Image processing method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an image processing method and device, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a to-be-processed image in response to an image processing request, and displaying a plurality of object key points corresponding to a target object in the to-be-processed image under the condition that the to-be-processed image contains the target object; and in response to a key point triggering operation for the object key points, determining a plurality of target key points from the plurality of object key points, and displaying posture prompt information corresponding to the plurality of target key points. According to the technical scheme provided by the embodiment of the invention, matching of local postures, namely processing of partial object key points, is supported, and the data processing amount in the posture matching process can be effectively reduced, so that the posture matching efficiency and the matching precision are improved. Moreover, the effect of carrying out attitude matching on the object attitude in the image through simple interaction operation and a plurality of target key points improves the interaction experience in the attitude matching process.

Description

Technical Field

[0001] This disclosure relates to computer application technology, and more particularly to an image processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In motion matching scenarios, image-based motion matching is becoming increasingly relied upon. An image of the object's pose can be obtained. Then, pose matching can be performed on the object's pose in the image to determine if the object's pose matches the expected presentation pose.

[0003] In related technologies, pose matching for images to be processed is typically performed manually. This involves manually matching the image to be processed against a reference image that includes the expected pose. This method relies on human experience and is time-consuming and labor-intensive, thus affecting both efficiency and accuracy. Summary of the Invention

[0004] This disclosure provides an image processing method, apparatus, electronic device, storage medium, and program product to achieve pose matching of objects in an image through simple interactive operations and multiple target key points.

[0005] In a first aspect, embodiments of this disclosure provide an image processing method, the method comprising:

[0006] In response to an image processing request, an image to be processed is acquired. If the image to be processed contains a target object, multiple object key points corresponding to the target object are displayed in the image to be processed.

[0007] In response to a keypoint triggering operation for the object keypoint, multiple target keypoints are determined from the multiple object keypoints, and posture prompt information corresponding to the multiple target keypoints is displayed.

[0008] Secondly, embodiments of this disclosure also provide an image processing apparatus, the apparatus comprising:

[0009] The image acquisition module is used to acquire an image to be processed in response to an image processing request, and if the image to be processed contains a target object, to display multiple object key points corresponding to the target object in the image to be processed;

[0010] The posture prompting module is used to respond to a key point triggering operation for the key points of the object, determine multiple target key points from multiple object key points, and display posture prompting information corresponding to the multiple target key points.

[0011] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0012] One or more processors;

[0013] Storage device for storing one or more programs.

[0014] When the one or more programs are executed by the one or more processors, the one or more processors implement the image processing method as described in any of the embodiments of this disclosure.

[0015] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the image processing method as described in any of the embodiments of this disclosure.

[0016] Fifthly, this disclosure also provides a computer program product, which includes a computer program that, when executed by a processor, implements the image processing method described in any embodiment of the present invention.

[0017] The technical solution of this disclosure, in response to an image processing request, acquires an image to be processed. If the image contains a target object, it displays multiple object key points corresponding to the target object. The acquisition of the image and the display of object key points can be triggered through simple interactive operations, providing a data foundation for subsequent pose matching and improving image processing efficiency. Furthermore, in response to key point triggering operations targeting object key points, multiple target key points are determined from the multiple object key points, and pose prompts corresponding to these target key points are displayed. This solves the problem that pose matching methods in related technologies rely on manual experience, are laborious, and affect pose matching efficiency and accuracy. It supports the custom determination of target key points, and is particularly suitable for matching local poses, i.e., processing only some object key points. Using target key points to generate pose prompts effectively reduces the amount of data processing in the pose matching process, thereby improving the efficiency and accuracy of pose matching. Moreover, the simple interactive operation and the effect of matching the pose of objects in the image using multiple target key points enhance the interactive experience during the pose matching process. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0019] Figure 1This is a schematic flowchart of an image processing method provided in an embodiment of the present disclosure;

[0020] Figure 2 This is a schematic flowchart of another image processing method provided in an embodiment of the present disclosure;

[0021] Figure 3 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of the present disclosure;

[0022] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0025] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0026] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0027] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0028] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0029] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0030] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0031] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0033] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0034] Figure 1 This is a flowchart illustrating an image processing method provided in an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to the situation of pose matching of objects in an image based on object key points. The method can be executed by an image processing device, which can be implemented in the form of software and / or hardware, or optionally by an electronic device, such as a mobile terminal, a PC, or a server.

[0035] like Figure 1 As shown, the method in this embodiment may specifically include:

[0036] S110. In response to an image processing request, obtain an image to be processed, and if the image to be processed contains a target object, display multiple object key points corresponding to the target object in the image to be processed.

[0037] In this context, an image processing request can be understood as an instruction to request image processing. Image processing requests can be generated in various ways. Optionally, an image processing request can be generated upon detecting a trigger operation on a preset image processing control; or, if the received audio information includes a trigger word associated with image processing; or, if the received instruction includes an image processing instruction, etc. The image to be processed can be an image to be processed. In this embodiment, the method of acquiring the image to be processed can include various methods, including, optionally, acquiring an uploaded or captured image as the image to be processed; and / or, acquiring a target video and extracting video frames from the target video as the image to be processed. The target video can be any video. The target video can be a video captured by a terminal device; or, it can be a video acquired from a target storage space (e.g., the video library of an application software, or the local terminal photo album, etc.) in response to a video selection operation; or, it can be a video received from an external device, etc.

[0038] As an optional implementation of this embodiment, upon receiving an image processing request, the device responds to the request and enters a shooting interface. At this time, the image displayed on the shooting interface is the view of the shooting device, and the content of the image displayed on the shooting interface can be updated by moving the shooting device. Furthermore, upon detecting a shooting trigger operation (e.g., triggering a shooting control or clicking the terminal device screen), the shooting device can capture the image displayed on the current shooting interface, and the captured image can be used as the image to be processed.

[0039] As another optional implementation of this disclosure, upon receiving an image processing request, in response to the request, any candidate video is selected from the target storage space based on a video selection operation to serve as the target video. Further, image selection prompt information can be obtained, and video frames can be extracted from the target video based on the prompt information, with the extracted video frames serving as images to be processed. The image selection prompt information can be used to indicate the video frames expected to be selected from the target video.

[0040] In the embodiments of this disclosure, the acquired image to be processed may or may not include the target object. If the image to be processed includes the target object, processing can continue based on the following image processing flow. If the image to be processed does not include the target object, the image to be processed can be reacquired until the target object is included.

