution of the camera. For example, the image resolution of the photo preview image may be 1024×768 or 1280×960.

More specifically, the corresponding relationship may be determined according to the screen resolution of the photo preview interface and the image resolution of the photo preview image. For example, the screen resolution of the photo preview interface is 1024×768, and the image resolution of the photo preview image is 1024×768. At this time, the pixel coordinates of each image in the photo preview image correspond to the pixel coordinates of each screen in the photo preview interface. . For another example, the screen resolution of the photo preview interface is 1024×720, and the image resolution of the photo preview image is 1280×960. At this time, it is necessary to determine the screen resolution of the photo preview interface and the image resolution of the photo preview image. Correspondence, so as to ensure that the photo preview image with the image resolution of 1280×960 is displayed in the photo preview interface with the screen resolution of 1024×720. Wherein, the specific correspondence determination rules are not limited in this embodiment.

Exemplarily, after determining the image pixel coordinates of the reference focus object in the photo preview image, according to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image, determine the reference focus object in the photo preview interface. The screen pixel coordinates in , and use the screen pixel coordinates as a reference to the position of the focused object in the photo preview interface.

Step 223 : Determine a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photo preview interface.

Specifically, the marked position is the position where the identity mark is marked in the photo preview interface. The calibration position is related to the position of the reference focus object in the photo preview interface. More specifically, the calibration position may be a specific screen pixel coordinate value, or a specific screen pixel coordinate range.

For example, after determining the position of the reference focus object in the photo preview interface, set the calibration position to be within a screen pixel coordinate range directly above the position of the reference focus object. For another example, after determining the position of the reference focus object in the photo preview interface, set the calibration position to be within a screen pixel coordinate range at the lower right of the reference focus object position. As another example, after determining the position of the reference focus object in the photo preview interface, set a screen pixel coordinate range where the calibration position is located in the center of the reference focus object position. It should be noted that the specific setting rules of the calibration position are not limited to the above examples.

Optionally, the calibration positions corresponding to different reference focus objects in the same photo preview interface may be different. For example, the current photo preview interface contains two reference focus objects, set the calibration position of one of the reference focus objects to be within a screen pixel coordinate range directly above the position of the reference focus object, and set the calibration position of the other reference focus object to be within the reference A range of screen pixel coordinates in the center of the focus object position.

Step 224 , display the identity mark corresponding to the reference focus object at the marked position in the photo preview interface.

Exemplarily, after the calibration position corresponding to the reference focus object is determined, the identity mark corresponding to the reference focus object is displayed at the calibration position.

Step 230, acquiring the target focusing object selected by the user according to the calibration prompt.

Specifically, after a calibration prompt is given to at least one reference focus object in the photo preview interface, the user can select the corresponding target focus object according to the calibration prompt and in combination with their own photographing needs.

Further, after the camera function is turned on, it is possible to monitor whether the user confirms that the user selects the target focus object according to the calibration prompt. Alternatively, after the calibration prompt is displayed, monitor whether the user has selected the target focus object according to the calibration prompt, and obtain the target focus object when the user confirms that the user has selected the target focus object according to the calibration prompt.

Optionally, in this embodiment, the user may select the target focus object through voice input. Fig. 2d is a flow chart of a speech input method provided by Embodiment 2 of the present invention. Referring to FIG. 2d, step 230 may specifically include:

Step 231, acquiring voice information input by the user in real time.

Specifically, the voice information input by the user is acquired in real time through the audio input device. Wherein, the audio input device may be in the smart terminal, for example, the audio input device may be a microphone of the smart terminal. The audio input device may also be in other devices associated with the smart terminal, for example, the audio input device may be a microphone in an earphone associated with the smart terminal.

Step 232, judging whether a keyword matching the marking prompt can be recognized in the voice information. If a keyword matching the marking prompt is identified in the voice information, then step 233 is executed; otherwise, step 231 is executed.

