An AI vision-based real-time photography guidance system, method, medium and terminal

Abstract

The application provides an AI vision-based real-time photography guidance system, method, medium and terminal, which is applied to a mobile terminal, integrates core elements affecting the shooting effect by deep linkage of local offline AI vision recognition and a professional photography skill database, and forms a standardized shooting guidance scheme. In the shooting process, the shooting scene is analyzed in real time, shooting parameters and operation steps are dynamically pushed, and the user is guided in real time in multiple forms and deviation correction to complete the shooting, thereby constructing a closed-loop dynamic guidance system. The application is locally offline in the whole process and does not need network connection, thereby eliminating the cost, delay and privacy risk caused by cloud dependence, and the technical architecture is not bound to a specific AI model or framework, and the universality is high. Compared with the existing static auxiliary scheme, the application can significantly reduce the threshold of professional photography, help ordinary users without photography foundation to quickly master the shooting skills and improve the quality of the finished product.

Description

Technical Field

[0001] This invention relates to the field of mobile terminals, and in particular to a real-time photography guidance system, method, medium, and terminal based on AI vision. Background Technology

[0002] With the rapid improvement of mobile terminal hardware performance and the popularization of artificial intelligence technology, smartphones have become the most important photography tool for the general public. Statistics show that the number of photos taken globally each year by mobile phones exceeds 1.4 trillion. To meet the diverse shooting needs of users, a wide variety of photography-related mobile applications have emerged in the market.

[0003] These photography-related mobile applications can be broadly categorized into three types. The first type is the system's native camera app, which typically offers basic photo and video recording functions and manual parameter adjustment. Some products also include simple AI beautification, night scene enhancement, or static composition assistance. The second type is post-processing apps, such as Meitu and Xingtu. These apps focus on post-photo processing, including filter enhancement, portrait retouching, image quality enhancement, background replacement, and other post-editing operations. The third type is professional camera apps, geared towards users with some photography experience, offering richer manual parameter adjustment, RAW format shooting, and professional filters.

[0004] In recent years, AI vision technology has been gradually applied to the field of photography. Some photography products have already achieved features such as automatic scene recognition, portrait background blurring, and intelligent composition. The application of these technologies has lowered the barrier to entry for users to take photos to some extent. However, existing technical solutions still have several fundamental flaws that are difficult to overcome, making it difficult for ordinary users without professional photography skills to achieve high-quality shooting results: the guidance process is seriously lagging behind, focusing only on post-processing; the composition assistance function is limited and lacks scene adaptability; it does not integrate a professional photography knowledge system, resulting in insufficient guidance depth; it lacks real-time operation deviation correction and does not form a closed-loop guidance; and it relies heavily on the cloud, posing cost and privacy issues. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a real-time photography guidance system, method, medium and terminal based on AI vision, which solves the problems that existing photography applications can only provide post-editing or single static composition assistance, cannot solve the full process guidance for ordinary users before and during shooting, and lack personalized selection space.

[0006] To achieve the above and other related objectives, a first aspect of the present invention provides a real-time photography guidance system based on AI vision, applied to a mobile terminal, comprising: a camera acquisition module for real-time acquisition of viewfinder video stream and obtaining current basic camera parameter information; an AI offline visual recognition module connected to the camera acquisition module for multi-dimensional analysis and recognition of the viewfinder video stream at a preset frequency to obtain multi-dimensional recognition results; a professional photography skill matching module connected to the AI ​​offline visual recognition module for matching the multi-dimensional recognition results with a built-in structured professional photography skill database to obtain multiple shooting guidance schemes adapted to the current scene; a multi-scheme generation and selection module connected to the professional photography skill matching module for selecting multiple candidate shooting guidance schemes representing different styles and shooting effects from the obtained shooting guidance schemes, and obtaining a standard shooting scheme selected by the user from the candidate shooting guidance schemes; and a real-time interactive guidance module connected to the multi-scheme generation and selection module for generating interactive guidance operation instructions based on the standard shooting scheme selected by the user, guiding the user to make shooting adjustments and complete the shooting, and generating a shooting effect review report and saving the shooting scheme.

