Multi-angle shooting method, device, electronic device and storage medium
Through pre-trained AI models, analyzing the perspective images of multi-camera devices, and automatically combining them to generate aesthetic and story-like images, solving the problems of insufficient aesthetics of combined images and complex user operations in the prior art, improving photography quality and simplicity of operation.
Patent Information
- Application Number
- CN202010613639.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-30
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2040-06-30
AI Technical Summary
When shooting, the combined picture lacks aesthetics and storylines. Users need to have professional background knowledge to choose the camera, which is complicated to operate.
Using pre-trained AI models, we obtain the perspective images of multiple cameras, analyze the components, and generate aesthetic and story-rich target images, automatically combine the perspectives to reduce the user's need to choose a camera.
The photography quality is improved, the generated images are full of aesthetics and storyliness, simplifying user operation processes, and avoiding the cumbersome process of camera selection.
Smart Images

Figure CN113873177B_ABST
Abstract
Description
Technical Field
[0001] The present application generally relates to the field of electronic technology, and specifically relates to a multi-view shooting method, device, electronic device and storage medium. Background Art
[0002] With the rapid development of terminal technology, more and more electronic devices are equipped with multiple cameras. In actual use, these cameras can have different uses such as ultra-wide angle, wide angle, telephoto and macro. The various lenses provide hardware conditions for taking photos of different subjects.
[0003] However, the related technology has at least the following problems: the images from multiple cameras are combined awkwardly, lacking aesthetics and storytelling; and the selection of cameras by users requires professional background knowledge and has poor operability. Summary of the invention
[0004] In view of the above-mentioned defects or deficiencies in the related art, it is desired to provide a multi-perspective shooting method, device, electronic device and storage medium, which can call multiple cameras to take pictures and automatically combine the perspective pictures to obtain beautiful and story-telling images, improve the photography quality, and do not require the user to select the camera.
[0005] In a first aspect, the present application provides a multi-view shooting method, the method comprising:
[0006] Obtaining visual images captured by at least two cameras;
[0007] According to the pre-trained AI model, the constituent elements of each of the perspective images are analyzed, and the target image is generated based on the constituent elements of each of the perspective images.
[0008] In a second aspect, the present application provides a multi-view shooting device, the device comprising:
[0009] An acquisition module configured to acquire viewing angle images captured by at least two cameras;
[0010] A generation module is configured to analyze the constituent elements of each of the perspective images according to a pre-trained AI model, and generate a target image based on the constituent elements of each of the perspective images.
[0011] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the multi-view shooting method as described in the first aspect.
[0012] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the multi-view shooting method as described in the first aspect.
[0013] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0014] The embodiments of the present application provide a multi-perspective shooting method, device, electronic device and storage medium. Since the AI model has been pre-learned and trained on the characteristics and advantages of massive images, that is to say, the AI model has aesthetic ability and can perform real-time analysis on the constituent elements of the picture. Therefore, the target image obtained based on the combination of pictures from various perspectives is aesthetically pleasing and narrative, which improves the quality of photography. At the same time, it avoids the tediousness of user camera selection and simplifies the process. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0016] Figure 1 A schematic diagram of a basic process of a multi-view shooting method provided in an embodiment of the present application;
[0017] Figure 2 A schematic diagram of a layout division provided in an embodiment of the present application;
[0018] Figure 3 A scenario example of a target format provided in an embodiment of the present application;
[0019] Figure 4 Another example of a target layout scenario provided in an embodiment of the present application;
[0020] Figure 5 An example of a multi-view shooting method provided in an embodiment of the present application;
[0021] Figure 6 A schematic diagram of a close-up format provided in an embodiment of the present application;
[0022] Figure 7 A schematic diagram of a perspective layout provided in an embodiment of the present application;
[0023] Figure 8 A schematic diagram of another perspective layout provided in an embodiment of the present application;
[0024] Fig. 9 A schematic diagram of the structure of a multi-viewing angle shooting device provided in an embodiment of the present application;
[0025] Fig.10 A schematic diagram of the structure of another multi-view shooting device provided in an embodiment of the present application;
[0026] Fig.11 A schematic diagram of the structure of another multi-view shooting device provided in an embodiment of the present application;
[0027] Fig.12 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the application described can be implemented in an order other than those illustrated or described herein.
