Shooting method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a shooting method and device, electronic equipment and a readable storage medium, and belongs to the technical field of camera shooting. The method comprises the following steps: acquiring actual position coordinates of N object key points of a shooting object in a preview image displayed in a shooting preview interface; under the condition that the actual position coordinates of M object key points in the N object key points are matched with the reference position coordinates of M reference key points of at least one attitude template image, shooting at least one image; wherein the part posture similarity between the object part posture formed by the M object key points and the reference part posture formed by the M reference key points is greater than a first similarity threshold value; n is an integer greater than 1, M is a positive integer, and M is less than or equal to N.

Description

Technical Field

[0001] The present application belongs to the field of camera technology, and specifically relates to a shooting method, device, electronic device and readable storage medium. Background Art

[0002] Stage photography is an art form that aims to capture and record artistic moments of drama, dance, music, folk art and acrobatics on stage through photography. The key point of stage photography is that the photographer can capture representative scenes and beautiful expressions and movements in an instant, and vividly and perfectly express the artistic modeling on the stage.

[0003] However, in the process of stage shooting, since the performers are usually in motion, it is difficult to capture good images in the dynamic capture process, so the only way is to use trial and error shooting method, using electronic devices to continuously shoot a large number of images, and then select the better images from them. Continuously shooting a large number of images will increase the power consumption of electronic devices and shorten the use time of electronic devices. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a shooting method, device and electronic device, which can automatically and accurately capture an image of a part posture basically similar to that composed of reference key points in a posture template image as desired by the user based on the matching operation of key points without the need for user shooting input, thereby reducing the difficulty of shooting and increasing the success rate of shooting, without the need for the electronic device to continuously shoot a large number of images, which can reduce the power consumption of the electronic device and extend the use time of the electronic device.

[0005] In a first aspect, an embodiment of the present application provides a shooting method, the method comprising: obtaining the actual position coordinates of N object key points of a shooting object in a preview image displayed in a shooting preview interface; shooting at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image; wherein the similarity between the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than a first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

[0006] In a second aspect, an embodiment of the present application provides a shooting device, comprising: an acquisition module, used to acquire the actual position coordinates of N object key points of the shooting object in the preview image displayed in the shooting preview interface; a shooting module, used to shoot at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image; wherein the part posture similarity between the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than a first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0010] In a sixth aspect, an embodiment of the present application provides a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0011] In an embodiment of the present application, the actual position coordinates of N object key points of the photographed object in the preview image displayed on the shooting preview interface can be obtained; when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image, at least one image is photographed; wherein the part posture similarity of the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than the first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N. Through this scheme, since the object key points of the photographed object in the preview image can be matched with the reference key points in the posture template image in terms of key point position coordinates, and at least one image is photographed when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points, without the user's shooting input, the image that is substantially similar to the part posture composed of the reference key points in the posture template image that the user expects can be automatically and accurately captured based on the key point matching operation, thereby reducing the difficulty of shooting and increasing the success rate of shooting, without the need to continuously shoot a large number of images through the electronic device, thus reducing the power consumption of the electronic device and extending the use time of the electronic device. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flowchart of a shooting method provided by some embodiments of the present application;

[0013] Figure 2 is a schematic diagram of selecting a posture template image in a shooting method provided in some embodiments of the present application;

[0014] Figure 3 is a schematic diagram of selecting a posture template image in a shooting method provided in some embodiments of the present application;

[0015] Figure 4 is a schematic diagram of adjusting the position of a reference key point in a shooting method provided in some embodiments of the present application;

[0016] Figure 5 is a schematic diagram of adjusting the position of a reference key point in a shooting method provided in some embodiments of the present application;

[0017] Figure 6 It is a schematic diagram of customizing and adding a posture template image in a shooting method provided in some embodiments of the present application;

[0018] Figure 7 It is a schematic diagram of customizing and adding a posture template image in a shooting method provided in some embodiments of the present application;

[0019] Figure 8 is a schematic diagram of selecting a key point detection area in a shooting method provided in some embodiments of the present application;

[0020] Fig. 9 is a schematic diagram of selecting a key point detection area in a shooting method provided in some embodiments of the present application;

[0021] Fig.10 is a schematic diagram of setting the number of shots of a posture template image in a posture template sequence in a shooting method provided in some embodiments of the present application;

[0022] Fig.11 is a schematic diagram of setting whether to automatically zoom a photographed object in a photographing method provided in some embodiments of the present application;

[0023] Fig.12 is a schematic diagram of a photographing device provided in some embodiments of the present application;

[0024] Fig.13 is a schematic diagram of an electronic device provided by some embodiments of the present application;

[0025] Fig.14 It is a hardware schematic diagram of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0027] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0028] The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication; an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.

[0029] The terms "at least one (item)", "at least one of" and the like in the specification and claims of the present application refer to any one, any two or a combination of more than two of the objects included therein. For example, at least one (item) of a, b, and c can be represented by: "a", "b", "c", "a and b", "a and c", "b and c" and "a, b and c", where a, b, and c can be single or multiple. Similarly, "at least two (items)" refers to two or more, and its meaning is similar to that of "at least one (item)".

[0030] First, some nouns or terms involved in the specification and claims of this application are explained below.

[0031] Human key point detection: mainly detects some key points of the human body, such as joints, facial features, etc., and describes the human body's skeletal information and posture information through these key points.

[0032] Facial key point detection: used to locate and return the coordinates of key points in a face image, including the face contour, eyes, eyebrows, lips, and nose contour.

[0033] Logo: The logo in this application refers to text, symbols, images, etc. used to indicate information. Controls or other containers can be used as carriers for displaying information, including but not limited to text logos, symbol logos, and image logos.

[0034] Image fusion processing refers to the process of extracting useful information from each channel to the maximum extent through image processing and computer technology from image data collected by multiple source channels about the same target, and finally integrating them into high-quality images to improve the utilization rate of image information, improve the accuracy and reliability of computer interpretation, and enhance the spatial resolution and spectral resolution of the original image, which is beneficial for monitoring.