Specifically, pre-set keywords that match the calibration prompt, for example, if the calibration prompt is 1 and 2, then the set keywords can be focus 1 and focus 2 respectively, or the set keywords can also be 1 and 2 respectively. 2. Wherein, the specific setting method and content of the keyword can be determined according to the actual situation.

Further, after acquiring the voice information input by the user, the voice information is recognized to obtain the text content of the voice information, and it is judged whether the text content contains keywords matching the calibration prompt. The specific voice information recognition method is not limited in this embodiment.

Step 233 , acquiring a target focus object corresponding to the calibration prompt.

Exemplarily, if a keyword matching the calibration prompt is recognized in the voice information, the target focus object corresponding to the calibration prompt is acquired.

For example, if it is recognized in the voice information that the keyword matching the marking prompt is focus 1, then it is confirmed that the marking prompt selected by the user is 1, and at this time, the target focus object corresponding to 1 is obtained.

Step 240: Focus on the photo preview image according to the target focus object.

The specific implementation process of selecting the target focus object in this embodiment is given as an example below.

After the camera function of the smart terminal is turned on, the dual cameras are used to acquire images and generate a depth map, and a photo preview image corresponding to the depth map is displayed in the photo preview interface. It is assumed that FIG. 2e is a schematic diagram of displaying the first photo preview interface provided by Embodiment 2 of the present invention. Referring to FIG. 2e, a photo preview image is displayed on the photo preview interface 21 of the smart terminal.

Further, at least one reference focus object in the depth of field map is identified, and the number of reference focus objects is determined to be three. Correspondingly, identity marks are established for the three reference focus objects, wherein the established identity marks are focus 1, focus 2, and focus 3 respectively.

Furthermore, the screen resolution of the photo preview interface is set to 1024×768, the image resolution of the photo preview image is 1024×768, and the image resolution of the depth map is the same as the image resolution of the photo preview image. Determine the image pixel coordinates of the three reference focus objects in the depth-of-field map, and use the image pixel coordinates as the image pixel coordinates of the three reference focus objects in the photo preview image. Since the screen resolution of the photo preview interface is the same as the image resolution of the photo preview image, the screen pixel coordinates of the photo preview interface are in one-to-one correspondence with the image pixel coordinates of the photo preview image. Accordingly, according to the image pixel coordinates of the three reference focus objects in the photo preview image, the screen pixel coordinates of the three reference focus objects in the photo preview interface are respectively determined, and the determined screen pixel coordinates are respectively used as the corresponding reference focus objects in the photo preview interface. The position in the photo preview interface.

Specifically, after determining the positions of the three reference focus objects in the photographing preview screen, determine the calibration position corresponding to the reference focus object, and display the corresponding identity mark at the calibration position. Fig. 2f is a schematic diagram of displaying a second photo preview interface provided by Embodiment 2 of the present invention. Referring to Fig. 2f, the identity mark of the first reference focus object is displayed in the first calibration position 22 in the photo preview interface 21, that is, focus 1, and the calibration position 22 is located inside the first reference focus object. In the second calibration position 23 in the interface 21, the identity mark of the second reference focus object is displayed, that is, focus 2, and the calibration position 23 is located inside the second reference focus object, and the third reference focus object in the photo preview interface 21 The identification mark of the third reference focus object, ie focus 3, is displayed in the calibration position 24, and the calibration position 24 is located at the lower right of the third reference focus object.

Further, the microphone is turned on to obtain voice information input by the user. After acquiring the voice information, it is recognized that the voice information contains the keyword focus 2, and the keyword matches the keyword of the second calibration prompt. At this time, it is determined that the target focus object selected by the user is 2, and at the same time, focus according to the target The object is focused on the photo preview image.

In the technical solution of this embodiment, by identifying at least one reference focus object in the depth-of-field map generated in the photographing preview state, and displaying a calibration prompt of at least one reference focus object in the photographing preview interface, it is possible to obtain the user selected according to the calibration prompt. The target focus object, and then focus on the photo preview image, realize the precise focus on the target focus object according to the target focus object selected by the user in at least one reference focus object, so that the final focus result is closer to the user's actual focus At the same time, it optimizes the existing smart terminal camera technology and improves the user experience.