[0030] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or apparatuses.
[0031] For ease of understanding and explanation, the following Figures 1 to 12 The multi-view shooting method, device, electronic device and storage medium provided by the embodiments of the present application are described in detail.
[0032] Please refer to Figure 1 , which is a basic flow chart of a multi-view shooting method provided by an embodiment of the present application. The method comprises the following steps:
[0033] S101, obtaining viewing angle images captured by at least two cameras.
[0034] For example, when at least two cameras include a first camera and a second camera, an embodiment of the present application obtains a first perspective picture captured by the first camera and a second perspective picture captured by the second camera, and the shooting mode corresponding to the second perspective picture is different from the shooting mode corresponding to the first perspective picture.
[0035] It should be noted that the camera may include but is not limited to a main camera and a secondary camera. The main camera and the secondary camera have different viewing angles. For example, if the main camera is a wide-angle camera, its corresponding shooting mode is a wide-angle mode, that is, the wide-angle camera's viewing angle picture contains various components, such as nearby people and distant mountains, etc.; for another example, if the secondary camera is a macro camera, its corresponding shooting mode is a macro mode, that is, relative to the viewing angle picture of the wide-angle camera, the macro camera's viewing angle picture contains fewer components, such as only nearby people, etc. In addition, the viewing angle pictures captured by at least two cameras can be the same viewing angle, such as both cameras are wide-angle cameras, or different viewing angles, such as one camera is a wide-angle camera and the other camera is a macro camera, which is not limited in the embodiments of the present application.
[0036] In actual use, the main camera is responsible for the main imaging, while each sub-camera is used for auxiliary imaging. For example, the ultra-wide-angle sub-camera can bring a wider field of view when shooting, and with a simple composition, it can achieve very good results when shooting landscapes and portraits; the telephoto sub-camera uses a larger fixed focal length to achieve the purpose of shooting farther objects; the macro sub-camera uses a smaller preset focal length to achieve the function of shooting small objects. The embodiment of the present application uses multiple cameras to capture images from different perspectives to obtain more details of the subject and clearer and more delicate images.
[0037] In some optional embodiments, before obtaining the perspective images captured by at least two cameras, the embodiment of the present application responds to the user's operation instruction, takes the photographed object displayed by the first camera in the imaging display area as a reference, and automatically adjusts at least one second camera other than the first camera to focus on the photographed object. Optionally, the optical axis of at least one second camera can be automatically adjusted to converge at a point of the photographed object so that the focus of at least one second camera is aligned with the photographed object; wherein the first camera is a camera specified by the user. Among them, the user's operation instruction may include but is not limited to at least one of manual operation or voice operation. For example, the user performs manual operation by clicking the AI multi-view button on the interface; or the user speaks "Please turn on AI multi-view" to the microphone on the electronic device for voice operation. The advantage of such a setting is that the embodiment of the present application can not only obtain the perspective image taken by the user autonomously, that is, the image captured by the first camera, but also obtain the perspective image shot by AI multi-view at the same time, that is, the image captured by at least one second camera other than the first camera, thereby giving full play to the functions of each camera, making the image more beautiful and storytelling.
[0038] It should be noted that AI multi-view shooting means that the AI model can automatically call at least one second camera other than the first camera to collect the perspective images based on the characteristics and advantages of massive images in advance, and autonomously analyze the components of each perspective image to synthesize the perspective images with artistic aesthetic value. This process is invisible to the user, that is, the user does not need to select the camera. In addition, the user can choose to keep the perspective images shot by AI multi-view shooting or delete them, thereby meeting the diverse shooting needs and improving the experience.
[0039] S102, analyzing the constituent elements of each perspective picture according to the pre-trained AI model, and generating a target image based on the constituent elements of each perspective picture.
[0040] It should be noted that the components of the perspective image are, for example, people, roads, cars, flowers, or landscapes. The target image may include, but is not limited to, static images and dynamic images. Among them, a static image refers to an image whose state does not change over time, such as when all objects in the image are stationary; and a dynamic image refers to an image whose state changes over time, such as when there are moving objects in the image.