[0007] In some embodiments of the first aspect of the present invention, the AI ​​offline visual recognition module includes: a scene classification and recognition unit, used to perform scene classification and recognition on the viewfinder video stream to obtain the current shooting scene type; a human posture detection unit, used to obtain human posture data based on the viewfinder video stream; wherein the human posture data includes at least: the standing position, posture, and distance of the subject from the photographer, as well as the height and angle of the photographer's camera position; and a picture composition analysis unit, used to obtain picture composition and environmental element information based on the viewfinder video stream; wherein the picture composition and environmental element information includes at least: subject position, foreground, background, picture element analysis, white space ratio, and lighting conditions.

[0008] In some embodiments of the first aspect of the present invention, the step of matching the multi-dimensional recognition results with a built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene includes: automatically matching the scene characteristics of the multi-dimensional recognition results with the professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; wherein each shooting guidance scheme includes at least: shooting posture, camera height, zoom range, composition method, camera parameter information, shooting distance, and style tags.

[0009] In some embodiments of the first aspect of the present invention, the step of selecting multiple typical shooting guidance schemes representing different styles and shooting effects from the obtained shooting guidance schemes, and obtaining the standard shooting scheme selected by the user from each typical shooting guidance scheme includes: selecting multiple candidate shooting guidance schemes representing different styles and shooting effects from the obtained multiple shooting guidance schemes, and displaying their operation instructions on the display interface; when a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, the selected candidate shooting guidance scheme is used as the standard shooting scheme; when a refresh instruction is triggered by the user on the display interface, new candidate shooting guidance schemes are selected again from the obtained multiple shooting guidance schemes and displayed, and the operation is repeated until a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, and the selected candidate shooting guidance scheme is used as the standard shooting scheme.

[0010] In some embodiments of the first aspect of the present invention, the real-time interactive guidance module includes: a visual guidance unit, configured to generate visual guidance operation instructions based on the user-selected standard shooting scheme and display them on the camera viewfinder; wherein the visual guidance operation instructions include at least: dynamic composition guide lines, subject position markers, and camera position adjustments; a text guidance unit, configured to generate text guidance operation instructions based on the user-selected standard shooting scheme and display them in a specific display area; a voice guidance unit, configured to generate voice guidance instructions based on the user-selected standard shooting scheme and play the voice; a deviation correction guidance unit, configured to generate targeted deviation correction guidance instructions based on the deviation between the user's shooting operation and the user-selected standard shooting scheme detected in real time, and push them out; and a data storage unit, configured to generate a shooting effect review report and save the shooting effect review report and shooting guidance scheme.

[0011] In some embodiments of the first aspect of the present invention, the system further includes a parameter control module connected to the real-time interactive guidance module, used to automatically adjust the basic camera parameter information or recommend optimal parameter settings to the user based on the standard shooting scheme selected by the user.

[0012] In some embodiments of the first aspect of the present invention, the camera basic parameter information includes at least: zoom magnification, focus position, and exposure parameters.

[0013] To achieve the above and other related objectives, a second aspect of the present invention provides a real-time photography guidance method based on AI vision, comprising: applying any of the above-described real-time photography guidance systems based on AI vision, the method comprising: real-time acquisition of viewfinder video stream and obtaining current camera basic parameter information; performing multi-dimensional analysis and recognition on the viewfinder video stream at a preset frequency to obtain multi-dimensional recognition results; matching the multi-dimensional recognition results with a built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; filtering the obtained multiple shooting guidance schemes to obtain multiple candidate shooting guidance schemes representing different styles and shooting effects, and obtaining a standard shooting scheme selected by the user from each candidate shooting guidance scheme; generating interactive guidance operation instructions based on the standard shooting scheme selected by the user, guiding the user to make shooting adjustments and complete the shooting, and generating a shooting effect review report and saving the shooting scheme.

[0014] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described above.

[0015] To achieve the above and other related objectives, a fourth aspect of the present invention provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method described above.