Embodiment three

FIG. 3 is a flow chart of a photographing processing method provided by Embodiment 3 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiments. In this embodiment, identifying at least one reference focus object in the depth-of-field map generated in the photographing preview state is specifically: acquiring the depth-of-field information of each image pixel in the depth-of-field map, wherein the depth-of-field information includes image pixel points The distance information between the associated subject and the camera lens; the image pixels whose difference between the distance information meets the set threshold condition are grouped into the same pixel group; the images with continuous image pixel coordinates in each pixel group Pixels are identified as reference focus objects.

At the same time, focusing on the photo preview image according to the target focusing object specifically includes: determining the target distance information between the target focusing object and the camera lens according to the depth of field map; The corresponding relationship between the distance of the lens and the moving distance of the focus motor, and the target distance information, determine the adjustment and movement position of the focus motor; control the movement of the focus motor according to the adjustment and movement position, so as to preview the image of the photo to focus. Referring to Figure 3, the method of this embodiment specifically includes:

Step 310: Obtain depth information of each image pixel in the depth map, wherein the depth information includes distance information between the subject associated with the image pixel and the camera lens.

Specifically, when a camera is used to take a photo, the distance from the same subject to the camera lens is the same, therefore, the subject can be identified according to the distance information from the subject to the camera lens.

Exemplarily, after the depth map is generated, the depth information of each image pixel in the depth map is acquired. Wherein, the depth of field information may include the distance information between the subject and the camera lens associated with the image pixel and the focus distance range information of the image pixel. Optionally, the depth of field information is the distance information between the subject associated with the image pixel and the camera lens.

Step 320, grouping the image pixel points whose difference between the distance information satisfies the set threshold condition into the same pixel group.

Specifically, the distance information in the depth information of each image pixel point in the depth map is subtracted, and the absolute value of the difference is obtained. Optionally, the distance information of each image pixel in the depth map is subtracted from the distance information of adjacent image pixels, and the absolute value of the difference is taken.

Further, image pixel points whose difference values satisfy the preset threshold condition are grouped together, that is, grouped into the same pixel group. Wherein, the preset threshold condition can be set according to the actual situation. For example, according to the depth information of each image pixel, it is determined that each subject in the depth map is closer to the camera lens. At this time, the preset threshold condition can be less than or equal to 1cm, that is, in each image pixel, the distance information The image pixels whose difference between them is less than or equal to 1cm are grouped into the same pixel group. As another example, according to the depth information of each image pixel, it is determined that each subject in the depth map is far away from the camera lens. At this time, the preset threshold condition can be less than or equal to 10cm, that is, in each image pixel, the distance Image pixels whose information difference is less than or equal to 10cm are grouped into the same pixel group.

Step 330, identifying image pixel points with continuous image pixel coordinates in each pixel group as a reference focus object.

Considering that in the same depth map, the distance information of different subjects from the camera lens may be the same, but the image pixel coordinates of the same subject in the depth map are absolutely continuous. Therefore, after the image pixels of the depth of field map are grouped according to the difference of the distance information, the image pixels with continuous image pixel coordinates in the same pixel group are identified as the reference focus object.

Further, image pixel points with continuous image pixel coordinates in each pixel group are identified as reference focus objects.

Step 340, acquire the selected target focus object.

Step 350 : Determine target distance information between the target focus object and the camera lens according to the depth-of-field map.

Specifically, the target distance information between the target focus object and the camera lens is determined according to the depth of field information of each image pixel point corresponding to the target focus object in the depth of field map.

Step 360 , according to the pre-stored correspondence between the distance from the subject to the lens and the moving distance of the focus motor, and the target distance information, determine the adjustment movement position of the focus motor.