[0035] The following is a detailed description of the shooting method, device and electronic device provided in the embodiments of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0036] Stage photography is an art form that aims to capture and record artistic moments of drama, dance, music, folk art and acrobatics on stage through photography. These moments often have profound artistic significance and emotional expression. Through stage photography, photographers can capture representative scenes and beautiful expressions and movements in an instant, and shoot those beautiful and meaningful stage art performances to introduce them to the society for people to appreciate and savor. This form of artistic expression not only shows the charm of stage art, but also allows photographers to experience and feel the excitement of stage performances again through photos.

[0037] With the popularity of stage performances, stage scene photography has become a necessary part of daily photography. The key to stage photography is that the photographer can capture representative scenes and beautiful expressions and movements in an instant, vividly and perfectly present the artistic forms on the stage, and allow the photographer to experience and feel the excitement of stage performances again through photos.

[0038] It should be noted that the shooting method provided in some embodiments of the present application may be executed by a shooting device, an electronic device, or a functional module in an electronic device, etc. In some embodiments of the present application, an electronic device executing the shooting method is taken as an example to illustrate the shooting method provided in the embodiments of the present application.

[0039] The shooting method provided in the embodiment of the present application can be applied to stage shooting scenarios, wherein one specific application scenario is capturing the expressions and postures of singers in a concert, such as capturing the sad expression of male singer A in a solo concert; another specific application scenario is capturing the movements and postures of performers on a drama stage, such as capturing the jumping movements of male performer A and the clapping movements of female performer B in a multi-person drama.

[0040] Figure 1 FIG. 1 is a flowchart of a shooting method provided by some embodiments of the present application. Figure 1 As shown, the shooting method provided by some embodiments of the present application may include the following steps 101 and 102.

[0041] Step 101: The electronic device obtains the actual position coordinates of N object key points of the photographed object in the preview image displayed on the shooting preview interface.

[0042] Wherein, N is an integer greater than 1.

[0043] In some embodiments of the present application, the above-mentioned object key points may include at least one of human body key points and face key points.

[0044] In some embodiments of the present application, the above-mentioned human body key points may include but are not limited to at least one of the following: human body joint key points, human body facial features key points.

[0045] In some embodiments of the present application, the above-mentioned human joint key points may include but are not limited to at least one of the following: neck joint key points, shoulder joint key points, elbow joint key points, wrist joint key points, hip joint key points, knee joint key points, and ankle joint key points.

[0046] In some embodiments of the present application, the above-mentioned facial key points may include but are not limited to at least one of the following: facial contour key points, eye contour key points, eyebrow contour key points, lip contour key points, and nose contour key points.

[0047] In some embodiments of the present application, the above-mentioned shooting preview interface can be an interface used to display the preview image captured by the camera in real time during the shooting process through the camera application; the electronic device can display the shooting preview interface after starting the camera application.

[0048] In some embodiments of the present application, the above-mentioned photographing object can be any photographing object in motion, such as a person or an animal.

[0049] In some embodiments of the present application, the number of the above-mentioned shooting objects can be one or more.

[0050] In some embodiments of the present application, before obtaining the actual position coordinates of the N object key points in the preview image, the electronic device can first determine the above-mentioned shooting object in the preview image through the user's selection input of the shooting object of the preview image when the preview image is displayed on the above-mentioned shooting preview interface.

[0051] In some embodiments of the present application, the above-mentioned shooting object selection input can be used to select the shooting object.

[0052] In some embodiments of the present application, the above-mentioned shooting object selection input can be any possible form of input such as touch input, voice input or physical button input.

[0053] For example, taking the above-mentioned shooting object selection input as touch input as an example, the shooting object selection input may include but is not limited to: a single-click input, a double-click input, a triple-click input, a long press input, a heavy press input, a sliding input or a special trajectory input of the above-mentioned preview image by the user through a finger or a stylus; wherein the special trajectory input may include but is not limited to: any trajectory input such as a circular trajectory input, an elliptical trajectory input, a heart-shaped trajectory input, a wavy trajectory input, a square trajectory input, a rectangular trajectory input, a diamond trajectory input or a trapezoidal trajectory input.

[0054] For example, taking the above-mentioned shooting object selection input as voice input as an example, the shooting object selection input may include but is not limited to: voice "select object A" or voice "lock object B" and any other possible voice inputs.

[0055] For example, taking the above-mentioned shooting object selection input as a physical button input as an example, the shooting object selection input may include but is not limited to any of the following: the input of pressing the lock screen button and the volume "+" button at the same time, the input of pressing the lock screen button and the volume "-" button at the same time, the input of pressing the volume "+" button and the volume "-" button at the same time, and the input of pressing the lock screen button, the volume "+" button and the volume "-" button at the same time.

[0056] In some embodiments of the present application, the electronic device can obtain the actual position coordinates of the N object key points of the above-mentioned photographed object in the above-mentioned preview image through some trained models, and then obtain the action posture or expression posture of the photographed object.

[0057] For example, when a user needs to capture the sad expression of male singer A in a solo concert, after the electronic device acquires the preview image, it can send the preview image to a trained person detector to detect in real time whether there is a person in the preview image. When a person is detected in the preview image, the user can input the above-mentioned shooting object selection for male singer A among the people detected in the preview image, so that the electronic device determines male singer A as the above-mentioned shooting object. In the subsequent shooting process, male singer A will be tracked in real time, and the sad expression of male singer A will be captured.

[0058] Then, after the electronic device determines the male singer A, it can send the image of the male singer A to the trained tracker, and then use the detection result of the male singer A as a tracking template, send the subsequent preview image to the trained tracker, and use the tracking template to perform real-time shooting and tracking. If the male singer A is lost in the tracking, the preview image of the next frame is re-detected, and then after the image of the male singer A is detected, the image of the male singer A is sent to the tracker again, and the detection result of the male singer A is used as a tracking template, and the subsequent preview image is sent to the trained tracker, and the tracking template is used to perform real-time shooting and tracking. If the male singer A is successfully tracked, the actual position coordinates of the face area can be obtained, and then the face area output by the tracker is sent to the face key point detector to detect the face key points of the photographed object, specifically including the detection of the face contour key points, eye contour key points, eyebrow contour key points, lip contour key points and nose contour key points, so as to obtain the actual position coordinates of the face key points of the male singer A, so that the expression and posture of the male singer A can be obtained.