[0016] As described above, the present invention has the following beneficial effects:

[0017] This invention provides a real-time photography guidance system, method, medium, and terminal based on AI vision, applicable to mobile terminals. By deeply linking local offline AI visual recognition with a professional photography skills database, it integrates core elements affecting shooting results to form a standardized shooting guidance scheme. During the shooting process, the shooting scene is analyzed in real time, dynamically pushing shooting parameters and operation steps, and assisting users to complete the shooting with real-time guidance and deviation correction in multiple forms, constructing a closed-loop dynamic guidance system. This invention operates entirely locally offline, requiring no network connection, eliminating the cost, latency, and privacy risks associated with cloud reliance, and its technical architecture is not bound to a specific AI model or framework, making it highly versatile. Compared to existing static assistance solutions, this invention can significantly lower the barrier to professional photography, helping ordinary users with no photography experience quickly master shooting skills and improve the quality of their final images. Attached Figure Description

[0018] Figure 1 The diagram shown is a structural schematic of a real-time photography guidance system based on AI vision according to an embodiment of the present invention.

[0019] Figure 2 The diagram shown is a structural schematic of a real-time photography guidance system based on AI vision according to an embodiment of the present invention.

[0020] Figure 3 The diagram shown is a flowchart illustrating a real-time photography guidance method based on AI vision, according to an embodiment of the present invention.

[0021] Figure 4 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of the present invention. Detailed Implementation

[0022] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0023] In embodiments of the present invention, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0024] It should be noted that in the embodiments of the present invention, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0025] In this embodiment of the invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0026] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0027] <1> AI visual recognition, or Artificial Intelligence Visual Recognition, also known as computer vision recognition, is a core subfield of artificial intelligence. It refers to the ability of machines to automatically extract key features from images or videos, identify target objects, understand scene semantics, and output structured decision results using technologies such as deep learning and computer vision. Essentially, it transforms visualized image information into machine-processable digital signals, completing the automated analysis from "pixel" to "cognition."

[0028] <2> Cloud APIs, or Cloud Application Programming Interfaces, are collections of interfaces deployed on cloud servers that can be called by external programs. They serve as standardized channels for cloud platforms to provide services. Developers do not need to build underlying hardware, deploy complex services, or maintain servers; they only need to send requests according to agreed-upon rules to remotely access cloud computing power, algorithms, data, and functional modules, enabling data interaction and functional linkage between different software, terminals, and cloud services.

[0029] <3> SDK, or Software Development Kit, is a complete set of development tools provided to developers. It is usually presented in the form of library files, API interfaces, development documentation, sample code (demo), and debugging tools. It aims to help developers quickly integrate specific functions and build applications without having to delve into the underlying implementation details.

[0030] To facilitate understanding of the embodiments of the present invention, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 A schematic diagram of a real-time photography guidance system based on AI vision, as shown in this embodiment of the invention, is illustrated. This AI vision-based real-time photography guidance system, applied to a mobile terminal, mainly includes: a camera acquisition module 1, an AI offline visual recognition module 2, a professional photography skill matching module 3, a multi-scheme generation and selection module 4, and a real-time interactive guidance module 5.

[0031] Camera acquisition module 1 is used to acquire the viewfinder image stream in real time and obtain the current basic camera parameter information;

[0032] AI offline visual recognition module 2 is connected to the camera acquisition module 1 and is used to perform multi-dimensional analysis and recognition on the viewfinder stream at a preset frequency to obtain multi-dimensional recognition results.

[0033] The professional photography skills matching module 3 is connected to the AI ​​offline visual recognition module 2 and is used to match the multi-dimensional recognition results with the built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene.

[0034] The multi-scheme generation and selection module 4 is connected to the professional photography skills matching module 3. It is used to filter out multiple sets of candidate shooting guidance schemes that represent different styles and shooting effects from the obtained shooting guidance schemes, and to obtain the standard shooting scheme selected by the user from each candidate shooting guidance scheme.

[0035] The real-time interactive guidance module 5 is connected to the multi-scheme generation and selection module 4. It is used to generate interactive guidance operation instructions based on the standard shooting scheme selected by the user, guide the user to make shooting adjustments and complete the shooting, and generate a shooting effect review report and save the shooting scheme.

[0036] The system first launches the relevant applications on the mobile terminal. The camera acquisition module 1 acquires the viewfinder stream of the camera in real time and simultaneously acquires the current basic parameter information of the camera to provide a data foundation for the AI ​​offline visual recognition module 2.