Exemplarily, a focus motor is provided in the smart terminal, and the movement distance of the focus motor corresponding to different distances from the subject to the camera lens is preset. For example, the distance from the subject to the camera lens is 10cm, and the set moving distance of the focus motor is 0.5cm. For another example, the distance from the subject to the camera lens is 30cm, and the set moving distance of the focus motor is 2cm.

Specifically, after determining the target distance information of the target focus object from the camera lens, the adjustment and movement position of the focus motor is determined according to the above correspondence.

For example, if it is determined that the moving distance of the focus motor is 2 cm according to the target distance information between the target focus object and the camera lens and the above correspondence, then the adjusted moving position of the focus motor is determined to be 2 cm.

Step 370 , controlling the focus motor to move according to the adjusted moving position, so as to focus on the preview image for shooting.

Specifically, the focus motor is controlled to move according to the adjusted moving position of the focus motor. After the focus motor is moved, the focusing method for focusing on the photo preview image is the focusing method actually required by the user.

In the technical solution of this embodiment, at least one reference focus object is identified through the depth of field information of each image pixel point in the depth of field map, and the selected target focus object is obtained, and the adjustment movement of the focus motor is determined according to the distance information between the target focus object and the camera lens Position, and then control the focus motor to move according to the adjustment of the moving position. The focus on the preview image of the photo has been completed, and at least one reference focus object has been realized. According to the depth of field information of the target focus object selected by the user, the target focus object is accurately completed. Focusing makes the final focusing result closer to the user's actual focusing needs. At the same time, it optimizes the existing smart terminal camera technology and improves the user experience.

Embodiment Four

FIG. 4 is a flow chart of a photographing processing method provided by Embodiment 4 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiments. In this embodiment, focusing on the photographing preview image according to the target focus object specifically includes: according to the image pixel coordinates of the target focus object in the depth-of-field map, determining where the target focus object is The pixel coordinates of the target screen in the photo preview interface; in the pixel coordinates of the target screen, the coordinates of the central pixel point are obtained as the focus point; according to the focus point, the focus is carried out on the preview image of the photo. Referring to Figure 4, the method provided in this embodiment includes:

Step 410: Identify at least one reference focus object in the depth map generated in the photo preview state, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface.

Step 420, acquire the selected target focus object.

Step 430 : Determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map.

Specifically, the image pixel coordinates of the target focus object in the depth map are acquired.

Further, since the image pixel coordinates of the depth-of-field map correspond to the image pixel coordinates of the photographing preview image, each image of the target focusing object in the photographing preview image can be determined according to the pixel coordinates of each image of the target focusing object in the depth-of-field map. pixel coordinates.

Furthermore, according to the corresponding relationship between the image resolution of the photo preview image and the screen resolution of the photo preview interface, and the image pixel coordinates of the target focus object in the photo preview image, determine the target screen of the target focus object in the photo preview interface pixel coordinates.

Step 440, in the pixel coordinates of the target screen, acquire the coordinates of the central pixel point as the focusing point.

Specifically, in the pixel coordinates of each target screen corresponding to the target focus object, the coordinates of the central pixel point are selected. Wherein, it may be to calculate the mean value of the pixel coordinates of the target screen, and take the integer of the mean value as the center pixel point coordinates. It is also possible to select, among the target screen pixel coordinates of the target focus object, the target screen pixel coordinate located at the center of the target focus object as the center pixel point coordinates.

Further, the central pixel is used as the focusing point. Wherein, the focusing point is a central point when performing focusing processing.

Step 450: Focus on the photo preview image according to the focus point.

Exemplarily, the camera preview image may be focused on the focus point.

Optionally, the focused photo preview image is displayed in the photo preview interface.