[0059] For example, when a user needs to capture the jumping action of male performer a and the clapping action of female performer b in a multi-person drama, after the electronic device collects the above preview image, it can send the preview image to a trained person detector to detect in real time whether there is a person in the preview image. When it is detected that there is a person in the preview image, the user can perform the above-mentioned shooting object selection input for the male performer a and the female performer b detected in the preview image, so that the electronic device determines the male performer a and the female performer b as the above-mentioned shooting objects. In the subsequent shooting process, the male performer a and the female performer b will be tracked in real time, and the jumping action of the male performer a and the clapping action of the female performer b will be captured. Then, after determining the male performer a and the female performer b, the electronic device can send the images of the male performer a and the female performer b into the human key point detector to perform human key point detection on the male performer a and the female performer b, specifically including the detection of the key points of the neck joint, the key points of the shoulder joint, the key points of the elbow joint, the key points of the wrist joint, the key points of the hip joint, the key points of the knee joint and the key points of the ankle joint. If the male performer a and the female performer b are tracked successfully, the actual position coordinates of the human body area can be obtained, and then the human body area output by the tracker is sent to the human body key point detector to obtain the actual position coordinates of the human body key points of the male performer a and the female performer b, so that the action postures of the male performer a and the female performer b can be obtained.

[0060] Step 102: When the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one gesture template image, the electronic device captures at least one image.

[0061] Among them, the part posture similarity between the object part posture composed of the above M object key points and the reference part posture composed of the above M reference key points is greater than a first similarity threshold; M is a positive integer, M≤N.

[0062] In some embodiments of the present application, the first similarity threshold may be a system default, or may be arbitrarily set by the user according to actual usage requirements.

[0063] It can be understood that when the part posture similarity between the object part posture composed of the above-mentioned M object key points and the reference part posture composed of the above-mentioned M reference key points is greater than the above-mentioned first similarity threshold, it can be considered that the object part posture composed of the M object key points and the reference part posture composed of the M reference key points are basically similar.

[0064] In some embodiments of the present application, the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the above-mentioned M reference key points, which can be understood as: the matching degree between the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points is greater than or equal to the matching degree threshold.

[0065] In some embodiments of the present application, the electronic device can determine whether the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points based on the Euclidean distance between each two corresponding key points among the M object key points and the M reference key points; the specific method will be described in detail in the following embodiments, and will not be described here to avoid repetition.

[0066] In some embodiments of the present application, the above-mentioned posture template image may be a posture template image preset by the system, or may be a posture template image arbitrarily set by the user according to usage requirements.

[0067] In some embodiments of the present application, the above-mentioned posture template image may be a three-dimensional image or a two-dimensional image.

[0068] Exemplarily, taking the capture of the sad expression of male singer A in a solo concert as an example, assuming that the reference part posture composed of the M reference key points of the at least one posture template image is a sad expression posture, then after the electronic device obtains the actual position coordinates of the N facial key points of male singer A in the preview image, it can automatically take at least one image when the actual position coordinates of M facial key points among the N facial key points match the reference position coordinates of the M reference key points of the at least one posture template image, thereby automatically capturing an image of the sad expression of male singer A.

[0069] Exemplarily, taking the capture of the jumping action of male performer a and the clapping action of female performer b in a multi-person drama as an example, assuming that the reference part posture composed of the M reference key points of the above-mentioned at least one posture template image includes the jumping action posture and the clapping action posture, then after the electronic device obtains the actual position coordinates of the N human body key points of the male performer a and the female performer b in the above-mentioned preview image, it can automatically take at least one image when the actual position coordinates of M human body key points among the N human body key points match the reference position coordinates of the M reference key points of the at least one posture template image, thereby automatically capturing images of the jumping action of male performer a and the clapping action of female performer b.

[0070] In some embodiments of the present application, each of the at least one posture template image corresponds to a number of shots. Exemplarily, the step 102 may be implemented by the following step 102a.

[0071] Step 102a, when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image, the electronic device takes at least one image according to the number of shots corresponding to each posture template image.

[0072] In some embodiments of the present application, the electronic device can pre-set the number of shots corresponding to each of the above-mentioned posture template images through user input, and then when the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the M reference key points of a certain posture template image, the image is taken according to the number of shots corresponding to the posture template image.

[0073] For example, Fig.10 As shown, the at least one posture template image mentioned above includes a posture template image 12 and a posture template image 15, and the number of shots corresponding to the posture template image 12 is 10, and the number of shots corresponding to the posture template image 15 is 1; then when the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the M reference key points of the at least one posture template image, the electronic device can shoot 10 images according to the number of shots corresponding to the posture template image 12, and shoot 1 image according to the number of shots corresponding to the posture template image 15, so as to obtain the at least one image mentioned above.

[0074] In some embodiments of the present application, since the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the M reference key points of the above-mentioned at least one posture template image, the electronic device can take at least one image according to the number of shots corresponding to each posture template image. Therefore, based on the matched different posture template images, the corresponding number of images can be taken, so that the number of images required by the user can be taken for different posture template images, thereby improving the flexibility of taking images.

[0075] In some embodiments of the present application, the above step 102 can be specifically implemented through the following step 102b.

[0076] Step 102b: When the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the gesture template image in at least one gesture template sequence, the electronic device captures at least one image.

[0077] The above-mentioned posture template sequence includes at least two posture template images, and the posture template sequence includes at least one of the following: an expression posture template sequence, an action posture template sequence, and an expression-action posture template sequence.

[0078] In some embodiments of the present application, the gesture template images in the above-mentioned expression gesture template sequence are all used to represent the expression gesture of the photographed subject.