[0037] In one specific embodiment, the camera's basic parameter information includes at least: zoom magnification, focus position, and exposure parameters.

[0038] In one specific embodiment, the AI ​​offline visual recognition module 2 includes:

[0039] Scene classification and recognition unit 21 is used to classify and recognize the current shooting scene type by analyzing the viewfinder image stream; human posture detection unit 22 is used to acquire human posture data based on the viewfinder image stream; wherein, the human posture data includes at least: the position, posture, and distance of the subject from the photographer, as well as the height and angle of the photographer's camera position; image composition analysis unit 23 is used to acquire image composition and environmental element information based on the viewfinder image stream; wherein, the image composition and environmental element information includes at least: subject position, foreground, background, image element analysis, white space ratio, and lighting conditions.

[0040] The system activates the local offline AI visual recognition module 2 to perform multi-dimensional analysis and recognition of the viewfinder stream at a preset frequency, obtaining multi-dimensional recognition results. These multi-dimensional recognition results include at least: the current shooting scene type, human posture information, image composition, and ambient lighting conditions.

[0041] Furthermore, the AI ​​offline visual recognition module 2 utilizes the scene classification and recognition unit 21, the human posture detection unit 22, and the image composition analysis unit 23 to perform multi-dimensional recognition and analysis on the viewfinder image stream, and obtain the multi-dimensional recognition results.

[0042] Specifically, the AI ​​offline visual recognition module 2 mainly completes the following three core recognition tasks: First, scene classification recognition: identifying the type of the current shooting scene, including but not limited to portrait, full-body portrait, landscape, sunset, architecture, street, green plants, lakeside, night scene, indoor store exploration, etc.; Second, human posture detection: detecting the position, posture, and distance of the subject from the photographer, as well as the height and angle of the photographer's camera position; Third, image composition analysis: analyzing the position of the subject, foreground, background, distribution of image elements, white space ratio, lighting conditions, and other related composition and environmental elements in the image.

[0043] Furthermore, the AI ​​offline visual recognition module 2 is deployed locally on the mobile terminal and employs any type of lightweight mobile AI visual recognition model. This AI visual recognition model includes, but is not limited to, frameworks such as TFLite, ONNX, and PyTorch Mobile, or visual models provided by open-source, self-developed, or third-party SDKs. Moreover, all AI recognition calculations, multi-scheme generation, data processing, and guidance scheme generation are completed locally on the mobile terminal, eliminating the need to upload the user's viewfinder stream to a cloud server. This not only significantly reduces network latency and improves response speed but also completely avoids the risk of user privacy leaks, while eliminating the high operating costs associated with cloud API calls.

[0044] In one specific embodiment, matching the multi-dimensional recognition results with a built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene includes:

[0045] The scene characteristics of the multi-dimensional recognition results are automatically matched with the professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; wherein each shooting guidance scheme includes at least: shooting posture, camera position height, zoom range, composition method, camera parameter information, shooting distance and style tags.

[0046] The mobile terminal includes a pre-built professional photography skills database. This database stores multiple differentiated shooting guidance schemes for different shooting scenarios. Each scheme includes core elements such as shooting posture, camera height, zoom range, composition method, shooting distance, and style tags (e.g., atmosphere, sophistication, documentary style, fresh style). Based on the recognition results obtained from the AI ​​offline visual recognition module 2, the professional photography skills database automatically retrieves and matches multiple shooting guidance schemes suitable for the current scene.

[0047] The professional photography skills database employs a structured design, transforming the shooting experience of professional photographers into standardized data that can be recognized and matched by computers. Each solution is labeled with style tags and applicable scenarios. Furthermore, the database integrates the four core elements affecting shooting results—shooting posture, camera height, zoom level, and composition—to form standardized shooting guidance solutions, rather than providing fragmented suggestions for individual elements. Based on the characteristics of different scenarios, it automatically matches the optimal combination of these four elements, ensuring users receive complete and actionable shooting guidance. The database also supports subsequent iterative updates and expansions, allowing for the continuous addition of shooting scenarios and corresponding differentiated guidance solutions, enhancing the system's applicability and professionalism.