[0041] The target object can be a person or animal, or any part of a body, such as a person's face or limbs. In this embodiment, the target object can be an object in the image to be processed that can move actively or passively. Object key points can be understood as feature points representing the object's body part or outline. Object key points can be used to represent information such as the target object's action, posture, or shape. Object key points can be feature points on the target object, such as skeletal feature points or facial feature points; or, object key points can be feature points outside the target object, such as outline points of a human body. For example, when the target object is a person, the object key points can be skeletal feature points of the person's body and / or facial feature points.

[0042] In this embodiment of the disclosure, displaying the key points of the target object in the image to be processed can include various display methods. Optionally, it can be displayed using feature points of a preset color; and / or, it can be displayed using key point identifiers. The key point identifiers can be used to identify the corresponding object key points. The key point identifier can be the name of the part to which the key point belongs or a preset key point number, etc. The preset color can be any color, optionally green, red, yellow, or blue, etc. The preset color can be a pre-determined color, or it can be a color determined based on the overall color of the target object in the image to be processed, etc.

[0043] As an optional implementation of this disclosure, upon receiving an image processing request, in response to the request, a captured image can be acquired as the image to be processed. Further, object detection can be performed on the image to be processed, and if it is determined that the image to be processed contains a target object, keypoint detection can be performed on the target object to obtain multiple object keypoints corresponding to the target object. Further, the multiple object keypoints can be displayed in the image to be processed as feature points of a preset color at the corresponding positions of the keypoints on the target object. For example, assuming the target object in the image to be processed includes a person, and the person's limbs and face are both displayed in the image to be processed. Further, keypoint detection is performed on the target object to obtain multiple skeletal keypoints and multiple facial keypoints, and the obtained keypoints can be used as object keypoints. Further, the object keypoints can be displayed in the image to be processed as green feature points on the corresponding limb bones and face of the person.

[0044] S120. In response to the key point triggering operation for object key points, determine multiple target key points from multiple object key points and display the posture prompt information corresponding to the multiple target key points.

[0045] In this context, a keypoint triggering operation can be understood as an operation that triggers a keypoint to update it to a selected state. The keypoint triggering operation can be any operation capable of triggering a keypoint to update its state; optionally, it can be a keypoint selection operation, a trajectory drawing operation, or a location selection operation targeting the keypoint's location. A target keypoint can be understood as a keypoint determined from object keypoints based on the keypoint triggering operation. A target keypoint can be an object keypoint associated with the pose to be prompted. It should be noted that the number of target keypoints is at least two. Pose prompting information can be used to indicate whether the pose matches a preset standard pose. In this embodiment, the pose prompting information can be used to determine whether the pose of the target object in the image to be processed matches a preset standard pose. In other words, the pose of the target object can be adjusted based on the pose prompting information to match the preset standard pose. The pose prompting information can include various information associated with the target keypoint, optionally including the object location associated with the target keypoint, the target keypoint to be adjusted, and the reference keypoint corresponding to the preset standard pose.

[0046] In the embodiments of this disclosure, the key point triggering operation may include a variety of operations, and consequently, the methods for determining the target key point may also include a variety of methods. These various determination methods will be described below.

[0047] One approach is to determine multiple target keypoints from multiple object keypoints based on the selected object keypoints in response to a keypoint selection operation.

[0048] The key point selection operation can be any operation that selects the corresponding key point. The key point selection operation can be any operation performed on the key points of an object, optionally including click operations on the key points and / or key point marker editing operations.

[0049] As an optional implementation of this embodiment, when multiple object key points corresponding to the target object are displayed in the image to be processed, a click operation can be input on any object key point. Furthermore, if a click operation on multiple object key points is detected, it can be determined that a key point selection operation has been detected. Then, the selected object key point is taken as the target key point.

[0050] As another optional implementation of this disclosure, when multiple object key points corresponding to the target object are displayed in the image to be processed, a key point editing interface is displayed in response to a key point editing operation. This key point editing interface includes key point editing items. Further, in response to an identifier input operation for the key point editing items, the key point identifiers of the object key points to be processed are input into the key point editing items. Then, in response to an editing completion operation, the selected object key point is determined based on the input key point identifiers, and the selected object key point is used as the target key point.

[0051] Another approach is to determine multiple target key points from multiple object key points based on the drawn target trajectory in response to the target object's trajectory drawing operation.

[0052] The trajectory drawing operation can be an operation that draws a trajectory on the interface based on an input device or touch point. In this embodiment, the trajectory drawing operation can be an operation that connects multiple object key points in a target object to form at least one trajectory. The trajectory drawing operation can include any operation that connects multiple key points to form a trajectory, optionally including key point connection operations, continuous input click operations on key points within a preset time period, and / or trajectory drawing and editing operations, etc. The target trajectory can be a trajectory formed by connecting multiple object key points based on the trajectory drawing operation.

[0053] As an optional implementation of this embodiment, when multiple object key points corresponding to the target object are displayed in the image to be processed, any object key point can be selected as the starting point of the drawing trajectory. Furthermore, based on the input device or touch point moving from the object key point in the display interface, the movement trajectory is controlled to pass through at least one object key point. Further, if it is detected that the dwell time of the input device or touch point at any object key point or its vicinity reaches a preset duration, the movement trajectory displayed in the display interface can be used as the target trajectory for drawing, and the multiple object key points included in the target trajectory can be used as target key points.

[0054] As another optional implementation of this disclosure, when multiple object key points corresponding to the target object are displayed in the image to be processed, click operations can be continuously input on multiple object key points within a preset time period. Furthermore, multiple object key points selected within the preset time period can be determined, and the trajectory connecting these multiple object key points can be used as the target trajectory for drawing, with the selected multiple object key points serving as the target key points.

[0055] As another optional implementation of this disclosure, in response to the trajectory drawing operation, a trajectory drawing editing interface is displayed. This interface includes a trajectory start point editing item, a trajectory path point editing item, and a trajectory end point editing item. Further, key point identifier input operations can be performed for the trajectory start point editing item, the trajectory path point editing item, and the trajectory end point editing item respectively, to input the corresponding key point identifiers in the corresponding editing items. Further, a trajectory can be generated based on the input key point identifiers, and the generated trajectory can be used as the target trajectory, with the object key points corresponding to the input key point identifiers used as target key points.

[0056] Another approach is to respond to a part selection operation for a target object, determine the object part of the target object based on the part selection operation, and determine multiple target key points from multiple object key points based on the object part.

[0057] The part selection operation can be any operation that selects a relevant part. The part selection operation can include any operation input on the relevant part, optionally including part click operations and / or part editing operations. The object part can be a part of a target object selected based on the part selection operation. For example, the object part can be the forearm, upper arm, shoulder, head, calf, thigh, or foot, etc.