[0041] Specifically, the training process of the AI (Artificial Intelligence) model in the embodiment of the present application is as follows: first, a set of sample images is obtained, the set of sample images includes at least two sample images and labels associated with the sample images, wherein the labels include at least one of the composition method and light and shadow color matching method of the sample images; then, the constituent elements of each sample image are extracted respectively, and a mapping relationship between the constituent elements of the sample image and the labels is established. Since the AI model has been pre-learned and trained on the characteristics and advantages of a large number of images, that is to say, the AI model has aesthetic ability and can analyze the constituent elements of the picture in real time, thereby generating an image that is full of beauty and storytelling. In the actual use of the AI model, the constituent elements of each perspective picture are screened according to the learned composition method and / or light and shadow color matching method. Therefore, the target image obtained by the subsequent synthesis of each perspective picture is full of beauty and storytelling, which improves the quality of photography.
[0042] Optionally, the AI model in the embodiment of the present application may include but is not limited to a neural network model, which may include but is not limited to any one of a convolutional neural network model (CNN) or a recurrent neural network model (RNN).
[0043] Optionally, the embodiment of the present application performs synthesis processing on each perspective screened by the composition elements according to the composition mode and / or light and shadow color matching mode in the AI model to obtain a target image. The synthesis processing operation may include but is not limited to any one or more of zooming, cropping, background blurring, adjusting picture parameters or adding materials, so that the target image obtained is more artistic, interesting and storytelling.
[0044] It should be noted that the picture parameters may include but are not limited to color, brightness, contrast and resolution. The embodiment of the present application can improve the image quality of the target image by adjusting the picture parameters, making the image clearer and more delicate. The material may include but is not limited to an identifier, a text box and a pattern, such as an identifier of an arrow, an ellipse or a rectangular box, and a pattern of an emoticon. The embodiment of the present application can meet the diverse usage needs of users and enhance the interest of the target image by adding materials.
[0045] In some optional embodiments of the present application, there is a mapping relationship between each camera in the shooting mode combination of at least two cameras and the display area of the layout. Exemplarily, the layout includes a first display area 201 and a second display area 202, and the second display area 202 is superimposed on the first display area 201, and the area of the second display area 202 is smaller than the area of the first display area 201. The first display area 201 and the second display area 202 can be further divided according to the number of cameras. For example, assuming that the number of cameras is 5, the corresponding numbers of the cameras are ①, ②, ③, ④ and ⑤ respectively. For example Figure 2 As shown, the first display area 201 can be divided into two sub-display areas, which are filled with the viewing angle picture collected by camera No. ① and the viewing angle picture collected by camera No. ②, respectively, and the second display area can be divided into three sub-display areas, which are filled with the viewing angle picture collected by camera No. ③, the viewing angle picture collected by camera No. ④, and the viewing angle picture collected by camera No. ⑤, respectively. It should be noted that the viewing angle pictures filled in each sub-display area can be set as needed, and the embodiment of the present application does not limit this. For example, the two sub-display areas of the first display area 201 can also be filled with the viewing angle picture collected by camera No. ① and the viewing angle picture collected by camera No. ③, respectively, and the three sub-display areas of the second display area 202 are filled with the viewing angle picture collected by camera No. ②, the viewing angle picture collected by camera No. ④, and the viewing angle picture collected by camera No. ⑤, respectively. This avoids setting too many layouts, saves the memory of the electronic device, and facilitates calling.
[0046] Exemplarily, when the viewing angle pictures captured by at least two cameras include a first viewing angle picture captured by a first camera and a second viewing angle picture captured by a second camera, and the shooting mode corresponding to the second viewing angle picture is different from the shooting mode corresponding to the first viewing angle picture, the embodiment of the present application detects whether the constituent elements of the first viewing angle picture and the constituent elements of the second viewing angle picture match according to the AI model; if the constituent elements of the first viewing angle picture and the constituent elements of the second viewing angle picture match, the second viewing angle picture is retained. It should be noted that matching means that there is a correlation between the constituent elements of the first viewing angle picture and the constituent elements of the second viewing angle picture, and matching these two constituent elements can enhance the beauty and story of the target image generated subsequently. For example, the constituent elements of the first viewing angle picture and the constituent elements of the second viewing angle picture are associated in appearance, such as the constituent elements of the first viewing angle picture include skyscrapers, and the constituent elements of the second viewing angle picture include street lights. The appearances of these two constituent elements are both vertical, so the two can be matched in a vertical composition. For another example, the components of the first perspective picture and the components of the second perspective picture are related in terms of light and dark changes. For example, the components of the first perspective picture include the sunset, and the components of the second perspective picture include trees with shadows. Therefore, these two components can be matched by changing the light and shadow colors. Optionally, in some embodiments, the components of the first perspective picture and the components of the second perspective picture can be matched and detected according to the composition method and / or light and shadow color matching method preset in the AI model.
