Shooting assisting method and device, storage medium and electronic equipment
The shooting assistance method improves photo quality by using multi-dimensional feature extraction and posture prediction to guide optimal shooting poses, addressing limitations in existing photo matching technologies.
Patent Information
- Application Number
- CN202411329686.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-12-06
AI Technical Summary
The quality of photos taken with devices like mobile phones is often limited by the shooting experience of the device holder, and existing photo matching methods in complex scenes provide inadequate shooting assistance.
A shooting assistance method involving multi-dimensional feature extraction, posture prediction, and posture adjustment prompts to improve photo quality by analyzing the shooting scene and providing guidance for posture adjustments.
Enhances the shooting assistance effect, allowing for better photo capture by aligning the target object's posture with predicted optimal poses, thereby improving photo quality.
Smart Images

Figure CN119094907A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of photographing technology, and in particular to a photographing auxiliary method, device, storage medium and electronic device. Background Art
[0002] When taking photos with devices such as mobile phones, the quality of the photos taken is often limited by the shooting experience of the device holder. It is of positive significance to assist the shooting during the shooting process.
[0003] In the current related technology, similar photos in the shooting scene are obtained by photo matching, and auxiliary shooting is guided by similar photos. In this way, due to various complex situations in the shooting scene, the auxiliary shooting effect is often limited, and the effect of the captured image needs to be further improved. Summary of the invention
[0004] The embodiment of the present application provides a shooting assistance solution, which can effectively improve the shooting assistance effect and improve the effect of the photos taken.
[0005] The embodiments of the present application provide the following technical solutions:
[0006] According to one embodiment of the present application, a shooting assistance method includes: performing multi-dimensional feature extraction on a shooting picture of a target object to obtain multi-dimensional image features; inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; comparing the predicted shooting posture of the target object with the actual object posture of the target object in the shooting picture to obtain a posture deviation; and providing a posture adjustment prompt for the target object according to the posture deviation.
[0007] In some embodiments of the present application, the shooting picture taken for the target object is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, including: detecting the target object area, the object area and the environment area in the shooting picture; and performing feature extraction on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
[0008] In some embodiments of the present application, the shooting picture taken for the target object is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, including: detecting the target object area, the non-preferred area and the area outside the object in the shooting picture; performing feature extraction on the target object area, the non-preferred area and the area outside the object respectively to obtain the multi-dimensional image features.
[0009] In some embodiments of the present application, inputting the multi-dimensional image features into a pose prediction model for analysis to obtain a predicted shooting pose of the target object includes: splicing the multi-dimensional image features to obtain spliced image features; inputting the spliced image features into the pose prediction model for analysis to obtain a predicted shooting pose of the target object.
[0010] In some embodiments of the present application, the multi-dimensional image features are input into a pose prediction model for analysis to obtain a predicted shooting pose of the target object, including: fusing the multi-dimensional image features with each other based on an attention mechanism to obtain a plurality of attention features; and the plurality of attention features are input into a pose prediction model for analysis to obtain a predicted shooting pose of the target object.
[0011] In some embodiments of the present application, providing a posture adjustment prompt for the target object based on the posture deviation includes: determining a target posture adjuster and corresponding prompt information based on the posture deviation, the target posture adjuster referring to the target object or the photographer; and providing a posture adjustment prompt for the target posture adjuster based on the prompt information.
[0012] In some embodiments of the present application, after providing a posture adjustment prompt for the target object based on the posture deviation, the method further includes: detecting whether the target object has reached a target posture; if it is detected that the target object has reached the target posture, providing a posture achievement prompt.
[0013] According to one embodiment of the present application, a shooting assisting device comprises: an extraction module, used to perform multi-dimensional feature extraction on a shooting picture taken for a target object to obtain multi-dimensional image features; an analysis module, used to input the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; a comparison module, used to compare the predicted shooting posture of the target object with the actual object posture of the target object in the shooting picture to obtain a posture deviation; and a prompt module, used to provide a posture adjustment prompt for the target object according to the posture deviation.
[0014] In some embodiments of the present application, the extraction module is used to: detect the target object area, the object area and the environment area in the captured image; perform feature extraction on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
[0015] In some embodiments of the present application, the extraction module is used to: detect the target object area, the non-preferred area and the outside object area in the captured image; perform feature extraction on the target object area, the non-preferred area and the outside object area respectively to obtain the multi-dimensional image features.