[0058] As an optional implementation of this disclosure, when a click operation is detected on any part of the target object, in response to the click operation, the part selected based on the click operation is determined, and the selected part is designated as the object part of the target object. Further, multiple object key points associated with the object part can be determined, and these multiple object key points can be designated as target key points. For example, assuming the target object is a person, when a click operation is detected on the person's forearm, the clicked forearm can be designated as the object part of the target object. Further, the wrist joint and elbow joint points associated with the forearm can be designated as target key points.

[0059] As another optional implementation of this disclosure, in response to a part editing operation, a part editing interface is displayed, which includes part editing items. Further, the part to be edited is input into the part editing items, and in response to an editing completion operation, the input part is designated as the object part of the target object. Further, multiple object key points associated with the object part are determined, and these multiple object key points are designated as target key points.

[0060] It should be noted that the advantage of using at least one of the above operations to determine the target key points is that it enriches the methods for determining the target key points, improves the flexibility of key point determination, enhances the fun of the posture matching function, and improves the user experience.

[0061] In this embodiment of the disclosure, when multiple target key points are determined from multiple object key points, it is possible to determine whether the pose of the target object matches the expected presentation pose based on the multiple target key points. That is, the pose of the target object is compared with the expected presentation pose based on the multiple target key points. Furthermore, pose prompt information can be generated based on the comparison result, and the pose prompt information can be displayed.

[0062] As an optional implementation of this disclosure, when multiple target key points are determined, a corresponding reference image can be obtained based on the pose of the target object in the image to be processed. This reference image includes multiple reference key points corresponding to the expected pose of the target object. Further, multiple target reference key points corresponding to the target key points can be determined from the multiple reference key points based on the multiple target key points. Further, multiple target key points and multiple target reference key points can be matched according to a preset key point matching method to determine whether the pose of the target object matches the expected pose. Further, if the pose of the target object matches the expected pose based on the key point matching result, pose prompt information can be generated, including information indicating successful pose matching. If the pose of the target object does not match the expected pose based on the key point matching result, pose prompt information can be generated, including information such as pose matching failure, mismatched object parts, and / or mismatched target key points. Further, the generated pose prompt information can be displayed so that relevant objects can clearly and intuitively understand the pose matching result and adjust their pose accordingly. The preset key point matching method can be any method that can achieve key point matching, and can be key point angle matching, key point line length matching, and / or key point line angle matching, etc.

[0063] It should be noted that the technical solution of this disclosure embodiment can be executed during the user's video recording process. That is, during the user's recording process using a terminal device, the content displayed on the terminal device's recording interface can be used as the image to be processed, and key point detection, key point trigger selection, and key point matching can be performed on the target object in the image to be processed. Then, posture prompt information is generated and displayed on the recording interface. Furthermore, the posture of the target object can be adjusted based on the displayed posture prompt information, and during the adjustment process, the content displayed on the recording interface continues to be used as the image to be processed, and image processing is performed on the image to be processed in the above manner. Then, the posture adjustment result can be displayed on the recording interface in the form of posture prompt information. The advantage of this setup is that it allows the user to match the posture of the target object in real time during recording and provides real-time feedback on the posture adjustment result. This improves the efficiency of posture matching and enhances the convenience of the user's application of related functions.

[0064] The technical solution of this disclosure, in response to an image processing request, acquires an image to be processed. If the image contains a target object, it displays multiple object key points corresponding to the target object. The acquisition of the image and the display of object key points can be triggered through simple interactive operations, providing a data foundation for subsequent pose matching and improving image processing efficiency. Furthermore, in response to key point triggering operations targeting object key points, multiple target key points are determined from the multiple object key points, and pose prompts corresponding to these target key points are displayed. This solves the problem that pose matching methods in related technologies rely on manual experience, are laborious, and affect pose matching efficiency and accuracy. It supports the custom determination of target key points, and is particularly suitable for matching local poses, i.e., processing only some object key points. Using target key points to generate pose prompts effectively reduces the amount of data processing in the pose matching process, thereby improving the efficiency and accuracy of pose matching. Moreover, the simple interactive operation and the effect of matching the pose of objects in the image using multiple target key points enhance the interactive experience during the pose matching process.

[0065] Figure 2This is a schematic flowchart illustrating another image processing method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment demonstrates pose prompting information corresponding to multiple target key points, including: acquiring a reference image corresponding to the image to be processed, wherein the reference image includes multiple reference key points corresponding to the expected presentation pose of the target object; determining pose prompting information corresponding to the target object based on the multiple target key points and the multiple reference key points, and displaying the pose prompting information. For detailed implementation, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here.

[0066] like Figure 2 As shown, the method in this embodiment may specifically include:

[0067] S210. In response to an image processing request, obtain an image to be processed, and if the image to be processed contains a target object, display multiple object key points corresponding to the target object in the image to be processed.

[0068] S220. In response to a keypoint triggering operation for object keypoints, determine multiple target keypoints from multiple object keypoints and obtain a reference image corresponding to the image to be processed, wherein the reference image includes multiple reference keypoints corresponding to the expected presentation posture of the target object.

[0069] The reference image can be understood as a standard image used for comparison and analysis. In this embodiment, the reference image corresponds to the image to be processed, and the parameter image includes multiple reference key points corresponding to the expected presentation posture of the target object. The expected presentation posture can be understood as the posture that the target object should present. Alternatively, the expected presentation posture can also be understood as a preset standard posture, that is, a posture that conforms to a preset posture standard. The reference key points can be object key points associated with the expected presentation posture, that is, object key points that can characterize the expected presentation posture. The reference image can include various acquisition methods, optionally including acquiring an uploaded or captured image corresponding to the image to be processed as the reference image; and / or selecting a motion type and selecting an image corresponding to the image to be processed from a library based on the motion type as the reference image, etc.

[0070] As an optional implementation of this disclosure, when acquiring an image to be processed, the expected presentation posture of the target object can be determined based on the posture of the target object in the image to be processed, and when the reference object assumes the expected presentation posture, the reference object is photographed using the photographing device. Furthermore, the photographed image can be used as a reference image.