[0079] In some embodiments of the present application, the posture template images in the above-mentioned action posture template sequence are all used to represent the action posture of the photographed object.

[0080] In some embodiments of the present application, the gesture template images in the above-mentioned expression and action gesture template sequence are all used to represent the expression and action gesture of the photographed object.

[0081] In some embodiments of the present application, the number of posture template images in any two posture template sequences in the at least one posture template sequence may be the same or different.

[0082] In some embodiments of the present application, at least two posture template images in each of the posture template sequences are arranged in sequence.

[0083] In some embodiments of the present application, the electronic device may first set the arrangement order of at least two posture template images in each of the above-mentioned posture template sequences through user input, and then shoot the above-mentioned at least one image when the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the M reference key points of the posture template image in the above-mentioned at least one posture template sequence.

[0084] In some embodiments of the present application, since the electronic device can capture the above-mentioned at least one image when the actual position coordinates of the above-mentioned M object key points match the reference position coordinates of the M reference key points of the posture template image in the above-mentioned at least one posture template sequence, it is possible to automatically capture images of multiple expression postures, action postures or expression-action postures when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points, thereby further improving the flexibility of shooting and simplifying the process of capturing images of multiple expression postures, action postures or expression-action postures.

[0085] In some embodiments of the present application, the above step 102b can be specifically implemented through the following steps 102b1 and 102b2.

[0086] Step 102b1: The electronic device detects the actual position coordinates of M object key points of the photographed object according to the arrangement order of the posture template images in each posture template sequence.

[0087] For example, Fig.10As shown, the at least one posture template sequence includes an expression template sequence 11, and the expression template sequence 11 includes a posture template image 12 and a posture template image 13 arranged in sequence. Then the electronic device can detect the actual position coordinates of M object key points of the photographed object according to the arrangement order of the posture template image 12 and the posture template image 13.

[0088] Step 102b2: When the distance between the actual position coordinates of each object key point among the M object key points and the reference position coordinates of the corresponding reference key point among the M reference key points of the i-th posture template image in the posture template sequence is less than the coordinate distance threshold, the electronic device captures at least one image.

[0089] Among them, the object part posture composed of M object key points in each image and the reference part posture composed of M reference key points in the above i-th posture template image have a posture similarity greater than the above-mentioned first similarity threshold; i is a positive integer, i≤the total number of posture template images in each posture template sequence.

[0090] In some embodiments of the present application, the M object key points correspond one-to-one to the M reference key points.

[0091] Exemplarily, assuming that the above-mentioned M object key points include object key point a, object key point b and object key point c, and the above-mentioned M reference key points include: reference key point A corresponding to object key point a, reference key point B corresponding to object key point b, and reference key point C corresponding to object key point c; then when the distance between the actual position coordinates of object key point a and the reference position coordinates of reference key point A is less than the above-mentioned coordinate distance threshold, and the distance between the actual position coordinates of object key point b and the reference position coordinates of reference key point B is less than the coordinate distance threshold, and the distance between the actual position coordinates of object key point c and the reference position coordinates of reference key point C is less than the coordinate distance threshold, the electronic device can capture at least one image.

[0092] In some embodiments of the present application, the above-mentioned coordinate distance threshold may be a system default, or may be arbitrarily set by the user according to actual usage requirements.

[0093] It can be understood that when the distance between the actual position coordinates of an object key point and the reference position coordinates of a reference key point is less than the above-mentioned coordinate distance threshold, it can be considered that the object key point matches the reference key point.

[0094] In some embodiments of the present application, since images with part postures similar to the reference part posture composed of M reference key points of the above-mentioned i-th posture template image can be captured in sequence according to the arrangement order of the posture template images in each posture template sequence, images can be captured in the order of the part postures of the subject required by the user, so as to capture images in a sequence that meets the user's needs.

[0095] In some embodiments of the present application, the above step 102b can be specifically implemented through the following steps 102b3 and 102b4.

[0096] Step 102b3: The electronic device detects the actual position coordinates of M object key points of the photographed object.

[0097] Step 102b4, the electronic device captures at least one image when the distance between the reference position coordinates of each reference key point among the M reference key points of the jth posture template image in the posture template sequence and the actual position coordinates of the corresponding object key point among the M object key points is less than the coordinate distance threshold.

[0098] Among them, the above-mentioned j-th posture template image is any posture template image in the above-mentioned posture template sequence; the object part posture composed of M object key points in each image and the part posture similarity of the reference part posture composed of M reference key points of the j-th posture template image is greater than the above-mentioned first similarity threshold; j is a positive integer, j≤the total number of posture template images in each posture template sequence.

[0099] For the specific description of the above steps 102b3 and 102b4, reference may be made to the relevant description of the above steps 102b1 and 102b2, and in order to avoid repetition, they will not be repeated here.

[0100] In some embodiments of the present application, since the distance between the reference position coordinates of each reference key point among the M reference key points of the j-th posture template image in the posture template sequence and the actual position coordinates of the corresponding object key point among the M object key points are less than the coordinate distance threshold, the electronic device can take at least one image. Therefore, as long as an image with a part posture similar to the part posture of the posture template image is detected, the electronic device will take a snapshot, thereby reducing the shooting time and shortening the shooting process.

[0101] In the shooting method provided in some embodiments of the present application, since the object key points of the shooting object in the preview image can be matched with the reference key points in the posture template image in terms of key point position coordinates, and at least one image is shot when the actual position coordinates of M object key points match the reference position coordinates of M reference key points, an image that is basically similar to the posture of the part formed by the reference key points in the posture template image as desired by the user can be automatically and accurately captured based on the key point matching operation, thereby reducing the difficulty of shooting and increasing the success rate of shooting without the need to continuously shoot a large number of images through the electronic device, which can reduce the power consumption of the electronic device and extend the use time of the electronic device.

[0102] In some embodiments of the present application, before the above step 102, the shooting method provided by some embodiments of the present application may also include the following steps 103 to 107.

[0103] Step 103: The electronic device receives a user's input of selecting a template image from a set of gesture template images.