[0016] In some embodiments of the present application, the analysis module is used to: stitch the multi-dimensional image features to obtain stitched image features; input the stitched image features into the posture prediction model for analysis to obtain the predicted shooting posture of the target object.
[0017] In some embodiments of the present application, the analysis module is used to: fuse the multi-dimensional image features with each other based on the attention mechanism to obtain multiple attention features; input the multiple attention features into the posture prediction model for analysis to obtain the predicted shooting posture of the target object.
[0018] In some embodiments of the present application, the prompt module is used to: determine a target posture adjuster and corresponding prompt information based on the posture deviation, where the target posture adjuster refers to the target object or the photographer; and provide posture adjustment prompts for the target posture adjuster based on the prompt information.
[0019] In some embodiments of the present application, after providing a posture adjustment prompt for the target object based on the posture deviation, the enhancement module is further used to: detect whether the target object has reached the target posture; if it is detected that the target object has reached the target posture, provide a posture achievement prompt.
[0020] According to another embodiment of the present application, a storage medium stores a computer program thereon, and when the computer program is executed by a processor of a computer, the computer executes the method described in the embodiment of the present application.
[0021] According to another embodiment of the present application, an electronic device may include: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the method described in the embodiment of the present application.
[0022] According to another embodiment of the present application, a computer program product or a computer program includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional implementations described in the embodiments of the present application.
[0023] In an embodiment of the present application, multi-dimensional features are extracted from a shooting picture of a target object to obtain multi-dimensional image features; the multi-dimensional image features are input into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; the predicted shooting posture of the target object is compared with the actual object posture of the target object in the shooting picture to obtain a posture deviation; and a posture adjustment prompt is given to the target object based on the posture deviation.
[0024] In this way, multi-dimensional image features are extracted from the shooting picture of the target object, and then the multi-dimensional image features are input into the posture prediction model for analysis to obtain the predicted shooting posture of the target object. Then, the predicted shooting posture is compared with the actual object posture to obtain the posture deviation, and the posture adjustment prompt is given to the target object based on the posture deviation, so that the target object can adjust its posture, so as to take excellent photos, which effectively improves the shooting assistance effect as a whole and improves the effect of the photos taken. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0026] Figure 1 A flowchart of a shooting assistance method according to an embodiment of the present application is shown.
[0027] Figure 2 A feature extraction flow chart according to an embodiment of the present application is shown.
[0028] Figure 3 A feature extraction flow chart according to an embodiment of the present application is shown.
[0029] Figure 4 A block diagram of a shooting assistance device according to an embodiment of the present application is shown.
[0030] Figure 5 A block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0031] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments provided herein are only used to explain the present disclosure and are not intended to limit the present disclosure. In addition, the embodiments provided below are partial embodiments for implementing the present disclosure, rather than providing all embodiments for implementing the present disclosure. In the absence of conflict, the technical solutions recorded in the embodiments of the present disclosure can be implemented in any combination.
[0032] It should be noted that, in the embodiments of the present disclosure, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or apparatus including a series of elements includes not only the elements explicitly recorded, but also includes other elements not explicitly listed, or also includes elements inherent to the implementation of the method or apparatus. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other related elements in the method or apparatus including the element (such as a step in the method or a unit in the apparatus, for example, a unit may be a part of a circuit, a part of a processor, a part of a program or software, etc.).
[0033] For example, the shooting assistance method provided by the embodiment of the present disclosure includes a series of steps, but the shooting assistance method provided by the embodiment of the present disclosure is not limited to the recorded steps. Similarly, the shooting assistance device provided by the embodiment of the present disclosure includes a series of units, but the device provided by the embodiment of the present disclosure is not limited to including the units explicitly recorded, and may also include units that need to be set to obtain relevant information or perform processing based on the information.
[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure belongs. The terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.
[0035] It is understandable that in the specific implementation of this application, relevant data is involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.
[0036] Figure 1 The flowchart of a shooting assistance method according to an embodiment of the present application is schematically shown. The execution subject of the shooting assistance method can be any device with processing capabilities, such as a mobile phone, a smart watch, a camera, a television, a computer, and a home appliance.
[0037] like Figure 1 As shown, the shooting assistance method may include steps S110 to S140.