[0071] As another optional implementation of this disclosure, when acquiring an image to be processed, the corresponding target motion type can be determined based on the posture of the target object in the image to be processed. Further, in response to a reference image selection operation, a motion type selection interface is displayed, which includes at least one candidate motion type. Further, in response to the motion type selection operation, a target motion type is selected from the at least one candidate motion type, and a gallery corresponding to the target motion type is displayed. This gallery includes at least one motion posture image corresponding to the target motion type, and the motion posture included in each motion posture image is the expected presentation posture of the corresponding action. Further, a motion posture image corresponding to the image to be processed can be determined from the at least one motion posture image according to the image selection operation, and the determined motion posture image is used as the reference image corresponding to the image to be processed. The candidate motion types may include running, basketball, football, badminton, table tennis, and tennis, etc.

[0072] In this embodiment of the disclosure, when a reference image is obtained, key point detection can be performed on the reference object included in the reference image. Furthermore, multiple reference key points corresponding to the expected presentation posture can be obtained.

[0073] S230. Determine the posture prompt information corresponding to the target object based on multiple target key points and multiple reference key points, and display the posture prompt information.

[0074] In this embodiment of the disclosure, when multiple target keypoints are determined and multiple reference keypoints are obtained, keypoint information of the target keypoints and keypoint information of the reference keypoints can be acquired. Then, keypoint matching can be performed on the multiple target keypoints and multiple reference keypoints based on the acquired keypoint information. Furthermore, posture prompting information can be generated based on the keypoint matching results, and the posture prompting information can be displayed.

[0075] Optionally, the posture prompting information corresponding to the target object is determined based on multiple target key points and multiple reference key points, including: determining first key point information corresponding to the multiple target key points; determining second key point information corresponding to the first key point information based on the multiple reference key points; and determining posture prompting information corresponding to the target object based on the first key point information and the second key point information.

[0076] The first keypoint information can be information used for keypoint matching corresponding to the target keypoints. The first keypoint information may include any information capable of keypoint matching, optionally including a first included angle between target keypoints and / or a first connecting line between target keypoints. The second keypoint information can be information used for keypoint matching corresponding to reference keypoints. It should be noted that the information included in the second keypoint information corresponds to the information included in the first keypoint information. Optionally, if the first keypoint information includes a first included angle between target keypoints, the second keypoint information also includes a second included angle between reference keypoints; if the first keypoint information includes a first connecting line between target keypoints, the second keypoint information also includes a second connecting line between reference keypoints; if the first keypoint information includes both a first included angle and a first connecting line between target keypoints, the second keypoint information also includes both a second included angle and a second connecting line between reference keypoints.

[0077] In this embodiment, when multiple target keypoints are identified, first keypoint information corresponding to the multiple target keypoints can be determined based on the display information of the multiple target keypoints in the image to be processed. Further, keypoints to be matched corresponding to each target keypoint can be determined from multiple reference keypoints. Then, second keypoint information can be determined based on the display information of the keypoints to be matched in the reference image and the first keypoint information. Further, keypoint matching can be performed on the multiple target keypoints and the multiple keypoints to be matched based on the first and second keypoint information to determine posture cueing information based on the keypoint matching results. The advantage of this setup is that it improves the accuracy of keypoint matching and enhances the precision of posture matching.

[0078] Optionally, determining the first key point information corresponding to multiple target key points includes: determining key point association information corresponding to multiple target key points, and determining the first key point information corresponding to multiple target key points based on the key point association information.

[0079] The keypoint association information can be understood as information associated with the display of keypoints in the image to be processed. Optionally, the keypoint association information includes at least one of the following: the location information of multiple target keypoints, the number of target keypoints, and the distance between target keypoints. The location information can be information representing the display position of the keypoints in the image. The distance between target keypoints can be the distance between any two target keypoints.

[0080] It should be noted that the location information of target key points can generally be represented by key point coordinates, such as three-dimensional key point coordinates or two-dimensional key point coordinates. In this embodiment of the disclosure, the location information can be represented by two-dimensional key point coordinates, that is, the location information can be the coordinate information of the target key point in two-dimensional screen space.

[0081] In practical applications, when identifying key points of target objects within an image, 3D recognition algorithms are typically used. The resulting location information of the target key points is represented in the form of 3D coordinates. However, 3D recognition algorithms have high performance requirements on the terminal device, leading to high image processing costs and poor versatility.

[0082] To address the above issues, in this embodiment of the disclosure, a two-dimensional keypoint recognition algorithm can be used to identify keypoints of target objects in the image to be processed. The resulting location information of the target keypoints is represented by two-dimensional keypoint coordinates. Furthermore, while reducing terminal performance overhead and ensuring matching accuracy, keypoints can be effectively identified and matched, thereby improving keypoint matching efficiency and image processing efficiency.

[0083] As an optional implementation of this embodiment, when multiple target key points are determined, a preset key point recognition algorithm can be used to identify the multiple target key points in the image to be processed, so as to obtain key point association information corresponding to the multiple target key points. This key point association information includes at least one of the following: the location information of the multiple target key points, the number of target key points, and the distance between the target key points. Further, it can be determined whether a first angle between the target key points needs to be determined based on the number of target key points and the distance between them. In other words, it is determined whether key point matching can be performed based on the first angle between the target key points based on the number of target key points and the distance between them. Further, if it is determined that a first angle between the target key points is needed, the first angle between the target key points can be determined based on the location information of the multiple target key points. Furthermore, a first connecting line between the target key points can also be determined based on the location information of the multiple target key points. Therefore, the first angle between the target key points and / or the first connecting line between the target key points can be used as the first key point information corresponding to the multiple target key points. The advantage of this setup is that it effectively identifies and matches key points while reducing terminal performance loss and ensuring matching accuracy, thereby improving key point matching efficiency and image processing efficiency.

[0084] In this embodiment of the disclosure, the information included in the first key point information corresponds to the information included in the second key information. Optionally, when the first key point information includes a first included angle between target key points, the second key point information includes a second included angle between reference key points corresponding to the target key points; determining the posture prompt information corresponding to the target object based on the first key point information and the second key point information includes: determining the angular deviation between the first included angle and the second included angle, and determining the posture prompt information corresponding to the target object based on the angular deviation.

[0085] The first included angle between target keypoints can be the angle formed when the lines connecting multiple target keypoints intersect. For example, suppose there are three target keypoints: point A, point B, and point C, where point B and point C are adjacent to point A. Therefore, angle BAC can be used as the first included angle between the target keypoints. The second included angle can be the angle formed when the lines connecting reference keypoints corresponding to the target keypoints intersect.