[0104] In some embodiments of the present application, the above-mentioned posture template image set includes at least two posture template images.

[0105] In some embodiments of the present application, the above-mentioned template image selection input can be used to select a posture template image in a posture template image set.

[0106] In some embodiments of the present application, the template image selection input may be any possible form of input such as touch input, voice input, or physical key input.

[0107] For example, taking the above-mentioned template image selection input as touch input as an example, the template image selection input may include but is not limited to: single-click input, double-click input, triple-click input, long press input, heavy press input, sliding input or special trajectory input of the above-mentioned posture template image set by the user through a finger or a stylus; among which, the special trajectory input may include but is not limited to: circular trajectory input, elliptical trajectory input, heart-shaped trajectory input, wavy trajectory input, square trajectory input, rectangular trajectory input, diamond trajectory input or trapezoidal trajectory input and other arbitrary trajectory inputs.

[0108] For example, taking the template image selection input as voice input, the template image selection input may include but is not limited to: voice "select posture template image A" or voice "posture template image B" and any other possible voice inputs.

[0109] For example, taking the above-mentioned template image selection input as a physical button input as an example, the template image selection input may include but is not limited to any of the following: the input of pressing the lock screen button and the volume "+" button at the same time, the input of pressing the lock screen button and the volume "-" button at the same time, the input of pressing the volume "+" button and the volume "-" button at the same time, and the input of pressing the lock screen button, the volume "+" button and the volume "-" button at the same time.

[0110] Step 104: The electronic device selects a first posture template image from a posture template image set in response to a template image selection input.

[0111] In some embodiments of the present application, the number of the first posture template images may be one or more.

[0112] Step 105: The electronic device receives a user's input for selecting a region of the first posture template image.

[0113] In some embodiments of the present application, the above region selection input may be used to select an image region in a posture template image.

[0114] In some embodiments of the present application, the above-mentioned area selection input can be any possible form of input such as touch input, voice input or physical key input.

[0115] For example, taking the above-mentioned area selection input as touch input as an example, the area selection input may include but is not limited to: single-click input, double-click input, triple-click input, long press input, heavy press input, sliding input or special trajectory input of the above-mentioned first posture template image by the user through a finger or a stylus; among which, the special trajectory input may include but is not limited to: circular trajectory input, elliptical trajectory input, heart-shaped trajectory input, wavy trajectory input, square trajectory input, rectangular trajectory input, diamond trajectory input or trapezoidal trajectory input and other arbitrary trajectory inputs.

[0116] For example, taking the above-mentioned area selection input as a voice input as an example, the area selection input may include but is not limited to: voice "select image area a" or voice "lock image area b" and any other possible voice inputs.

[0117] For example, taking the above-mentioned area selection input as a physical button input, the area selection input may include but is not limited to any of the following: the input of pressing the lock screen button and the volume "+" button at the same time, the input of pressing the lock screen button and the volume "-" button at the same time, the input of pressing the volume "+" button and the volume "-" button at the same time, and the input of pressing the lock screen button, the volume "+" button and the volume "-" button at the same time.

[0118] Step 106: In response to the region selection input, the electronic device determines the region selected by the region selection input as a key point detection region of the first posture template image.

[0119] In some embodiments of the present application, the key point detection area is an area where key point detection is performed.

[0120] Step 107: The electronic device performs key point detection on the key point detection area to obtain M reference key points.

[0121] For other descriptions of the embodiments of the present application, reference can be made to the relevant descriptions in the above embodiments. To avoid repetition, they will not be repeated here.

[0122] For example, when a user needs to capture the sad expression of male singer A in a solo concert, he can first select and input a template image of the posture template image set; the electronic device responds to the template image selection input and selects a first posture template image from the posture template image set. Then the user can perform a region selection input on the first posture template image; the electronic device responds to the region selection input and determines the face region selected by the region selection input as the key point detection area of ​​the first posture template image. Thus, the electronic device can perform key point detection on the key point detection area to obtain the above-mentioned M reference key points.

[0123] For example, when a user needs to capture the jumping action of male performer a and the clapping action of female performer b in a multi-person drama, the user can first select and input the template image of the posture template image set; the electronic device responds to the template image selection input and selects the first posture template image from the posture template image set. Then the user can perform area selection input on the first posture template image; the electronic device responds to the area selection input and determines the leg area and hand area selected by the area selection input as the key point detection area of ​​the first posture template image. Thus, the electronic device can perform key point detection on the key point detection area to obtain the above-mentioned M reference key points.

[0124] In some embodiments of the present application, since the electronic device can select the key point detection area in the first posture template image through user input, and perform key point detection on the key point detection area to obtain the above-mentioned M reference key points, key point tracking and matching can be performed only on the image area selected by the user, thereby improving the flexibility of key point tracking and matching.

[0125] In some embodiments of the present application, before the above step 102, the shooting method provided by some embodiments of the present application may further include the following steps 108 to 111.

[0126] Step 108: The electronic device receives a user's input of selecting a template image from a set of gesture template images.

[0127] Step 109: The electronic device selects a second posture template image from the posture template image set in response to the template image selection input, and displays at least one reference key point identifier on the second posture template image.

[0128] In some embodiments of the present application, the number of the first posture template images may be one or more.

[0129] In some embodiments of the present application, the second posture template image and the first posture template image may be the same as or different from each other.

[0130] Wherein, each reference key point identifier in the above-mentioned at least one reference key point identifier is used to indicate a reference key point.

[0131] In some embodiments of the present application, each reference key point identifier in the at least one reference key point identifier may be used to identify a reference key point in the second posture template image.

[0132] In some embodiments of the present application, the display parameters identified by the reference key points may be any possible display parameters.

[0133] In some embodiments of the present application, the above display parameters may include but are not limited to at least one of the following: display color, display shape, display size, display transparency, etc.

[0134] For example, Figure 5 As shown, the reference key point mark 51 can be a black equilateral triangle mark with a side length of 2 mm.