[0038] Step S110, extracting multi-dimensional features from a shooting picture taken for the target object to obtain multi-dimensional image features; Step S120, inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; Step S130, comparing the predicted shooting posture of the target object with the actual object posture of the target object in the shooting picture to obtain a posture deviation; Step S140, providing a posture adjustment prompt for the target object according to the posture deviation.
[0039] The shooting picture taken for the target object is the picture in the preview interface when the device is used to shoot the target object. The shooting picture is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, which can more effectively represent the characteristics of the current shooting scene. Among them, the target object can be the user selected by the photographer on the screen, or the user with the largest area in the shooting picture automatically detected, etc.
[0040] A deep learning-based pose prediction model is pre-trained, and the multi-dimensional image features are input into the pose prediction model for analysis. The pose prediction model can output a more suitable predicted shooting pose of the target object in the current scene. The predicted shooting pose can include the predicted pose and position.
[0041] Furthermore, the predicted shooting posture of the target object is compared with the real-time actual object posture of the target object in the shooting picture to obtain the posture deviation. According to the posture deviation, the target object can be prompted to adjust the posture by voice prompt, device vibration, prompt box, remote transmission of posture adjustment prompt information to the device carried by the target object, etc., so that the target object can be prompted to adjust the posture, so that the photographer can easily take a better-looking photo of the target object in the current scene. The actual object posture may include the actual posture and position of the target object.
[0042] In this way, multi-dimensional image features are extracted from the shooting picture of the target object, and then the multi-dimensional image features are input into the posture prediction model for analysis to obtain the predicted shooting posture of the target object. Then, the predicted shooting posture is compared with the actual object posture to obtain the posture deviation, and the posture adjustment prompt is given to the target object based on the posture deviation, so that the target object can adjust its posture, so as to take excellent photos, which effectively improves the shooting assistance effect as a whole and improves the effect of the photos taken.
[0043] Described below Figure 1 When performing shooting assistance under the embodiment, further optional specific embodiments are provided under each step performed.
[0044] In one embodiment, see Figure 2 The step of performing multi-dimensional feature extraction on a shooting picture taken for the target object to obtain multi-dimensional image features may include: step S210, detecting a target object area, an object area and an environment area in the shooting picture; and step S220, performing feature extraction on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
[0045] In this embodiment, the target object area, object area and environment area in the captured picture are detected, wherein the target object area is the picture area where the target object is located, the object area is the picture area where other objects other than the target object (such as animals, trees, stools, etc.) are located, and the environment area is other areas in the captured picture except the target object area and the object area.
[0046] Feature extraction is performed on the target object area, the object area and the environment area respectively to obtain multi-dimensional image features, which include image features of the target object dimension, image features of the object dimension and image features of the environment dimension.
[0047] Extracting image features of the target object dimension, the object dimension, and the environment dimension can enrich and effectively characterize the characteristics of the current shooting scene, and can be used to effectively predict the appropriate predicted shooting pose of the target object.
[0048] Specifically, the multi-dimensional image features can be automatically extracted by performing target detection and semantic segmentation on the captured images through a deep learning model. Specifically, the image features can be feature vectors or feature matrices that represent image information.
[0049] Further, in one embodiment, see Figure 3 , the shooting picture taken for the target object is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, including: step S310, detecting the target object area, the non-preferred area and the area outside the object in the shooting picture; step S320, respectively performing feature extraction on the target object area, the non-preferred area and the area outside the object to obtain the multi-dimensional image features.
[0050] In this embodiment, the target object area, non-preferred area and out-of-object area in the captured image are detected, wherein the target object area is the image area where the target object is located, the non-preferred area is the image area where the target object or a position that the photographer does not like is located, and the out-of-object area is other areas in the captured image except the target object area.
[0051] The area where the disliked position input by the user is located can be detected as the non-preferred area, or the user can click on the screen to select the area where the disliked position is located as the non-preferred area.
[0052] Feature extraction is performed on the target object area, the non-preferred area and the area outside the object respectively to obtain multi-dimensional image features, which include image features of the target object dimension, image features of the non-preferred dimension and image features of the outside object dimension.
[0053] Extracting image features of the target object dimension, non-preferred dimension, and out-of-object dimension can further enrich and effectively represent the characteristics of the current shooting scene while representing the user's dislike for shooting information, which can be further used to effectively predict the appropriate predicted shooting pose of the target object.