[0048] In one specific embodiment, the step of selecting multiple typical shooting guidance schemes representing different styles and shooting effects from the obtained shooting guidance schemes, and obtaining the standard shooting scheme selected by the user from each typical shooting guidance scheme, includes: selecting multiple candidate shooting guidance schemes representing different styles and shooting effects from the obtained multiple shooting guidance schemes, and displaying their operation instructions on the display interface; when a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, the selected candidate shooting guidance scheme is used as the standard shooting scheme; when a refresh instruction is triggered by the user on the display interface, new candidate shooting guidance schemes are selected again from the obtained multiple shooting guidance schemes and displayed, and the operation is repeated until a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, and the selected candidate shooting guidance scheme is used as the standard shooting scheme.

[0049] The specific methods for users to select a standard shooting plan from various typical shooting guidelines include:

[0050] Step S21: Select multiple shooting guidance schemes from the obtained multiple shooting guidance schemes that represent different styles and shooting effects, and display their operation instructions on the display interface;

[0051] Step S22: When the user triggers the command to select a candidate shooting guidance scheme on the display interface, the selected candidate shooting guidance scheme is taken as the standard shooting scheme.

[0052] Step S23: When a refresh command triggered by the user on the display interface is received, a new candidate shooting guidance scheme is selected from the multiple shooting guidance schemes and displayed.

[0053] Repeat steps S22 to S23 until the user-selected standard scheme is obtained and the image is taken.

[0054] Specifically, from the multiple shooting guidance schemes adapted to the current scene, at least three shooting guidance schemes with significantly different styles and effects are selected for the same shooting scene. For example, in portrait scenes, different schemes such as "atmospheric low-angle shot," "high-end centered composition," and "documentary-style rule of thirds composition" can be generated. Furthermore, a corresponding effect preview image, style description, and core operation points are generated for each shooting guidance scheme, presented to the user in the form of cards or lists on the camera viewfinder for the user to choose from.

[0055] Meanwhile, if the user is not satisfied with the selected shooting guidelines, the interface also displays a refresh trigger entry, allowing the user to choose again. The system continuously monitors whether the user has triggered a refresh. If the user does, it generates a new batch of shooting guidelines with distinct styles and effects for the user to choose from. If the user does not trigger a refresh, they can continue shooting according to the selected standard shooting guide.

[0056] In one specific embodiment, the real-time interactive guidance module 5 includes:

[0057] A visual guidance unit 51 is used to generate visual guidance operation instructions based on the standard shooting scheme selected by the user and display them on the camera viewfinder; wherein, the visual guidance operation instructions include at least: dynamic composition guide lines, subject position markers, and camera position adjustments; a text guidance unit 52 is used to generate text guidance operation instructions based on the standard shooting scheme selected by the user and display them in a specific display area; a voice guidance unit 53 is used to generate voice guidance instructions based on the standard shooting scheme selected by the user and play the voice; a deviation correction guidance unit 54 is used to generate targeted deviation correction guidance instructions based on the deviation between the user's shooting operation and the standard shooting scheme selected by the user detected in real time, and push them out; a data storage unit 55 is used to generate a shooting effect review report and save the shooting effect review report and shooting guidance scheme.

[0058] The real-time interactive guidance module 5 converts the standard shooting guidance scheme selected by the user into operation instructions that the user can directly execute, and presents them to the user in real time through various interactive forms.

[0059] Specifically, the visual guidance unit 51 transforms the user-selected standard shooting guide into visual guidance operation instructions by overlaying dynamic composition guidelines, subject position markers, and camera position adjustment instructions onto the camera viewfinder and displays them thereon. The text guidance unit 52 transforms the user-selected standard shooting guide into text guidance operation instructions in the form of a floating pop-up or fixed-area text and displays them thereon. The voice guidance unit 53 transforms the user-selected standard shooting guide into voice guidance instructions through voice broadcasting and plays the voice message. The deviation correction guidance unit 54 generates targeted adjustment instructions by real-time detection of the deviation between the user's shooting operation and the selected standard plan, transforms them into deviation correction guidance instructions, and pushes them out.

[0060] For example, interactive guidance instructions include, but are not limited to, the following forms: overlaying dynamic composition guide lines, subject position markers, camera position adjustment instructions, fixed area text display, and voice broadcast (e.g., "Please lower the camera position", "Please adjust to 2.5x zoom", "Please move the subject to the bottom third line of the frame").