[0047] Furthermore, the embodiment of the present application calls a target layout that matches the shooting mode combination according to the shooting mode combination of the first camera and the second camera, fills the first perspective picture in the first target display area of the target layout, and fills the second perspective picture in the second target display area of the target layout to generate a target image.
[0048] Optionally, in some embodiments, when the magnification of the second viewing angle picture is greater than the magnification of the first viewing angle picture, the second target display area of the target layout is superimposed on the first target display area, and the area of the second target display area is smaller than the area of the first target display area. Figure 3 As shown, the first perspective picture includes the park path, and the second perspective picture includes fallen leaves. At this time, the second perspective picture with a larger magnification is placed in the upper small display frame, that is, the second target display area, and the first perspective picture with a smaller magnification is placed in the bottom large display frame, that is, the first target display area, so that the target image generated is more artistic.
[0049] Optionally, in some embodiments, when the magnification of the second viewing angle picture is greater than the magnification of the first viewing angle picture, the second target display area of the target layout is set below the first target display area, and the area of the second target display area is greater than the area of the first target display area. Figure 4 As shown, the first perspective image includes a bicycle, and the second perspective image includes a bicycle bell. At this time, the second perspective image with a larger magnification is placed in the large display frame of the bottom layer, that is, the second target display area, and the first perspective image with a smaller magnification is placed in the small display frame of the upper layer, that is, the first target display area, so that the target image generated is interesting.
[0050] To facilitate a better understanding of the multi-view shooting method of the embodiment of the present application, a detailed description is given below in conjunction with actual application scenarios. In some optional embodiments, it is assumed that at least two cameras include a first camera and a second camera. Exemplarily, the first camera can be a main camera, and the second camera can be a camera other than the first camera, such as a second camera. It can be understood that in a specific example, the second camera can be a secondary camera or multiple secondary cameras.
[0051] In actual use, such as Figure 5 As shown, it is an example of a multi-view shooting method provided by an embodiment of the present application, in which an AI multi-view button is set on the photo mode interface. When the user presses the shutter, the electronic device can automatically call other sub-cameras except the main camera for synchronous shooting, and present the perspectives of multiple cameras in one image, which is the target image. For example, when the shooting mode of the first camera is wide-angle mode and the shooting mode of the second camera is macro mode, that is, the first camera is a wide-angle main camera and the second camera is a macro sub-camera, the shooting mode combination matches the close-up layout. Exemplarily, as Figure 6 As shown, the close-up layout includes two display areas, namely a first display area 201 and a second display area 202, and the display area is not divided into sub-display areas. The second display area 202 is superimposed on the first display area 201, and the area of the second display area 202 is smaller than the area of the first display area 201. Since the magnification of the second viewing angle picture captured by the macro sub-camera is greater than the magnification of the first viewing angle picture captured by the wide-angle main camera, the first viewing angle picture is filled in the first display area 201 of the close-up layout, and the second viewing angle picture is filled in the second display area 202 of the close-up layout, which is more beautiful and storytelling. It can be understood that the first viewing angle picture captured by the wide-angle main camera can also be filled in the second display area 202 of the close-up layout, and the second viewing angle picture captured by the macro sub-camera can also be filled in the first display area 201 of the close-up layout, and the embodiment of the present application is not limited to this.
[0052] For another example, the layout that matches the shooting mode combination of the wide-angle main camera, the ultra-wide-angle secondary camera, and the telephoto secondary camera corresponds to the long-range layout. Figure 7 As shown, the perspective layout includes three display areas, namely, the first display area 201, the second sub-display area 2021 and the third sub-display area 2022, wherein the second sub-display area 2021 and the third sub-display area 2022 are obtained by dividing the second display area 202. The second sub-display area 2021 and the third sub-display area 2022 are respectively superimposed on the first display area 201, and the area of the second sub-display area 2021 and the area of the third sub-display area 2022 are both smaller than the area of the first display area 201. It can be understood that the second sub-display area 2021 and the third sub-display area 2022 can be Figure 7 The method shown is horizontally set, or Figure 8 For example, the first display area 201 of the telescopic layout is filled with the viewing angle image captured by the wide-angle main camera, the second sub-display area 2021 of the telescopic layout is filled with the viewing angle image captured by the ultra-wide-angle secondary camera, and the third sub-display area 2022 of the telescopic layout is filled with the viewing angle image captured by the telephoto secondary camera.