In the technical solution of this embodiment, by identifying at least one reference focus object in the depth-of-field map generated in the photo preview state, and determining the target screen pixel coordinates of the target focus object in the photo preview interface according to the acquired selected target focus object, The central pixel point of the pixel coordinates of the target screen is used as the focus point, and then the camera preview image is focused, so that in at least one reference focus object, the focus point is determined according to the target focus object selected by the user, and the focus is completed based on the focus point. The precise focusing of the target focusing object makes the final focusing result closer to the actual focusing needs of the user. At the same time, it optimizes the existing smart terminal camera technology and improves the user experience.

Embodiment five

FIG. 5 is a schematic structural diagram of a camera processing device provided in Embodiment 5 of the present invention. As shown in Figure 5, the device includes: a reference object recognition module 51, a target acquisition module 52 and a focusing module 53, wherein:

The reference object recognition module 51 is used to identify at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface;

A target acquisition module 52, configured to acquire a selected target focus object;

The focusing module 53 is configured to focus on the photographing preview image according to the target focusing object.

The photographing processing device provided by the embodiment of the present invention identifies at least one reference focus object in the depth map generated in the photographing preview state, and focuses on the photographing preview image according to the acquired and selected target focus object. The technical means of focusing on the photo preview image by acquiring the selected target focus object can achieve precise focusing on the target focus object according to the target focus object selected by the user in at least one reference focus object, so that the final focus result The technical effect that is closer to the user's actual focusing needs optimizes the existing smart terminal camera technology and improves the user experience. For example, when the default auto-focus mode is implemented so that the preview image after focusing does not meet the actual needs of the user, the device provided by this embodiment can obtain the ideal preview image after focusing without adjusting the shooting angle.

On the basis of the above-mentioned embodiments, the target acquisition module 52 may include:

The calibration prompting sub-module is used to provide a calibration prompt for the identified reference focus object in the photo preview interface;

The target selection sub-module is configured to acquire the target focusing object selected by the user according to the calibration prompt.

On the basis of the above-mentioned embodiments, the reference object recognition module 51 may include:

The depth map acquisition sub-module is used to preview the photo through the dual cameras to obtain the depth map, and present the photo preview image in the photo preview interface;

The identification submodule is used to identify at least one reference focus object in the depth map, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface.

On the basis of the above-mentioned embodiments, the reference object recognition module 51 may include:

The depth of field information acquisition sub-module is used to obtain the depth of field information of each image pixel in the depth of field map, wherein the depth of field information includes the distance information between the subject associated with the image pixel and the camera lens;

The pixel grouping sub-module is used for grouping the image pixel points whose difference between the distance information satisfies the set threshold condition into the same pixel grouping;

The reference object identification sub-module is used to identify the image pixel points with continuous image pixel coordinates in each pixel group as the reference focus object.

On the basis of the above-mentioned embodiments, the calibration prompt submodule may include:

An identity identification establishing unit, configured to establish an identity identification for the reference focusing object according to the number of identified reference focusing objects;

A reference position determination unit, configured to determine the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map;

A calibration position determination unit, configured to determine a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photographing preview interface;

The ID display unit is configured to display the ID corresponding to the reference focus object at the marked position in the photo preview interface.

On the basis of the above embodiments, the reference position determining unit may include:

A coordinate determining subunit, configured to use the image pixel coordinates of the reference focus object in the depth map as the image pixel coordinates of the reference focus object in the photo preview image;

The position determination subunit is used to obtain the correspondence between the image pixel coordinates in the photo preview interface and the photo preview image according to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image The screen pixel coordinates are used as the position of the reference focus object in the photo preview interface.

On the basis of the above-mentioned embodiments, the target selection submodule may include:

A voice information acquisition unit, configured to acquire voice information input by the user in real time;

A target determining unit, configured to acquire a target focusing object corresponding to the marking prompt if a keyword matching the marking prompt is recognized in the voice information.

On the basis of the above-mentioned embodiments, the focusing module 53 may include:

A target distance determination submodule, configured to determine target distance information between the target focus object and the camera lens according to the depth-of-field map;

The moving position determination sub-module is used to determine the adjusted moving position of the focus motor according to the pre-stored correspondence between the distance from the subject to the lens and the movement distance of the focus motor, and the target distance information;

The focus motor moving sub-module is used to control the focus motor to move according to the adjusted moving position, so as to focus on the preview image for taking pictures.