[0135] Step 110: The electronic device receives a user's key point mark editing input for at least one reference key point mark.

[0136] In some embodiments of the present application, the above-mentioned key point identification editing input can be used to edit the key point identification.

[0137] In some embodiments of the present application, the key point identification editing input may be any possible form of input such as touch input, voice input, or physical key input.

[0138] For example, taking the above-mentioned key point identification editing input as touch input as an example, the key point identification editing input may include but is not limited to: a single-click input, double-click input, triple-click input, long press input, heavy press input, sliding input or special trajectory input by a user through a finger or a stylus for at least one of the above-mentioned reference key point identifications; wherein, the special trajectory input may include but is not limited to: circular trajectory input, elliptical trajectory input, heart-shaped trajectory input, wavy trajectory input, square trajectory input, rectangular trajectory input, diamond trajectory input or trapezoidal trajectory input and other arbitrary trajectory inputs.

[0139] For example, taking the above-mentioned key point mark editing input as voice input as an example, the key point mark editing input may include but is not limited to: voice "delete key point mark 1" or voice "adjust the position of key point mark 2" and any other possible voice inputs.

[0140] For example, taking the above-mentioned key point identification editing input as a physical button input as an example, the key point identification editing input may include but is not limited to any of the following: the input of pressing the lock screen button and the volume "+" button at the same time, the input of pressing the lock screen button and the volume "-" button at the same time, the input of pressing the volume "+" button and the volume "-" button at the same time, and the input of pressing the lock screen button, the volume "+" button and the volume "-" button at the same time.

[0141] Step 111: The electronic device performs a key point identification editing operation in response to a key point identification editing input.

[0142] The key point mark editing operation includes at least one of the following: adding at least one reference key point mark, deleting at least one key point mark, and adjusting the display position of at least one reference key point mark.

[0143] In some embodiments of the present application, the above-mentioned addition of at least one reference key point identifier is to add at least one reference key point identifier in addition to the at least one reference key point identifier displayed on the above-mentioned second posture template image.

[0144] In some embodiments of the present application, the deleting of at least one key point identifier is to delete at least one reference key point identifier displayed on the second posture template image.

[0145] In some embodiments of the present application, the above adjustment of the display position of at least one reference key point marker is to adjust the display position of at least one reference key point marker displayed on the above second posture template image.

[0146] In some embodiments of the present application, since the electronic device can perform key point identifier editing operations on the reference key point identifiers displayed in the posture template image through user input, the reference key point identifiers in the posture template image can be flexibly edited so that the reference part posture composed of the reference key points in the posture template image meets the shooting part posture requirements required by the user.

[0147] In some embodiments of the present application, the above-mentioned M object key points and the above-mentioned M reference key points constitute M pairs of key points, and each pair of key points includes an object key point and a reference key point at a position corresponding to the object key point. Exemplarily, before the above-mentioned step 102, the shooting method provided in some embodiments of the present application may also include the following steps 112 and 113.

[0148] Step 112: The electronic device calculates the Euclidean distance between the object key point and the reference key point in each pair of key points based on the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points.

[0149] It should be noted that the Euclidean distance, also known as the Euclidean metric or the Euclidean distance, is the true distance between two points in the m-dimensional space.

[0150] Step 113: When the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to the distance threshold, the electronic device determines that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points.

[0151] In some embodiments of the present application, the above distance threshold may be a system default, or may be arbitrarily set by the user according to actual usage requirements.

[0152] For example, taking the above object key points including the above human key points as an example, the electronic device can first calculate the Euclidean distance between the object key points and the reference key points of each pair of key points by the following formula (1):

[0153]

[0154] in, represents the Euclidean distance between the p-th person and the i-th corresponding key point. represents the position coordinates of the i-th key point in the p-th person in the above preset template image. Indicates the position coordinates of the i-th key point of the p-th person in the above-mentioned preview image.

[0155] For example, is (a, b), is (c, d), then Among them, a, b, c, and d are all positive integers.

[0156] In this way, the Euclidean distance between the object key point and the reference key point of each pair of key points can be calculated, so that the real distance between the two points in the two-dimensional space can be obtained.

[0157] When the above Euclidean distance is less than or equal to a distance threshold Th i , the above two key points are considered to be similar or matched. In the following formula (2), is_near i Indicates whether the position of the i-th key point in the above posture template image and the above preview image is similar, Represents the scale factor of the pth person, usually the torso size of the person.

[0158]

[0159] When the number of similar key points in all key point detection areas selected by the user reaches a certain ratio, the human body posture in the posture template image and the preview image is considered to be similar, and the similarity ratio is used as the human body posture similarity score. p Indicates whether the posture template image is similar to the pth person in the preview image, N represents the number of all key points in all key point detection areas selected by the user, Th simi Indicates the posture similarity ratio threshold. If it exceeds this threshold, the postures of the two are considered similar.

[0160]

[0161] In this way, by comparing with the above distance threshold, it is possible to accurately determine whether any two key points match, thereby improving the accuracy of key point matching and simplifying the key point matching process.

[0162] In some embodiments of the present application, since the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to the distance threshold, the electronic device determines that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points. Therefore, the Euclidean distance can be used to accurately determine the degree of match between the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points.

[0163] In some embodiments of the present application, when the number of the above-mentioned photographed objects is at least one, the number of the above-mentioned posture template images is one and at least two images are photographed, after the above-mentioned step 102, the shooting method provided by some embodiments of the present application may also include the following steps 114 and 115.

[0164] Step 114: For each photographed object, the electronic device determines a reference fused image from at least two images.

[0165] The similarity between the object part posture composed of the M object key points in the reference fusion image and the reference part posture composed of the M reference key points in the posture template image is greater than a second similarity threshold.

[0166] In some embodiments of the present application, the second similarity threshold may be a system default, or may be arbitrarily set by the user according to actual usage requirements.

[0167] It can be understood that when the part posture similarity between the object part posture composed of the M object key points in the above-mentioned benchmark fusion image and the reference part posture composed of the M reference key points in the above-mentioned posture template image is greater than the above-mentioned second similarity threshold, it can be considered that the object part posture composed of the M object key points and the reference part posture composed of the M reference key points are basically similar.