[0086] As an optional implementation of this embodiment, when the first key point information includes a first included angle and the second key point information includes a second included angle, the angular deviation between the first included angle and the second included angle can be determined. Further, if the angular deviation is less than a preset deviation threshold, it can be determined that the target key point matches its corresponding reference key point. Therefore, it can be determined that the pose of the target object in the image to be processed matches the expected presentation pose, and a pose prompt message including pose matching success information is generated. If the angular deviation is not less than the preset deviation threshold, it can be determined that the target key point does not match its corresponding reference key point. Therefore, it can be determined that the pose of the target object in the image to be processed does not match the expected presentation pose, and a pose prompt message including pose matching failure information is generated. The advantage of this setting is that it achieves the effect of pose matching based on the included angle between target key points, reduces the steps of pose matching, improves pose matching efficiency, and reduces the performance loss required for the pose matching process.

[0087] In this embodiment of the disclosure, when determining the first key point information, there may be situations where it is impossible or unnecessary to determine the first included angle or the first connecting line between multiple target key points based on multiple target key points. Therefore, when determining the first key point information, multiple target key points can be judged first, so that if multiple target key points meet the corresponding conditions, the first included angle between the target key points can be determined, and the second included angle corresponding to the first included angle can be determined.

[0088] Optionally, determining first key point information corresponding to multiple target key points and determining second key point information corresponding to second key point information based on multiple reference key points includes: determining a first included angle corresponding to multiple target key points when multiple target key points meet a first preset condition, and determining a second included angle corresponding to the first included angle based on multiple reference key points corresponding to multiple target key points.

[0089] The first preset condition can be a pre-set condition used to determine whether the angle between key points can be determined or whether it is necessary to determine it. Optionally, the first preset condition includes at least one of the following: the number of target key points reaches a first number, the key point triggering operation is a first triggering operation, and the object parts associated with multiple target key points in the target object are preset parts.

[0090] The first quantity can be any number, optionally any value greater than or equal to 3. The first trigger operation can be any trigger operation, optionally a trajectory drawing operation that continuously passes through at least three target key points or a continuous click operation targeting a first preset number of target key points within a preset time period. The preset time period can be a short duration, optionally 1 second, 2 seconds, or 3 seconds, etc. The first preset quantity can be any value greater than or equal to 3. The preset body part can be a body part whose associated key points can form an angle, or a body part that can perform key point matching based on the angle. Optionally, the preset body part can be an upper limb body part or a lower limb body part.

[0091] As an optional implementation of this embodiment, when multiple target key points are determined, the number of target key points can be determined. Furthermore, when the number of target key points reaches a first quantity, it can be determined that multiple target key points satisfy a first preset condition. Alternatively, it can be determined whether the key point triggering operation corresponding to the target key point is a first triggering operation. Further, when the key point triggering operation is determined to be a first triggering operation, it can be determined that multiple target key points satisfy the first preset condition. Alternatively, it can be determined whether the object part associated with the target key point in the target object is a preset part, and further, when the object part is determined to be a preset part, it is determined that multiple target key points satisfy the first preset condition. Further, a first included angle corresponding to the multiple target key points can be determined based on the position information of the multiple target key points. And, a second included angle corresponding to the first included angle can be determined based on the position information of the multiple reference key points corresponding to the multiple target key points. The advantage of this setting is that it achieves the effect of determining the key point information required for matching before attitude matching, thereby improving attitude matching efficiency and enhancing the flexibility of the attitude matching process.

[0092] In this embodiment of the disclosure, when the first key point information includes a first line connecting target key points and the second key point information includes a second line connecting reference key points corresponding to the target key points, the target key points and their corresponding reference key points can be matched based on the first and second lines. When matching key points based on the first and second lines, at least two matching methods can be included, which will be described below.

[0093] One possible approach is to determine the length deviation between the first and second connecting lines, and then determine the posture cue information corresponding to the target object based on the length deviation.

[0094] The length deviation is the difference between the length of the first connection and the length of the second connection.

[0095] As an optional implementation of this embodiment, when a first line connecting the target keypoints and a second line connecting the reference keypoints are obtained, the length deviation between the first and second lines can be determined. Further, if the length deviation is less than a preset difference threshold, it can be determined that the target keypoint matches its corresponding reference keypoint. Therefore, it can be determined that the pose of the target object in the image to be processed matches the expected pose, and a pose prompt message including pose matching success information is generated. If the length deviation is not less than the preset difference threshold, it can be determined that the target keypoint does not match its corresponding reference keypoint. Therefore, it can be determined that the pose of the target object in the image to be processed does not match the expected pose, and a pose prompt message including pose matching failure information is generated. The advantage of this setting is that it achieves the effect of determining the pose matching result based on the length deviation between relevant lines, thereby improving the convenience and efficiency of pose matching.

[0096] Another option is to determine the angle between the first and second lines in the two-dimensional screen space, and then determine the posture prompt information corresponding to the target object based on the angle.

[0097] In this context, two-dimensional screen space can be understood as the representation of two-dimensional space on a terminal screen. Two-dimensional screen space can be a planar space composed of two elements: length and width (corresponding to the X and Y axes). The angle between lines can be the angle formed when any two lines intersect in two-dimensional screen space.

[0098] As another optional implementation of this disclosure, when a first line connecting the target key points and a second line connecting the reference key points are obtained, the angle between the first and second lines in the two-dimensional screen space can be determined. Further, if the angle is less than a preset angle threshold, it can be determined that the target key point matches its corresponding reference key point. Therefore, it can be determined that the pose of the target object in the image to be processed matches the expected presentation pose, and a pose prompt message including pose matching success information is generated. If the angle is not less than the preset angle threshold, it can be determined that the target key point does not match its corresponding reference key point. Therefore, it can be determined that the pose of the target object in the image to be processed does not match the expected presentation pose, and a pose prompt message including pose matching failure information is generated. The advantage of this setting is that it achieves the effect of determining the pose matching result based on the angle between the relevant lines in the two-dimensional screen space, thereby achieving the effect of effectively matching the object's pose while reducing terminal performance loss and ensuring matching accuracy.

[0099] In this embodiment of the disclosure, when determining whether the first key point information includes the first connecting line, multiple target key points can be judged first, so that if multiple target key points meet the corresponding conditions, the first connecting line between the target key points can be determined, and the second connecting line corresponding to the first connecting line can be determined.

[0100] Optionally, determining first key point information corresponding to multiple target key points and determining second key point information corresponding to second key point information based on multiple reference key points includes: determining a first connecting line between target key points when multiple target key points meet a second preset condition, and determining a second connecting line corresponding to the first connecting line based on multiple reference key points corresponding to multiple target key points.

[0101] The second preset condition can be a pre-set condition used to determine whether the connection between key points can be determined or whether it is necessary to determine it. Optionally, the second preset condition includes at least one of the following: the number of target key points reaches a second number, the distance between target key points is less than a preset distance threshold, and the key point triggering operation is a second triggering operation.