[0054] Specifically, the multi-dimensional image features can be automatically extracted by performing target detection and semantic segmentation on the captured images through a deep learning model. Specifically, the image features can be feature vectors or feature matrices that represent image information.
[0055] In one embodiment, inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object may include: splicing the multi-dimensional image features to obtain spliced image features; and inputting the spliced image features into the posture prediction model for analysis to obtain a predicted shooting posture of the target object.
[0056] The multi-dimensional image features can be spliced in series or superimposed to obtain spliced image features. The spliced image features are input into the pose prediction model, and the pose prediction model can perform shooting pose analysis based on the spliced image features and output the predicted shooting pose of the target object.
[0057] Furthermore, in one embodiment, the inputting the multi-dimensional image features into a pose prediction model for analysis to obtain a predicted shooting pose of the target object may include: fusing the multi-dimensional image features with each other based on an attention mechanism to obtain a plurality of attention features; and inputting the plurality of attention features into a pose prediction model for analysis to obtain a predicted shooting pose of the target object.
[0058] In this embodiment, the multi-dimensional image features are mutually fused based on the attention mechanism to obtain multiple attention features. The feature fusion through the attention mechanism can further effectively characterize the multi-dimensional shooting association relationship in the image. The multiple attention features are input into the posture prediction model for analysis, and the predicted shooting posture suitable for the target object can be further reliably obtained.
[0059] Among them, the multi-dimensional image features are fused with each other based on the attention mechanism to obtain multiple attention features, which can be specifically: generating a first query vector according to the first multi-dimensional image features, and generating a second key vector according to the second dimensional image features; calculating the attention weights representing the correlation between the first multi-dimensional image features and the second dimensional image feature words according to the first query vector and the second key vector; adjusting the first multi-dimensional image features based on the attention weights to obtain the first attention features.
[0060] For example, in one method, the multi-dimensional image features include image feature 1 of the target object dimension, image feature 2 of the non-preferred dimension, and image feature 3 of the out-of-object dimension; the multi-dimensional image features are fused with each other based on the attention mechanism to obtain multiple attention features, specifically: image feature 1 and image feature 2 are fused based on the attention mechanism to obtain attention feature 1, image feature 2 and image feature 3 are fused based on the attention mechanism to obtain attention feature 2, and image feature 1 and image feature 3 are fused based on the attention mechanism to obtain attention feature 3.
[0061] For example, in one method, the multi-dimensional image features include image feature 4 of the target object dimension, image feature 5 of the object dimension, and image feature 6 of the environment dimension; the multi-dimensional image features are fused with each other based on the attention mechanism to obtain multiple attention features, specifically: image feature 4 and image feature 5 are fused based on the attention mechanism to obtain attention feature 4, image feature 5 and image feature 6 are fused based on the attention mechanism to obtain attention feature 5, and image feature 4 and image feature 6 are fused based on the attention mechanism to obtain attention feature 6.
[0062] In one embodiment, providing a posture adjustment prompt for the target object based on the posture deviation may include: determining a target posture adjuster and corresponding prompt information based on the posture deviation, the target posture adjuster referring to the target object or the photographer; and providing a posture adjustment prompt for the target posture adjuster based on the prompt information.
[0063] The device can further determine which of the target object or the photographer is more suitable for adjustment based on the posture deviation to make the target object reach a suitable target posture, and then obtain the target posture adjuster. Then, corresponding prompt information is generated for the target posture adjuster, and the prompt information user prompts the target posture adjuster how to change posture and position.
[0064] Furthermore, the device can provide posture adjustment prompts to the target posture adjuster based on the prompt information, for example, through voice prompts, device vibration, prompt boxes, remote transmission of posture adjustment prompt information to the device carried by the target object, etc.
[0065] Optionally, the performing of posture adjustment prompts for the target object according to the posture deviation may include: taking a default object among the target object or the photographer as the target posture adjuster, generating corresponding prompt information; and performing posture adjustment prompts for the target posture adjuster according to the prompt information. That is, one of the target object or the photographer is designated as the default target posture adjuster in advance, without judging which of the target object or the photographer is more suitable as the target posture adjuster according to the posture deviation.
[0066] Furthermore, in one embodiment, after providing a posture adjustment prompt for the target object based on the posture deviation, the method may also include: detecting whether the target object has reached a target posture; if it is detected that the target object has reached the target posture, providing a posture achievement prompt.