[0168] In some embodiments of the present application, the second similarity threshold and the first similarity threshold may be the same or different.

[0169] In some embodiments of the present application, the at least two images mentioned above may be at least two images captured continuously.

[0170] In some embodiments of the present application, when the number of the above-mentioned photographed objects is one, if a human face is detected, the above-mentioned at least two images captured will be sorted according to the expression similarity scores, and the image with the highest expression similarity will be determined as the benchmark fusion image; if no human face is detected, the above-mentioned at least two images captured will be sorted according to the human body posture similarity scores, and the image with the highest human body posture similarity will be determined as the benchmark fusion image.

[0171] In some embodiments of the present application, when the number of the above-mentioned photographed objects is at least two, the above-mentioned at least two images taken are sorted by expression similarity score and posture similarity score according to the individuals. For the i-th person, if there is a face, the frame with the highest expression similarity score of the i-th person in the at least two images is selected as the reference fusion image for regional fusion of the i-th person. If there is no face, the frame with the highest posture similarity score of the i-th person in the at least two images is selected as the reference fusion image for regional fusion of the i-th person.

[0172] Step 115: The electronic device performs image fusion processing on at least two images based on the reference fusion image corresponding to each photographed object.

[0173] In some embodiments of the present application, each photographed subject in a multi-person scene has a corresponding benchmark fusion image. When performing multi-frame fusion, regional fusion processing is performed based on the benchmark fusion image corresponding to each photographed subject to ensure that all photographed subjects in the image obtained by the fusion processing have the posture desired by the photographer, and can achieve the purpose of noise reduction and image enhancement.

[0174] For the specific method of the above fusion processing, please refer to the specific description in the relevant technology. In order to avoid repetition, it will not be repeated here.

[0175] For example, taking the capture of the sad expression of male singer A in a solo concert as an example, after the electronic device automatically captures at least two images of the sad expression of male singer A, the electronic device can determine a baseline fusion image from the at least two images, and then perform image fusion processing on the at least two images based on the baseline fusion image to ensure that the male singer A in the image obtained by the fusion processing has the posture desired by the photographer, and can achieve the purpose of noise reduction and image enhancement.

[0176] For example, taking the capture of the jumping action of male performer a and the clapping action of female performer b in a multi-person drama as an example, after the electronic device continuously captures at least two images, the electronic device can determine the reference fusion image corresponding to male performer a and the reference fusion image corresponding to female performer b from the at least two images, and then perform image fusion processing on the at least two images in different regions based on the determined reference fusion images. In this way, it can be ensured that each photographed object has the posture desired by the photographer, and the purpose of noise reduction and image enhancement can be achieved.

[0177] In some embodiments of the present application, since the electronic device can first determine the baseline fusion image corresponding to each photographed object, and then perform fusion processing on at least two captured images based on the baseline fusion image, each photographed object in the final output image can have the posture desired by the photographer, and the purpose of noise reduction and image enhancement can be achieved.

[0178] The following is an illustrative description of the shooting methods provided in some embodiments of the present application in conjunction with the accompanying drawings.

[0179] For example, taking the above-mentioned posture template image as a classic template image of a concert as an example, the shooting method provided in some embodiments of the present application may include the following steps a to i:

[0180] Step a: The user selects a preset concert classic template image.

[0181] Users can input and select the best moment freeze function to open the stage mode in the electronic device, such as Figure 2As shown, the user clicks the classic template set icon 21 on the right side of the preview interface 20, triggering the electronic device to open the classic template image selection drop-down bar. Figure 3 As shown, some classic concert template images are preset in the classic template set 31 , and the user can select by clicking the thumbnail 32 of the classic template image in the drop-down bar, and the electronic device can display the classic template image 33 selected by the user in the preview interface 20 .

[0182] If the user is not satisfied with the action posture and expression posture of the currently selected classic template image and wants to make fine adjustments based on the classic template image, then Figure 4 As shown, the user can click the custom icon 41 on the right side of the preview interface 20, and then Figure 5 As shown, the electronic device can generate the corresponding key point identifier on the selected classic template image displayed in the current preview interface 20. Then the user can drag the key point identifier 51 displayed in the preview interface 20 to adjust the action posture or expression posture. When the user has completed the adjustment, the user can click the save button 52 on the right side of the preview interface 20 to save the classic template image. When saving, you can choose to replace the save or create a new save; replacing the save will replace the previous classic template image with the classic template image adjusted by the user; creating a new save will retain the original classic template image and add a new classic template image adjusted by the user.

[0183] Step b: The user adds a concert image as a classic template image.

[0184] like Figure 6 As shown, the user can upload the concert image to the classic template set 31 by clicking the "+" icon 61 in the drop-down bar of the classic template set 31, which is convenient for selecting classic template images in the future. After the user clicks the "+" icon in the drop-down bar of the classic template set, the electronic device can automatically jump to the album, and then the user can check the concert image they want to upload in the album to upload. This upload operation can select multiple concert images in the album at one time and upload them to the classic template set at the same time. After adding the classic template image, as shown in the figure below, the concert image can be uploaded to the classic template set 31. Figure 7 As shown, the first image 71 of the newly uploaded concert images is displayed on the preview interface 20, and a prompt "New template has been added" is displayed.

[0185] Step c: The user selects the area of ​​interest of the classic template image.

[0186] like Figure 8 As shown, the user can select a classic template image in the classic template set drop-down bar, click the pen icon 81 displayed on the right side of the preview interface 20, and specify a key point detection area for each classic template image. Fig. 9As shown, the user selects the key point detection area 91 by manually painting on the preview interface 20, and the key point detection area 91 is displayed on the preview interface 20. The user can select multiple different key point detection areas at the same time, so that the electronic device can use the key point detection area selected by the user in the classic template image as the focus area of ​​the classic template image matching, for subsequent key point feature extraction and detection.