[0102] The second quantity can be any number, optionally any value greater than or equal to 2. The preset distance threshold can be a pre-set criterion for determining whether to determine the distance between key points. The preset distance threshold can be any distance value. The second trigger operation can be any trigger operation, optionally a trajectory drawing operation that continuously passes through two target key points, a click operation for inputting a second preset number of target key points, or a part selection operation for a target part, etc. The second preset number can be any value greater than or equal to 2. The target part can be an object part associated with multiple target key points. For example, the target part can be a hand.

[0103] As an optional implementation of this embodiment, when multiple target key points are determined, the number of target key points can be determined. Furthermore, when the number of target key points reaches a second quantity, it can be determined that multiple target key points satisfy a second preset condition. Alternatively, the distance between target key points can be determined and compared with a preset distance threshold. Furthermore, when it is determined that the distance is less than the preset distance threshold, it can be determined that multiple target key points satisfy the second preset condition. Alternatively, it can be determined whether the key point triggering operation corresponding to the target key point is a second triggering operation. Further, when it is determined that the key point triggering operation is a second triggering operation, it can be determined that multiple target key points satisfy the second preset condition. Further, a first connecting line corresponding to the multiple target key points can be determined based on the position information of the multiple target key points. And, a second connecting line corresponding to the first connecting line can be determined based on the position information of multiple reference key points corresponding to the multiple target key points. The advantage of this setting is that it achieves the effect of determining the key point information required for matching before attitude matching, thereby improving attitude matching efficiency and enhancing the flexibility of the attitude matching process.

[0104] In this embodiment of the disclosure, in order to make the information included in the final displayed posture prompt information more comprehensive and clear, optionally, posture prompt information corresponding to the target object is determined based on multiple target key points and multiple reference key points, and the posture prompt information is displayed, including: determining the object part in the target object that is associated with multiple target key points, generating posture prompt information based on the object part, multiple target key points and multiple reference key points, and displaying the posture prompt information.

[0105] As an optional implementation of this embodiment, when multiple target key points are determined and multiple reference key points are obtained, a reference key point corresponding to each target key point can be determined from the multiple reference key points. Further, the object parts associated with the multiple target key points in the target object can be determined, and the multiple target key points and their corresponding multiple reference key points can be matched. Further, at least one successfully matched target key point and / or at least one unmatched target key point can be determined based on the key point matching results. Then, posture prompt information can be generated based on the object part, the at least one successfully matched target key point, and / or the at least one unmatched target key point, so that the posture prompt information includes information such as the matching results of the object part and the target key points, and the generated posture prompt information is displayed.

[0106] The technical solution of this disclosure embodiment determines multiple target key points from multiple object key points in response to a key point triggering operation for object key points, and obtains a reference image corresponding to the image to be processed. Since the reference image includes multiple reference key points corresponding to the expected presentation posture of the target object, posture prompt information corresponding to the target object is determined based on the multiple target key points and multiple reference key points, and the posture prompt information is displayed. This achieves the effect of matching the object posture and the expected presentation posture based on the target key points and reference key points, reducing the amount of data processing and improving the posture matching efficiency.

[0107] Figure 3 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of the present disclosure, as shown below. Figure 3 As shown, the device includes an image acquisition module 310 and a posture prompting module 320. The image acquisition module 310 is used to acquire an image to be processed in response to an image processing request, and if the image to be processed contains a target object, to display multiple object key points corresponding to the target object in the image to be processed. The posture prompting module 320 is used to determine multiple target key points from the multiple object key points in response to a key point triggering operation for the object key points, and to display posture prompting information corresponding to the multiple target key points.

[0108] The technical solution of this disclosure embodiment, through the image acquisition module 310 responding to an image processing request, acquires an image to be processed. If the image to be processed contains a target object, it displays multiple object key points corresponding to the target object in the image. The acquisition of the image to be processed and the display of object key points can be triggered through simple interactive operations, providing a data foundation for subsequent pose matching and improving image processing efficiency. Then, through the pose prompting module 320 responding to a key point triggering operation targeting object key points, it determines multiple target key points from multiple object key points and displays pose prompt information corresponding to these target key points. This solves the problem that pose matching methods in related technologies rely on manual experience, are laborious and time-consuming, and affect the efficiency and accuracy of pose matching. It supports the custom determination of target key points, and is particularly suitable for matching local poses, i.e., processing only some object key points. Using target key points to generate pose prompt information can effectively reduce the amount of data processing in the pose matching process, thereby improving the efficiency and accuracy of pose matching. Moreover, the effect of pose matching of objects in the image through simple interactive operations and multiple target key points enhances the interactive experience in the pose matching process.

[0109] Based on any of the above optional technical solutions, optionally, the posture prompting module 320 is specifically used to perform at least one of the following operations: in response to a key point selection operation for the object key points, determining a plurality of target key points from a plurality of object key points based on the selected object key points; in response to a trajectory drawing operation for the target object, determining a plurality of target key points from a plurality of object key points based on the drawn target trajectory; in response to a part selection operation for the target object, determining an object part of the target object based on the part selection operation, and determining a plurality of target key points from a plurality of object key points based on the object part.

[0110] Based on any of the above optional technical solutions, optionally, the posture prompting module 320 includes: a reference image acquisition submodule and a posture prompting submodule. The reference image acquisition submodule is used to acquire a reference image corresponding to the image to be processed, wherein the reference image includes multiple reference key points corresponding to the expected presentation posture of the target object; the posture prompting submodule is used to determine posture prompting information corresponding to the target object based on the multiple target key points and the multiple reference key points, and to display the posture prompting information.

[0111] Based on any of the above optional technical solutions, optionally, the posture prompting submodule includes: a key point information determination unit and a posture prompting unit. The key point information determination unit is used to determine first key point information corresponding to a plurality of target key points, and to determine second key point information corresponding to the second key point information based on a plurality of reference key points; the posture prompting unit is used to determine posture prompting information corresponding to the target object based on the first key point information and the second key point information.

[0112] Based on any of the above optional technical solutions, optionally, the key point information determination unit is specifically used to determine key point association information corresponding to multiple target key points, and determine first key point information corresponding to multiple target key points according to the key point association information; wherein, the key point association information includes at least one of the location information of multiple target key points, the number of target key points, and the distance between target key points.