[0067] After detecting that the target object has reached the target posture, the posture achievement prompt can be provided through voice prompts, device vibration, prompt boxes, remote transmission of posture adjustment prompt information to the device carried by the target object, etc., to prompt the target object to reach the appropriate target posture, so that the photographer and the target object can maintain the posture to take satisfactory photos.
[0068] In order to better implement the shooting assistance method provided in the embodiment of the present application, the embodiment of the present application also provides a shooting assistance device based on the shooting assistance method. The meanings of the terms are the same as those in the shooting assistance method, and the specific implementation details can refer to the description in the method embodiment. Figure 4 A block diagram of a shooting assistance device according to an embodiment of the present application is shown.
[0069] like Figure 4 As shown, the shooting assistance device 400 may include: an extraction module 410 can be used to extract multi-dimensional features from a shooting picture taken for a target object to obtain multi-dimensional image features; an analysis module 420 can be used to input the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; a comparison module 430 can be used to compare the predicted shooting posture of the target object with the actual object posture of the target object in the shooting picture to obtain a posture deviation; a prompt module 440 can be used to provide posture adjustment prompts for the target object according to the posture deviation.
[0070] In some embodiments of the present application, the extraction module is used to: detect the target object area, the object area and the environment area in the captured image; perform feature extraction on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
[0071] In some embodiments of the present application, the extraction module is used to: detect the target object area, the non-preferred area and the outside object area in the captured image; perform feature extraction on the target object area, the non-preferred area and the outside object area respectively to obtain the multi-dimensional image features.
[0072] In some embodiments of the present application, the analysis module is used to: stitch the multi-dimensional image features to obtain stitched image features; input the stitched image features into the posture prediction model for analysis to obtain the predicted shooting posture of the target object.
[0073] In some embodiments of the present application, the analysis module is used to: fuse the multi-dimensional image features with each other based on the attention mechanism to obtain multiple attention features; input the multiple attention features into the posture prediction model for analysis to obtain the predicted shooting posture of the target object.
[0074] In some embodiments of the present application, the prompt module is used to: determine a target posture adjuster and corresponding prompt information based on the posture deviation, where the target posture adjuster refers to the target object or the photographer; and provide posture adjustment prompts for the target posture adjuster based on the prompt information.
[0075] In some embodiments of the present application, after providing a posture adjustment prompt for the target object based on the posture deviation, the enhancement module is further used to: detect whether the target object has reached the target posture; if it is detected that the target object has reached the target posture, provide a posture achievement prompt.
[0076] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0077] In addition, the present application also provides an electronic device, such as Figure 5 As shown, Figure 5 A block diagram of an electronic device according to an embodiment of the present application is shown, specifically:
[0078] The electronic device may include one or more processors 501 of processing cores, one or more computer-readable storage media memories 502, a power supply 503 and other components. Those skilled in the art will appreciate that Figure 5The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.
[0079] The processor 501 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 502 and calling data stored in the memory 502, it executes various functions of the computer device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 501.
[0080] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.
[0081] The electronic device also includes a power supply 503 for supplying power to each component. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 503 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.
[0082] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 501 in the electronic device will load the executable files corresponding to the processes of one or more computer programs into the memory 502 according to the following instructions, and the processor 501 will run the computer program stored in the memory 502, thereby realizing various functions in the aforementioned embodiments of the present application, such as the processor 501 may perform the following steps:
[0083] A multi-dimensional feature extraction is performed on a shooting picture taken for a target object to obtain multi-dimensional image features; the multi-dimensional image features are input into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; the predicted shooting posture of the target object is compared with the actual object posture of the target object in the shooting picture to obtain a posture deviation; and a posture adjustment prompt is given to the target object according to the posture deviation.
[0084] In some embodiments of the present application, the shooting picture taken for the target object is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, including: detecting the target object area, the object area and the environment area in the shooting picture; and performing feature extraction on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
[0085] In some embodiments of the present application, the shooting picture taken for the target object is subjected to multi-dimensional feature extraction to obtain multi-dimensional image features, including: detecting the target object area, the non-preferred area and the area outside the object in the shooting picture; performing feature extraction on the target object area, the non-preferred area and the area outside the object respectively to obtain the multi-dimensional image features.
[0086] In some embodiments of the present application, inputting the multi-dimensional image features into a pose prediction model for analysis to obtain a predicted shooting pose of the target object includes: splicing the multi-dimensional image features to obtain spliced image features; inputting the spliced image features into the pose prediction model for analysis to obtain a predicted shooting pose of the target object.