[0053] It should be noted that the embodiments of this application Figure 6 to Figure 8 In the illustrated format, the frame shapes of the second display area 202, the second sub-display area 2021, and the third sub-display area 2022 may include, but are not limited to, rectangles, circles, or polygons. For example, circles may include, but are not limited to, perfect circles or ellipses, and polygons may include, but are not limited to, five-pointed stars or regular hexagons. For example, the frame shapes of the second sub-display area 2021 and the third sub-display area 2022 are both rectangular; or, the frame shape of the second sub-display area 2021 is rectangular, and the frame shape of the third sub-display area 2022 is circular. The advantage of such a setting is that it can be applied to a variety of shooting scenes, and the use is more flexible and changeable, thereby further enhancing the beauty and story of the resulting image.
[0054] The embodiment of the present application provides a multi-view shooting method, which obtains the view images captured by at least two cameras, and then analyzes the constituent elements of each view image according to the pre-trained AI model, and generates a target image based on the constituent elements of each view image. Since the AI model has been pre-trained on the characteristics and advantages of a large number of images, that is, the AI model has aesthetic ability and can analyze the constituent elements of the image in real time, the target image obtained by combining the view images is beautiful and storytelling, which improves the quality of photography, while avoiding the tediousness of user selection of cameras and simplifying the process.
[0055] Based on the above examples, please refer to Fig. 9 , which is a schematic diagram of the structure of a multi-view shooting device provided in an embodiment of the present application, the device can be applied to Figures 1 to 8 In the multi-angle shooting method provided in the corresponding embodiment. Fig. 9 As shown, the multi-view shooting device 900 includes:
[0056] An acquisition module 901 is configured to acquire viewing angle images captured by at least two cameras;
[0057] The generation module 902 is configured to analyze the constituent elements of each perspective picture according to a pre-trained AI model, and generate a target image based on the constituent elements of each perspective picture.
[0058] Optionally, the AI model is trained through the following steps:
[0059] Acquire a sample image set, the sample image set comprising at least two sample images and tags associated with the sample images, the tags comprising at least one of a composition method and a light and shadow color matching method of the sample images;
[0060] The constituent elements of each sample image are extracted respectively, and a mapping relationship between the constituent elements of the sample image and the label is established.
[0061] Optionally, the AI model includes a neural network model, which includes any one of a convolutional neural network model or a recurrent neural network model.
[0062] Alternatively, if Fig.10 As shown, the generating module 902 in the multi-view shooting device 900 includes:
[0063] A screening unit 9021 is configured to screen the constituent elements of each perspective image according to the composition method and / or light and shadow color matching method in the AI model;
[0064] The synthesis unit 9022 is configured to perform synthesis processing on the perspective picture that has been screened by the component elements to obtain a target image.
[0065] Optionally, the synthesis processing operation includes any one or more of zooming, cropping, background blurring, adjusting picture parameters or adding materials.
[0066] Optionally, when the at least two cameras include a first camera and a second camera, as Fig.11 As shown, the multi-view shooting device 900 also includes an adjustment module 903, which is configured to respond to the user's operating instructions, and automatically adjust at least one second camera other than the first camera to focus and shoot the shooting object based on the shooting object displayed by the first camera in the imaging display area, wherein the first camera is the camera specified by the user.
[0067] Optionally, the generating module 902 in the multi-view shooting device 900 is further configured to detect, according to the AI model, whether the constituent elements of the first perspective picture and the constituent elements of the second perspective picture match when the perspective pictures captured by the at least two cameras include a first perspective picture captured by the first camera and a second perspective picture captured by the second camera, and the shooting mode corresponding to the second perspective picture is different from the shooting mode corresponding to the first perspective picture;
[0068] If the constituent elements of the first-viewing angle picture match the constituent elements of the second-viewing angle picture, the second-viewing angle picture is retained.