[0113] Based on any of the above optional technical solutions, optionally, the first key point information includes a first included angle between the target key points; the second key point information includes a second included angle between the reference key points corresponding to the target key points; the posture prompting unit is specifically used to determine the angle deviation between the first included angle and the second included angle, and to determine posture prompting information corresponding to the target object based on the angle deviation.

[0114] Based on any of the above optional technical solutions, optionally, the key point information determination unit is specifically used to determine a first included angle corresponding to the multiple target key points when the multiple target key points meet a first preset condition, and to determine a second included angle corresponding to the first included angle based on the multiple reference key points corresponding to the multiple target key points, wherein the first preset condition includes at least one of the following: the number of target key points reaches a first number, the key point triggering operation is a first triggering operation, and the object part associated with the multiple target key points in the target object is a preset part.

[0115] Based on any of the above optional technical solutions, optionally, the first key point information includes a first connecting line between the target key points, and the second key point information includes a second connecting line between the reference key points corresponding to the target key points; the posture prompting unit is specifically used to determine the length deviation between the first connecting line and the second connecting line, and determine posture prompting information corresponding to the target object based on the length deviation; and / or, determine the angle between the first connecting line and the second connecting line in the two-dimensional screen space, and determine the posture prompting information corresponding to the target object based on the angle.

[0116] Based on any of the above optional technical solutions, optionally, the key point information determination unit is specifically used to determine a first connection between the target key points when multiple target key points meet a second preset condition, and to determine a second connection corresponding to the first connection based on multiple reference key points corresponding to the multiple target key points, wherein the second preset condition includes at least one of the following: the number of target key points reaches a second number, the distance between the target key points is less than a preset distance threshold, and the key point triggering operation is a second triggering operation.

[0117] Based on any of the above optional technical solutions, optionally, a posture prompting submodule is used to determine the object part in the target object that is associated with multiple target key points, generate posture prompting information based on the object part, multiple target key points and multiple reference key points, and display the posture prompting information.

[0118] The image processing apparatus provided in this disclosure can execute the image processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0119] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0120] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Reference is made below. Figure 4 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 4 The diagram below shows the structure of the terminal device or server 500. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0121] like Figure 4As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0122] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0123] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0124] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0125] The electronic device provided in this embodiment and the image processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0126] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the image processing method provided in the above embodiments.

[0127] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0128] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0129] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0130] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to an image processing request, acquire an image to be processed; if the image to be processed contains a target object, display multiple object key points in the image to be processed corresponding to the target object; and in response to a key point triggering operation for the object key points, determine multiple target key points from the multiple object key points and display posture prompt information corresponding to the multiple target key points.

[0131] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0133] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not necessarily limiting in certain circumstances; for example, an image acquisition module can also be described as a "module for acquiring an image to be processed".

[0134] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0135] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] According to one or more embodiments of this disclosure, [Example 1] provides an image processing method, including: in response to an image processing request, acquiring an image to be processed; if the image to be processed contains a target object, displaying a plurality of object key points corresponding to the target object in the image to be processed; in response to a key point triggering operation for the object key points, determining a plurality of target key points from the plurality of object key points, and displaying posture prompt information corresponding to the plurality of target key points.

[0137] According to one or more embodiments of this disclosure, [Example 2] provides the method of Example 1, further comprising: optionally, determining a plurality of target keypoints from a plurality of object keypoints in response to a keypoint triggering operation for the object keypoints, including at least one of the following operations: determining a plurality of target keypoints from a plurality of object keypoints based on a selected object keypoint in response to a keypoint selection operation for the object keypoints; determining a plurality of target keypoints from a plurality of object keypoints based on a drawn target trajectory in response to a trajectory drawing operation for the target object; and determining an object part of the target object based on the object part selection operation in response to a part selection operation for the target object, and determining a plurality of target keypoints from a plurality of object keypoints based on the object part.

[0138] According to one or more embodiments of this disclosure, [Example 3] provides the method of Example 1, which further includes: optionally, displaying pose prompt information corresponding to the plurality of target key points includes: acquiring a reference image corresponding to the image to be processed, wherein the reference image includes a plurality of reference key points corresponding to the expected presentation pose of the target object; determining pose prompt information corresponding to the target object based on the plurality of target key points and the plurality of reference key points, and displaying the pose prompt information.

[0139] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 3, which further includes: optionally, determining the posture prompt information corresponding to the target object based on a plurality of target key points and a plurality of reference key points includes: determining first key point information corresponding to the plurality of target key points; determining second key point information corresponding to the first key point information based on the plurality of reference key points; and determining the posture prompt information corresponding to the target object based on the first key point information and the second key point information.

[0140] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 4, which further includes: Optionally, determining the first key point information corresponding to the plurality of target key points includes: determining key point association information corresponding to the plurality of target key points, and determining the first key point information corresponding to the plurality of target key points based on the key point association information; wherein the key point association information includes at least one of the location information of the plurality of target key points, the number of target key points, and the distance between the target key points.

[0141] According to one or more embodiments of this disclosure, Example Six provides the method of Example Four, which further includes: optionally, the first key point information includes a first included angle between the target key points; the second key point information includes a second included angle between the reference key points corresponding to the target key points; the step of determining the posture prompt information corresponding to the target object based on the first key point information and the second key point information includes: determining the angle deviation between the first included angle and the second included angle, and determining the posture prompt information corresponding to the target object based on the angle deviation.

[0142] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 6, which further includes: Optionally, determining the first key point information corresponding to the plurality of target key points and determining the second key point information corresponding to the first key point information based on the plurality of reference key points includes: when the plurality of target key points meet a first preset condition, determining a first included angle corresponding to the plurality of target key points, and determining a second included angle corresponding to the first included angle based on the plurality of reference key points corresponding to the plurality of target key points, wherein the first preset condition includes at least one of the following: the number of target key points reaches a first number, the key point triggering operation is a first triggering operation, and the object part associated with the plurality of target key points in the target object is a preset part.

[0143] According to one or more embodiments of this disclosure, Example 8 provides the method of Example 4, further comprising: optionally, the first key point information includes a first line connecting the target key points, and the second key point information includes a second line connecting the reference key points corresponding to the target key points; the step of determining the posture prompt information corresponding to the target object based on the first key point information and the second key point information includes: determining the length deviation between the first line and the second line, and determining the posture prompt information corresponding to the target object based on the length deviation; and / or, determining the angle between the first line and the second line in a two-dimensional screen space, and determining the posture prompt information corresponding to the target object based on the angle.