[0087] In some embodiments of the present application, the multi-dimensional image features are input into a pose prediction model for analysis to obtain a predicted shooting pose of the target object, including: fusing the multi-dimensional image features with each other based on an attention mechanism to obtain a plurality of attention features; and the plurality of attention features are input into a pose prediction model for analysis to obtain a predicted shooting pose of the target object.
[0088] In some embodiments of the present application, providing a posture adjustment prompt for the target object based on the posture deviation includes: determining a target posture adjuster and corresponding prompt information based on the posture deviation, the target posture adjuster referring to the target object or the photographer; and providing a posture adjustment prompt for the target posture adjuster based on the prompt information.
[0089] In some embodiments of the present application, after providing a posture adjustment prompt for the target object based on the posture deviation, the method further includes: detecting whether the target object has reached a target posture; if it is detected that the target object has reached the target posture, providing a posture achievement prompt.
[0090] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.
[0091] To this end, an embodiment of the present application further provides a storage medium, in which a computer program is stored. The computer program can be loaded by a processor to execute the steps in any method provided in the embodiment of the present application.
[0092] The storage medium may be a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.
[0093] Since the computer program stored in the storage medium can execute the steps in any method provided in the embodiments of the present application, the beneficial effects that can be achieved by the method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.
[0094] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0095] It should be understood that the present application is not limited to the embodiments that have been described above and shown in the accompanying drawings, but various modifications and changes may be made without departing from the scope thereof.
Claims
1. A shooting assistance method, characterized in that: include: Extracting multi-dimensional features from a picture taken of a target object to obtain multi-dimensional image features; Inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; Comparing the predicted shooting pose of the target object with the actual object pose of the target object in the shooting picture to obtain a pose deviation; Prompt a posture adjustment for the target object according to the posture deviation.
2. The method according to claim 1, characterized in that The multi-dimensional feature extraction is performed on the shooting picture of the target object to obtain multi-dimensional image features, including: Detecting a target object area, an object area, and an environment area in the captured image; Feature extraction is performed on the target object area, the object area and the environment area respectively to obtain the multi-dimensional image features.
3. The method according to claim 1, characterized in that The multi-dimensional feature extraction is performed on the shooting picture of the target object to obtain multi-dimensional image features, including: Detecting a target object area, a non-preferred area, and an area outside the object in the captured image; Feature extraction is performed on the target object area, the non-preferred area and the area outside the object respectively to obtain the multi-dimensional image features.
4. The method according to claim 1, characterized in that The step of inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object includes: Splicing the multi-dimensional image features to obtain spliced image features; The stitched image features are input into the pose prediction model for analysis to obtain the predicted shooting pose of the target object.
5. The method according to claim 1, characterized in that The step of inputting the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object includes: The multi-dimensional image features are mutually integrated based on the attention mechanism to obtain multiple attention features; The multiple attention features are input into a posture prediction model for analysis to obtain a predicted shooting posture of the target object.
6. The method according to claim 1, characterized in that Providing a posture adjustment prompt for the target object according to the posture deviation includes: Determine a target posture adjuster and corresponding prompt information according to the posture deviation, wherein the target posture adjuster refers to the target object or the photographer; The target posture adjuster is prompted to adjust the posture according to the prompt information.
7. The method according to any one of claims 1 to 6, characterized in that: After providing a posture adjustment prompt for the target object according to the posture deviation, the method further includes: Detecting whether the target object reaches a target posture; If it is detected that the target object has reached the target posture, a posture achievement prompt is given.
8. A shooting auxiliary device, characterized in that: include: An extraction module is used to extract multi-dimensional features from a picture taken of a target object to obtain multi-dimensional image features; An analysis module is used to input the multi-dimensional image features into a posture prediction model for analysis to obtain a predicted shooting posture of the target object; A comparison module, used for comparing the predicted shooting posture of the target object with the actual object posture of the target object in the shooting picture to obtain a posture deviation; A prompt module is used to provide a posture adjustment prompt for the target object according to the posture deviation.
9. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method according to any one of claims 1 to 7.
10. An electronic device, characterized in that: include: a memory storing a computer program; A processor reads a computer program stored in a memory to execute the method according to any one of claims 1 to 7.