On the basis of the above-mentioned embodiments, the focusing module 53 may include:

The target screen pixel coordinate determination submodule is used to determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map;

The focus point determination submodule is used to obtain the coordinates of the central pixel point in the pixel coordinates of the target screen as the focus point;

The focusing realization sub-module is used to focus on the photo preview image according to the focusing point.

The above-mentioned product can execute the method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

An embodiment of the present invention also provides a storage medium containing computer-executable instructions, the computer-executable instructions are used to execute a photographing processing method when executed by a computer processor, the method comprising:

Identifying at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface;

Get the selected target focus object;

Focusing on the photo preview image according to the target focusing object.

Optionally, when the computer-executable instruction is executed by a computer processor, it may also be used to execute the technical solution of the photographing processing method provided in any embodiment of the present invention.

Through the above description about the implementation mode, those skilled in the art can clearly understand that the present invention can be realized by means of software and necessary general-purpose hardware, and of course it can also be realized by hardware, but in many cases the former is a better implementation mode . Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a floppy disk of a computer , read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), flash memory (FLASH), hard disk or optical disc, etc., including several instructions to make a computer device (which can be a personal computer, A server, or a network device, etc.) executes the methods described in various embodiments of the present invention.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims (18)

1. A photographic processing method, characterized in that, comprising: Identifying at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface; Get the selected target focus object; Focusing on the photo preview image according to the target focusing object. 2. The method according to claim 1, wherein obtaining the selected target focus object comprises: In the photo preview interface, the identified reference focus object is calibrated and prompted; Obtain the target focusing object selected by the user according to the calibration prompt. 3. The method according to claim 1, wherein the depth-of-field map generated in the photo preview state comprises: The photo preview is performed through dual cameras to obtain the depth of field map, and the photo preview image is presented in the photo preview interface. 4. The method according to any one of claims 1-3, wherein identifying at least one reference focus object in the depth map generated in the photo preview state comprises: Obtaining the depth of field information of each image pixel in the depth of field map, wherein the depth of field information includes the distance information between the subject associated with the image pixel and the camera lens; Collect the image pixels whose difference between the distance information satisfies the set threshold condition into the same pixel group; Image pixel points with continuous image pixel coordinates in each pixel group are identified as reference focus objects. 5. The method according to claim 2, wherein, in the photo preview interface, prompting the identified reference focus object to be calibrated includes: Establishing an identity mark for the reference focusing object according to the number of identified reference focusing objects; determining the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map; determining a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photo preview interface; At the marked position in the photo preview interface, an identity mark corresponding to the reference focus object is displayed. 6. The method according to claim 5, wherein, according to the image pixel coordinates of the reference focus object in the depth map, determining the position of the reference focus object in the photo preview interface comprises: Using the image pixel coordinates of the reference focus object in the depth map as the image pixel coordinates of the reference focus object in the photo preview image; According to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image, obtain the screen pixel coordinates corresponding to the image pixel coordinates in the photo preview image in the photo preview interface, as the The position of the reference focus object in the photo preview interface. 7. The method according to claim 2, wherein obtaining the target focus object selected by the user according to the calibration prompt comprises: Obtain the voice information input by the user in real time; If a keyword matching the calibration prompt is recognized in the voice information, a target focusing object corresponding to the calibration prompt is acquired. 8. The method according to claim 1, wherein focusing on the photograph preview image according to the target focus object comprises: Determine the target distance information between the target focus object and the camera lens according to the depth-of-field map; According to the pre-stored correspondence between the distance from the subject to the lens and the moving distance of the focus motor, and the target distance information, determine the adjusted moving position of the focus motor; The focus motor is controlled to move according to the adjusted moving position, so as to focus on the photo preview image. 