[0069] Optionally, the generating module 902 in the multi-view shooting device 900 is further configured to call a target format matching the shooting mode combination according to the shooting mode combination of the first camera and the second camera;
[0070] The first viewing angle picture is filled in the first target display area of the target layout, and the second viewing angle picture is filled in the second target display area of the target layout to generate a target image.
[0071] Optionally, when the magnification of the second viewing angle picture is greater than the magnification of the first viewing angle picture, the second target display area of the target format is superimposed on the first target display area, and the area of the second target display area is smaller than the area of the first target display area;
[0072] Alternatively, the second target display area of the target format is arranged below the first target display area, and the area of the second target display area is larger than the area of the first target display area.
[0073] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.
[0074] The embodiment of the present application provides a multi-view shooting device, wherein the acquisition module is configured to acquire the view images captured by at least two cameras, and then the generation module is configured to analyze the constituent elements of each view image according to a pre-trained AI model, and generate a target image based on the constituent elements of each view image. Since the AI model has been pre-trained on the characteristics and advantages of a large number of images, that is, the AI model has aesthetic ability and can analyze the constituent elements of the image in real time, the target image obtained by combining the view images is aesthetically pleasing and storytelling, which improves the quality of photography, while avoiding the tediousness of user selection of cameras and simplifying the process.
[0075] Based on the above examples, please refer to Fig.12, which is a structural block diagram of an electronic device provided in an embodiment of the present application. The electronic device 100 includes a processor 1001 and a memory 1002, wherein the processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1001 may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA).
[0076] The processor 1001 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state.
[0077] In addition, the processor 1001 may be integrated with a graphics processing unit (GPU), which is used to render and draw the content to be displayed on the display screen. In some embodiments, the processor 1001 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.
[0078] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one program, which is executed by the processor 1001 to implement the multi-view shooting method provided in the method embodiment of the present application.
[0079] In some embodiments, the electronic device 100 may further include a peripheral device interface 1003 and at least one peripheral device. The processor 1001, the memory 1002 and the peripheral device interface 1003 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1003 via a bus, a signal line or a circuit board.
[0080] Specifically, the peripheral devices include but are not limited to the radio frequency circuit 1004, the touch display screen 1005 and the power supply 1006. The peripheral device interface 1003 can be used to connect at least one peripheral device related to input / output (I / O) to the processor 1001 and the memory 1002. In some embodiments, the processor 1001, the memory 1002 and the peripheral device interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1001, the memory 1002 and the peripheral device interface 1003 can be implemented on a separate chip or circuit board, which is not limited in the embodiments of the present application.
[0081] The radio frequency circuit 1004 is used to receive and transmit radio frequency (RF) signals, also known as electromagnetic signals. The radio frequency circuit 1004 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1004 converts an electrical signal into an electromagnetic signal for transmission, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1004 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit 1004 can communicate with other devices through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a wireless fidelity (Wireless Fidelity, WiFi) network. In some embodiments, the radio frequency circuit 1004 may also include circuits related to near field communication (NFC).
[0082] The display screen 1005 is used to display a user interface (UI). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1005 is a touch display screen, the display screen 1005 also has the ability to collect touch signals on the surface or above the surface of the display screen 1005. The touch signal can be input to the processor 1001 as a control signal for processing. At this time, the display screen 1005 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1005 can be one, arranged on the front panel of the electronic device 100; in other embodiments, the display screen 1005 can be at least two, respectively arranged on different surfaces of the electronic device 100 or in a folding design; in some other embodiments, the display screen 1005 can be a flexible display screen, arranged on a curved surface or a folding surface of the electronic device 100. Even, the display screen 1005 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1005 can be prepared using materials such as a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.
[0083] Those skilled in the art will understand that Fig.12 The structure shown in the figure does not constitute a limitation on the electronic device 100, and the electronic device 100 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.
[0084] It should be noted that the electronic device 100 involved in the embodiments of the present application may include but is not limited to a personal digital assistant (PDA), a tablet computer, a wireless handheld device, a mobile phone, etc.
[0085] As another aspect, an embodiment of the present application provides a computer-readable storage medium for storing program code, where the program code is used to execute any one of the implementations of the multi-view shooting methods of the aforementioned embodiments.
[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0087] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.
[0088] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
[0089] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the multi-angle shooting method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.