[0061] The data storage unit 55 is used to generate a shooting effect review report and save the shooting effect review report and shooting guidance plan. The shooting effect review report includes at least: analysis of the shooting advantages and disadvantages and subsequent optimization suggestions; the saved shooting plan includes at least: saving the geographical location of this shooting and the shooting guidance plan for this shooting.

[0062] Specifically, after a user completes a shot, the system generates a shooting effect review report and provides access to view and share the report, allowing users to easily review its contents or share it with other users for shooting reference. Simultaneously, the shooting location and specific photography instructions, such as specific ISO parameters, are also saved. The shooting effect review report analyzes the strengths and weaknesses of the shot, provides suggestions for future optimization, and offers a complete shooting guide.

[0063] For example, if a user takes a particularly good photo or one they like at a scenic spot, they can share a review report of the shooting experience and their thoughts. The system will automatically save the user's actions during the shooting process, along with relevant camera parameters, the shooting location, the subject's pose, the camera position, and other parameters, which can then be displayed on the mobile device. If a saved location and shooting plan are analyzed and matched against a professional photography skills database and confirmed to produce the best results, the relevant shooting information will be stored in the professional photography skills database, allowing for database updates and expansions.

[0064] In one specific embodiment, the system further includes a parameter control module 6, which is connected to the real-time interactive guidance module 5, and is used to automatically adjust the basic camera parameter information or recommend the optimal parameter settings to the user based on the standard shooting scheme selected by the user.

[0065] like Figure 2 The diagram shown is a structural schematic of a real-time photography operation guidance system based on AI vision provided in an embodiment of the present invention. The parameter control module 6 automatically adjusts the corresponding camera parameters, such as zoom level, focus mode, and exposure compensation, according to the standard shooting guidance scheme selected by the user, or recommends optimal parameter settings to the user to assist in optimizing shooting parameters.

[0066] Figure 3 This is a flowchart illustrating a real-time photography operation guidance method based on AI vision provided in an embodiment of the present invention. Figure 3 As shown, the method includes:

[0067] Step S41: Real-time acquisition of viewfinder video stream and acquisition of current camera basic parameter information.

[0068] In one embodiment, step S41 includes: the camera basic parameter information includes at least: zoom magnification, focus position and exposure parameters.

[0069] Step S42: Perform multi-dimensional analysis and recognition on the viewfinder stream according to a preset frequency to obtain multi-dimensional recognition results.

[0070] In one embodiment, step S42 includes: the AI ​​offline visual recognition module includes: a scene classification and recognition unit 21, used to perform scene classification and recognition on the viewfinder video stream to obtain the current shooting scene type; a human posture detection unit 22, used to obtain human posture data based on the viewfinder video stream; wherein the human posture data includes at least: the standing position, posture, and distance from the photographer of the shooting object, as well as the height and angle of the photographer's camera position; and a picture composition analysis unit 23, used to obtain picture composition and environmental element information based on the viewfinder video stream; wherein the picture composition and environmental element information includes at least: the position of the subject, the foreground, the background, picture element analysis, the white space ratio, and the lighting conditions.

[0071] Step S43: Match the multi-dimensional recognition results with the built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene.

[0072] In one embodiment, step S43 includes: automatically matching the scene characteristics of the multi-dimensional recognition results with the professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; wherein, the shooting guidance scheme includes at least: shooting posture, camera position height, zoom range, composition method, camera parameter information, shooting distance and style tags.

[0073] Step S44: Filter the multiple shooting guidance schemes obtained to obtain multiple candidate shooting guidance schemes representing different styles and shooting effects, and obtain the standard shooting scheme selected by the user from each candidate shooting guidance scheme.

[0074] In one embodiment, step S44 includes: selecting multiple sets of candidate shooting guidance schemes representing different styles and shooting effects from the multiple sets of obtained shooting guidance schemes, and displaying their operation instructions on the display interface; when a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, the selected candidate shooting guidance scheme is used as the standard shooting scheme; when a refresh instruction is triggered by the user on the display interface, a new candidate shooting guidance scheme is selected from the multiple sets of obtained shooting guidance schemes and displayed, and the operation is repeated until a user triggers an instruction to select a candidate shooting guidance scheme on the display interface, and the selected candidate shooting guidance scheme is used as the standard shooting scheme.