9. The method according to claim 1, wherein focusing on the photograph preview image according to the target focus object comprises: Determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map; In the pixel coordinates of the target screen, obtain the coordinates of the center pixel point as the focus point; Focusing on the photo preview image according to the focusing point. 10. A camera processing device, characterized in that it comprises: The reference object recognition module is used to identify at least one reference focus object in the depth of field map generated in the photo preview state, wherein the depth of field map corresponds to the photo preview image displayed in the photo preview interface; A target acquisition module, configured to acquire a selected target focus object; The focusing module is configured to focus on the photo preview image according to the target focusing object. 11. The device according to claim 10, wherein the target acquisition module comprises: The calibration prompting sub-module is used to provide a calibration prompt for the identified reference focus object in the photo preview interface; The target selection sub-module is configured to acquire the target focusing object selected by the user according to the calibration prompt. 12. The device according to claim 10, wherein the reference object identification module comprises: The depth map acquisition sub-module is used to preview the photo through the dual cameras to obtain the depth map, and present the photo preview image in the photo preview interface; The identification submodule is used to identify at least one reference focus object in the depth map, wherein the depth map corresponds to the photo preview image displayed in the photo preview interface. 13. The device according to any one of claims 10-12, wherein the reference object recognition module comprises: The depth of field information acquisition sub-module is used to obtain the depth of field information of each image pixel in the depth of field map, wherein the depth of field information includes the distance information between the subject associated with the image pixel and the camera lens; The pixel grouping sub-module is used for grouping the image pixel points whose difference between the distance information satisfies the set threshold condition into the same pixel grouping; The reference object identification sub-module is used to identify the image pixel points with continuous image pixel coordinates in each pixel group as the reference focus object. 14. The device according to claim 11, wherein the calibration prompt submodule comprises: An identity identification establishing unit, configured to establish an identity identification for the reference focusing object according to the number of identified reference focusing objects; A reference position determination unit, configured to determine the position of the reference focus object in the photo preview interface according to the image pixel coordinates of the reference focus object in the depth map; A calibration position determination unit, configured to determine a calibration position corresponding to the reference focus object according to the position of the reference focus object in the photographing preview interface; The ID display unit is configured to display the ID corresponding to the reference focus object at the marked position in the photo preview interface. 15. The device according to claim 14, wherein the reference position determining unit comprises: A coordinate determining subunit, configured to use the image pixel coordinates of the reference focus object in the depth map as the image pixel coordinates of the reference focus object in the photo preview image; The position determination subunit is used to obtain the correspondence between the image pixel coordinates in the photo preview interface and the photo preview image according to the corresponding relationship between the screen resolution of the photo preview interface and the image resolution of the photo preview image The screen pixel coordinates are used as the position of the reference focus object in the photo preview interface. 16. The device according to claim 11, wherein the target selection submodule comprises: A voice information acquisition unit, configured to acquire voice information input by the user in real time; A target determining unit, configured to acquire a target focusing object corresponding to the marking prompt if a keyword matching the marking prompt is recognized in the voice information. 17. The device according to claim 10, wherein the focusing module comprises: A target distance determination submodule, configured to determine target distance information between the target focus object and the camera lens according to the depth-of-field map; The moving position determination sub-module is used to determine the adjusted moving position of the focus motor according to the pre-stored correspondence between the distance from the subject to the lens and the movement distance of the focus motor, and the target distance information; The focus motor moving sub-module is used to control the focus motor to move according to the adjusted moving position, so as to focus on the preview image for taking pictures. 18. The device according to claim 10, wherein the focusing module comprises: The target screen pixel coordinate determination submodule is used to determine the target screen pixel coordinates of the target focus object in the photo preview interface according to the image pixel coordinates of the target focus object in the depth map; The focus point determination submodule is used to obtain the coordinates of the central pixel point in the pixel coordinates of the target screen as the focus point; The focusing realization sub-module is used to focus on the photo preview image according to the focusing point.