[0144] According to one or more embodiments of this disclosure, [Example Nine] provides the method of Example Eight, which further includes: optionally, determining first key point information corresponding to a plurality of target key points and determining second key point information corresponding to the first key point information based on a plurality of reference key points includes: when the plurality of target key points meet a second preset condition, determining a first connection between the target key points, and determining a second connection corresponding to the first connection based on a plurality of reference key points corresponding to the plurality of target key points, wherein the second preset condition includes at least one of the following: the number of target key points reaches a second number, the distance between the target key points is less than a preset distance threshold, and the key point triggering operation is a second triggering operation.

[0145] According to one or more embodiments of this disclosure, Example 10 provides the method of Example 3, which further includes: Optionally, determining and displaying posture prompt information corresponding to the target object based on a plurality of target key points and a plurality of reference key points includes: determining an object part in the target object that is associated with a plurality of target key points, generating posture prompt information based on the object part, the plurality of target key points and the plurality of reference key points, and displaying the posture prompt information.

[0146] According to one or more embodiments of this disclosure, [Example 11] provides an image processing apparatus, including: an image acquisition module, configured to acquire an image to be processed in response to an image processing request, and, if the image to be processed contains a target object, display a plurality of object key points corresponding to the target object in the image to be processed; and a posture prompting module, configured to determine a plurality of target key points from the plurality of object key points in response to a key point triggering operation for the object key points, and display posture prompting information corresponding to the plurality of target key points.

[0147] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0148] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0149] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An image processing method, characterized by, The method comprises: in response to an image processing request, obtaining a to-be-processed image, and in a case where the to-be-processed image contains a target object, displaying a plurality of object key points corresponding to the target object in the to-be-processed image; in response to a key point triggering operation on the object key points, determining a plurality of target key points from the plurality of object key points, and displaying posture prompt information corresponding to the plurality of target key points.

2. The image processing method of claim 1, wherein, The operation of determining a plurality of target key points from the plurality of object key points in response to a key point triggering operation on the object key points comprises at least one of the following operations: in response to a key point selection operation on the object key points, determining a plurality of target key points from the plurality of object key points according to the selected object key points; in response to a trajectory drawing operation on the target object, determining a plurality of target key points from the plurality of object key points according to a drawn target trajectory; in response to a part selection operation on the target object, determining an object part of the target object according to the part selection operation, and determining a plurality of target key points from the plurality of object key points based on the object part.

3. The image processing method of claim 1, wherein, The operation of displaying posture prompt information corresponding to the plurality of target key points comprises: obtaining a reference image corresponding to the to-be-processed image, wherein the reference image contains a plurality of reference key points corresponding to an expected presentation posture of the target object; determining posture prompt information corresponding to the target object according to the plurality of target key points and the plurality of reference key points, and displaying the posture prompt information.

4. The image processing method of claim 3, wherein, The operation of determining posture prompt information corresponding to the target object according to the plurality of target key points and the plurality of reference key points comprises: determining first key point information corresponding to the plurality of target key points, and determining second key point information corresponding to the first key point information according to the plurality of reference key points; determining posture prompt information corresponding to the target object according to the first key point information and the second key point information.

5. The image processing method of claim 4, wherein, The operation of determining first key point information corresponding to the plurality of target key points comprises: determining key point association information corresponding to the plurality of target key points, and determining first key point information corresponding to the plurality of target key points according to the key point association information; wherein the key point association information comprises at least one of position information of the plurality of target key points, a number of the target key points, and a distance between the target key points.

6. The image processing method of claim 4, wherein, The first key point information comprises a first included angle between the target key points, and the second key point information comprises a second included angle between the reference key points corresponding to the target key points; The operation of determining posture prompt information corresponding to the target object according to the first key point information and the second key point information comprises: determining an angle deviation between the first included angle and the second included angle, and determining posture prompt information corresponding to the target object according to the angle deviation.

7. The image processing method of claim 6, wherein, The determining the first key point information corresponding to the plurality of target key points, and the determining the second key point information corresponding to the first key point information according to the plurality of reference key points, comprises: In a case where the plurality of target key points satisfy a first preset condition, a first included angle corresponding to the plurality of target key points is determined, and a second included angle corresponding to the first included angle is determined according to the plurality of reference key points corresponding to the plurality of target key points, wherein the first preset condition comprises at least one of the number of the target key points reaching a first number, the key point triggering operation being a first triggering operation, and the object part associated with the plurality of target key points in the target object being a preset part.

8. The image processing method of claim 4, wherein, The first key point information comprises a first connecting line between the target key points, and the second key point information comprises a second connecting line between the reference key points corresponding to the target key points; The determining the posture prompt information corresponding to the target object according to the first key point information and the second key point information comprises: determining a length deviation between the first connecting line and the second connecting line, and determining the posture prompt information corresponding to the target object according to the length deviation; and / or, determining a connecting line included angle of the first connecting line and the second connecting line in a two-dimensional screen space, and determining the posture prompt information corresponding to the target object according to the connecting line included angle.

9. The image processing method of claim 8, wherein, The determining the first key point information corresponding to the plurality of target key points, and the determining the second key point information corresponding to the first key point information according to the plurality of reference key points, comprises: In a case where the plurality of target key points satisfy a second preset condition, a first connecting line between the target key points is determined, and a second connecting line corresponding to the first connecting line is determined according to the plurality of reference key points corresponding to the plurality of target key points, wherein the second preset condition comprises at least one of the number of the target key points reaching a second number, the distance between the target key points being less than a preset distance threshold, and the key point triggering operation being a second triggering operation.

10. The image processing method of claim 3, wherein, The determining the posture prompt information corresponding to the target object according to the plurality of target key points and the plurality of reference key points, and the displaying the posture prompt information, comprises: determining an object part associated with the plurality of target key points in the target object, generating posture prompt information according to the object part, the plurality of target key points and the plurality of reference key points, and displaying the posture prompt information.

11. An image processing apparatus characterized by comprising: Comprises: An image acquisition module is used for acquiring a to-be-processed image in response to an image processing request, and in a case where a target object is included in the to-be-processed image, displaying a plurality of object key points corresponding to the target object in the to-be-processed image; A posture prompt module is used for determining a plurality of target key points from the plurality of object key points in response to a key point triggering operation for the object key points, and displaying posture prompt information corresponding to the plurality of target key points.

12. An electronic device, comprising: The electronic device comprises: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the image processing method as claimed in any one of claims 1-10.

13. A storage medium containing computer-executable instructions, wherein: The computer executable instructions, when executed by a computer processor, perform the image processing method as claimed in any one of claims 1-10.

14. A computer program product, characterised in that, The computer program product comprises a computer program which, when executed by a processor, implements the image processing method according to any one of claims 1-10.

Images