[0075] Step S45: Generate interactive guidance operation instructions based on the standard shooting scheme selected by the user, guide the user to make shooting adjustments and complete the shooting, and generate a shooting effect review report and save the shooting scheme.

[0076] In one embodiment, step S45 includes: the real-time interactive guidance module includes: a visual guidance unit 51, used to generate visual guidance operation instructions based on the standard shooting scheme selected by the user and display them on the camera viewfinder; wherein the visual guidance operation instructions include at least: dynamic composition guide lines, subject position markers, and camera position adjustments; a text guidance unit 52, used to generate text guidance operation instructions based on the standard shooting scheme selected by the user and display them in a specific display area; a voice guidance unit 53, used to generate voice guidance instructions based on the standard shooting scheme selected by the user and play the voice; a deviation correction guidance unit 54, used to generate targeted deviation correction guidance instructions based on the deviation between the user's shooting operation and the standard shooting scheme selected by the user detected in real time, and push them out; and a data storage unit 55, used to generate a shooting effect review report and save the shooting effect review report and shooting guidance scheme.

[0077] In one embodiment, step S45 further includes: the system further includes a parameter control module, used to automatically adjust the camera's basic parameter information or recommend the optimal parameter settings to the user based on the standard shooting scheme selected by the user.

[0078] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0079] It should also be understood that the module division in the embodiments of the present invention is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of the present invention can be integrated into a single processor, exist as separate physical entities, or two or more modules can be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0080] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to perform the method of any of the embodiments described above.

[0081] Figure 4 This is a schematic block diagram of an electronic terminal provided in an embodiment of the present invention. Figure 4 As shown, the electronic terminal 400 includes at least one processor 401, a memory 402, at least one network interface 403, and a user interface 405. The various components in the electronic terminal 400 are coupled together via a bus system 404. It is understood that the bus system 404 is used to implement communication between these components. In addition to a data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 4 The general will label all buses as bus systems.

[0082] The user interface 405 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0083] It is understood that memory 402 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0084] In this embodiment of the invention, the memory 402 is used to store various types of data to support the operation of the electronic terminal 400. Examples of this data include: any executable program for operation on the electronic terminal 400, such as the operating system 4021 and application program 4022; the operating system 4021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 4022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The real-time photography operation guidance method based on AI vision provided in this embodiment of the invention can be included in the application program 4022.

[0085] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 401 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 401 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in a memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0086] In an exemplary embodiment, the electronic terminal 400 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0087] In summary, this invention provides a real-time photography guidance system, method, medium, and terminal based on AI vision, applicable to mobile terminals. By deeply linking local offline AI visual recognition with a professional photography skills database, it integrates core elements affecting shooting results to form a standardized shooting guidance scheme. During the shooting process, the shooting scene is analyzed in real time, dynamically pushing shooting parameters and operation steps, and assisting users to complete the shooting with real-time guidance and deviation correction in multiple forms, constructing a closed-loop dynamic guidance system. This invention operates entirely locally offline, requiring no network connection, eliminating the cost, latency, and privacy risks associated with cloud reliance, and its technical architecture is not bound to a specific AI model or framework, making it highly versatile. Compared to existing static assistance solutions, this invention can significantly lower the barrier to professional photography, helping ordinary users with no photography background quickly master shooting skills and improve the quality of their final images.

[0088] Therefore, this invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0089] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A real-time photography guidance system based on AI vision, characterized in that, Applied to mobile terminals, including: The camera acquisition module is used to acquire the viewfinder image stream in real time and obtain the current basic camera parameter information; The AI ​​offline visual recognition module is connected to the camera acquisition module and is used to perform multi-dimensional analysis and recognition on the viewfinder stream at a preset frequency to obtain multi-dimensional recognition results. A professional photography skills matching module, connected to the AI ​​offline visual recognition module, is used to match the multi-dimensional recognition results with the built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene. The multi-scheme generation and selection module is connected to the professional photography skills matching module. It is used to filter out multiple sets of candidate shooting guidance schemes that represent different styles and shooting effects from the obtained shooting guidance schemes, and to obtain the standard shooting scheme selected by the user from each candidate shooting guidance scheme. The real-time interactive guidance module, connected to the multi-scheme generation and selection module, is used to generate interactive guidance operation instructions based on the standard shooting scheme selected by the user, guide the user to make shooting adjustments and complete the shooting, and generate a shooting effect review report and save the shooting scheme.

2. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The AI ​​offline visual recognition module includes: A scene classification and recognition unit is used to classify and recognize the current shooting scene type by performing scene classification and recognition on the viewfinder image stream; A human posture detection unit is used to acquire human posture data based on the viewfinder image stream; wherein, the human posture data includes at least: the standing position, posture, and distance of the subject from the photographer, as well as the height and angle of the photographer's position. The image composition analysis unit is used to acquire image composition and environmental element information based on the framing image stream; wherein, the image composition and environmental element information includes at least: subject position, foreground, background, image element analysis, white space ratio and lighting conditions.

3. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The step of matching the multi-dimensional recognition results with a built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene includes: The scene characteristics of the multi-dimensional recognition results are automatically matched with the professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; each shooting guidance scheme includes at least: shooting posture, camera height, zoom range, composition method, camera parameter information, shooting distance and style tags.

4. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The process of selecting multiple candidate shooting guidance schemes representing different styles and shooting effects from the obtained shooting guidance schemes, and obtaining the standard shooting scheme selected by the user from each candidate shooting guidance scheme, includes: From the multiple shooting guidance schemes obtained, select several alternative shooting guidance schemes that represent different styles and shooting effects, and display their operation instructions on the display interface; When a user triggers an instruction on the display interface to select a candidate shooting guidance scheme, the selected candidate shooting guidance scheme is used as the standard shooting scheme. When a refresh command is received from the user on the display interface, a new candidate shooting guidance scheme is selected from the multiple shooting guidance schemes and displayed. This process is repeated until a command is received from the user to select a candidate shooting guidance scheme on the display interface. The selected candidate shooting guidance scheme is then used as the standard shooting scheme.

5. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The real-time interactive guidance module includes: A visual guidance unit is used to generate visual guidance operation instructions based on the standard shooting scheme selected by the user and display them on the camera viewfinder; wherein, the visual guidance operation instructions include at least: dynamic composition guide lines, subject position markers, and camera position adjustments; The text guidance unit is used to generate text guidance operation instructions based on the standard shooting scheme selected by the user, and display them in a specific display area; The voice guidance unit is used to generate voice guidance instructions based on the standard shooting scheme selected by the user and to play the voice instructions outward. The deviation correction guidance unit is used to generate targeted deviation correction guidance instructions based on the deviation between the user's shooting operation detected in real time and the standard shooting scheme selected by the user, and then push them out. The data storage unit is used to generate a shooting effect review report and save the shooting effect review report and shooting guidance plan.

6. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The system also includes a parameter control module, which is connected to the real-time interactive guidance module, and is used to automatically adjust the basic camera parameters or recommend the optimal parameter settings to the user based on the standard shooting scheme selected by the user.

7. The real-time photography guidance system based on AI vision according to claim 1, characterized in that, The basic camera parameters include at least: zoom level, focus position, and exposure parameters.

8. A real-time photography guidance method based on AI vision, characterized in that, include: The method of using the AI ​​vision-based real-time photography guidance system as described in any one of claims 1-7 includes: Real-time acquisition of viewfinder video stream and acquisition of current basic camera parameter information; The viewfinder stream is analyzed and identified in multiple dimensions according to a preset frequency to obtain multi-dimensional recognition results; The multi-dimensional recognition results are matched with the built-in structured professional photography skills database to obtain multiple shooting guidance schemes adapted to the current scene; The multiple shooting guidance schemes obtained are screened to obtain multiple alternative shooting guidance schemes representing different styles and shooting effects, and the standard shooting scheme selected by the user from each alternative shooting guidance scheme is obtained. Based on the standard shooting plan selected by the user, interactive guidance instructions are generated to guide the user to make shooting adjustments and complete the shooting, and a shooting effect review report is generated and the shooting plan is saved.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in claim 8.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method as described in claim 8.

Images