[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A multi-view shooting method, characterized in that: The method comprises: Obtaining visual images captured by at least two cameras; Analyze the constituent elements of each of the perspective images according to the pre-trained AI model, and generate a target image based on the constituent elements of each of the perspective images; The at least two cameras include a first camera and a second camera. Before acquiring the viewing angle images captured by the at least two cameras, the method further includes: In response to a user's operation instruction, based on the photographing object displayed by the first camera in the imaging display area, automatically adjusting at least one of the second cameras other than the first camera to focus and shoot the photographing object, wherein the first camera is a camera designated by the user; When the viewing angle pictures captured by the at least two cameras include a first viewing angle picture captured by the first camera and a second viewing angle picture captured by the second camera, and the shooting mode corresponding to the second viewing angle picture is different from the shooting mode corresponding to the first viewing angle picture, analyzing the component elements of each of the viewing angle pictures according to the pre-trained AI model includes: According to the AI model, detecting whether the constituent elements of the first perspective picture and the constituent elements of the second perspective picture match; If the constituent elements of the first viewing angle picture match the constituent elements of the second viewing angle picture, the second viewing angle picture is retained.
2. The multi-view shooting method according to claim 1, characterized in that: The AI model is trained through the following steps: Acquire a sample image set, the sample image set comprising at least two sample images and tags associated with the sample images, the tags comprising at least one of a composition method and a light and shadow color matching method of the sample images; The constituent elements of each of the sample images are extracted respectively, and a mapping relationship between the constituent elements of the sample images and the labels is established.
3. The multi-view shooting method according to any one of claims 1 to 2, characterized in that: The AI model includes a neural network model, and the neural network model includes any one of a convolutional neural network model and a recurrent neural network model.
4. The multi-view shooting method according to claim 1, characterized in that: The analyzing the constituent elements of each of the perspective images according to the pre-trained AI model, and generating a target image based on the constituent elements of each of the perspective images, includes: Filter the constituent elements of each of the perspective images according to the composition method and / or light and shadow color matching method in the AI model; The target image is obtained by synthesizing the viewing angle images selected by the component elements.
5. The multi-view shooting method according to claim 4, characterized in that: The synthesis processing operation includes any one or more of zooming, cropping, background blurring, adjusting picture parameters or adding materials.
6. The multi-view shooting method according to claim 1, characterized in that: The generating a target image based on the constituent elements of each of the viewing angle pictures comprises: According to the shooting mode combination of the first camera and the second camera, calling a target layout matching the shooting mode combination; The first viewing angle picture is filled in a first target display area of the target layout, and the second viewing angle picture is filled in a second target display area of the target layout, so as to generate the target image.
7. The multi-view shooting method according to claim 6, characterized in that: When the magnification of the second viewing angle picture is greater than the magnification of the first viewing angle picture, the second target display area of the target format is superimposed on the first target display area, and the area of the second target display area is smaller than the area of the first target display area; Alternatively, when the magnification of the second viewing angle picture is greater than that of the first viewing angle picture, the second target display area of the target layout is set below the first target display area, and the area of the second target display area is greater than that of the first target display area.
8. A multi-view shooting device, characterized in that: The device comprises: An acquisition module configured to acquire viewing angle images captured by at least two cameras; A generation module configured to analyze the constituent elements of each of the perspective images according to a pre-trained AI model, and generate a target image based on the constituent elements of each of the perspective images; When the at least two cameras include a first camera and a second camera, the multi-view shooting device further includes an adjustment module configured to respond to an operation instruction of a user, and automatically adjust at least one second camera other than the first camera to focus and shoot the shooting object based on the shooting object displayed by the first camera in the imaging display area, wherein the first camera is a camera designated by the user; The generating module is further configured to: When the perspective images captured by at least two cameras include a first perspective image captured by a first camera and a second perspective image captured by a second camera, and the shooting mode corresponding to the second perspective image is different from the shooting mode corresponding to the first perspective image, detecting, according to the AI model, whether the constituent elements of the first perspective image and the constituent elements of the second perspective image match; If the constituent elements of the first-viewing angle picture match the constituent elements of the second-viewing angle picture, the second-viewing angle picture is retained.
9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the multi-view shooting method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the multi-view shooting method as described in any one of claims 1 to 7.