[0187] Step d: After the user has selected the above key point detection area, click the pen icon displayed on the right side of the preview screen again to exit the selection of the key point detection area.

[0188] After determining the key point detection area, the electronic device can perform human key point detection and face key point detection on the classic template image selected by the user, and display the key points detected in the key point detection area. When the user wants to readjust the position of the key point, the key point adjustment can be performed through the customization method in step a above. After all steps of the classic template image are adjusted, a classic template image corresponds to a set of key point detection areas and a set of subject key point information. Save the key point detection results of the key point detection area in the classic template image as a subsequent template to be matched.

[0189] Step e: In addition to the above-mentioned method of presetting the classic template image, the user can also manually adjust the key point positions of the three-dimensional human body posture and the key point positions of the three-dimensional face posture through the preset human three-dimensional model, and use it as the classic template image to be matched.

[0190] like Figure 2 As shown, the user enters the stage mode and can enter the three-dimensional model customization setting interface by clicking the "3D template customization" small icon 22 on the right side of the preview screen. The preview screen prompts the user "Please select a three-dimensional model", and the user can choose to customize the template expression or the template action. If the user chooses to customize the template expression, the three-dimensional model of the face is loaded in the preview interface. If the user chooses to customize the template action, the three-dimensional model of the human body is loaded in the preview interface. The three-dimensional face model displays the three-dimensional face key point information, and the three-dimensional human body model displays the three-dimensional human body key point information. The user manually adjusts the posture and facial expression of the human body by manually pulling the position of the human body key point and the position of the face key point in the preview interface. The small picture in the lower right corner of the preview screen displays the two-dimensional picture imaging effect corresponding to the three-dimensional model in real time. When the user has adjusted the posture or expression of the three-dimensional model, he can click the save icon in the lower right corner of the preview interface to save the corresponding action template image or expression template image.

[0191] When the posture and expression of the user's 3D model are adjusted, the complete user-defined classic template image is displayed on the preview interface, and a prompt "Customized template has been locked" is displayed. After the user clicks the save icon in the lower right corner of the preview interface, a classic template set drop-down bar appears on the preview screen, and the user-defined classic template image is saved in the thumbnail of the classic template set drop-down bar. The preview interface displays the user-defined template image, and a prompt "Customized template has been added" is displayed.

[0192] In this way, the setting of the above-mentioned classic template image can be completed, making it easier for subsequent users to select the classic template image for key point matching.

[0193] Step f: After the user clicks on the best moment to automatically freeze, it jumps to the default posture template sequence setting interface to be matched. In the posture template sequence setting interface, the electronic device prompts the user to "please add the automatic freeze expression set and action set". The existing classic template set is displayed at the bottom of the posture template sequence setting interface. The user can drag the classic template image in the classic template set to the expression template set or action template set to add it to the expression template sequence to be matched or the action template sequence to be matched. The template sequence in the expression template set only focuses on the expression of the template. The template sequence in the action template set only focuses on the action of the template. The same template can be placed in both the expression template set and the action template set, or it can be placed only in the expression template set, or only in the action template set. Within the template set sequence, it supports dragging templates to adjust the order.

[0194] By double-clicking the classic template image that has been added to the template sequence, you can set the number of shots for each classic template image. If the user does not set this option, the default number of shots for each classic template image is 3. After the user sets it, the number of shots for each classic template image is displayed as a number in the upper right corner of the classic template image. For example, Fig.10 As shown, the number of shots for the first classic template image 12 in the expression template sequence 11 is set to 10, and the number of shots for the second classic template image 13 in the expression template sequence 11 is set to N; the number of shots for the first classic template image 15 in the action template sequence 14 is set to 1, and the number of shots for the second classic template image 16 in the action template sequence 14 is set to 3. Among them, the number of shots being N means that there is no limit on the number of snapshots, and a snapshot is taken as long as a moment similar to the classic template image appears.

[0195] After the user completes the setting, click the Save button 17 to set it as the default posture template sequence to be matched. In the subsequent shooting process, if there is no other customized operation, the default posture template sequence will be applied to all selected shooting objects.

[0196] Step g: Select the subject.

[0197] Step g1: Single target: Select whether to use automatic zoom.

[0198] For example, Fig.11 As shown, the user has only selected a single photographing object 110. The user can double-click the photographing object 110 to select whether to support automatic zoom. If the user chooses not to support the automatic zoom function, the zoom ratio manually zoomed by the user is kept unchanged. If the user chooses to support the automatic zoom function, the zoom ratio is adjusted according to the height H of the photographing object currently detected. detect and the subject height H in the first classic template image to be matched in the pose template sequence model , calculate the zoom ratio To ensure that the current size of the photographed object is similar to the size of the target subject in the posture template sequence. Then, automatic scaling is performed according to the calculated zoom ratio.

[0199] After setting up support for automatic zoom, the classic template images to be matched in the pose template sequence are matched in order. When the number of automatically captured images of the first classic template image to be matched in the pose template sequence reaches the number set by the user, the classic template image to be matched becomes the second one. At this time, the zoom ratio is recalculated according to the height of the target subject in the current classic template image, and automatic zooming is performed according to the calculation result. This cycle is repeated until all the classic template images to be matched are captured.

[0200] Step g2: Multi-person target: Set a personalized customized template sequence for each subject.

[0201] If the user selects multiple subjects, the user can set personalized expression template sequences and action template sequences for each subject based on the set default posture template sequence to be matched. After the user selects multiple subjects, click the "+" prompt that appears in the upper right corner of the target subject to enter the multi-target personalized setting interface. In the multi-target personalized setting interface, the expression template sequence and action template sequence of each subject inherit the default settings made in the above steps. The user can change the expression template sequence, action template sequence and number of shots for each subject based on the default settings. Different subjects can be matched and captured with different template sequences. In the automatic freeze of multiple targets, the automatic zoom function is not supported.

[0202] Step h: Perform real-time classic template image matching based on the electronic device preview image.

[0203] First, human body key point detection is performed based on the preview image, and the detected human body key points are matched with the human body key points in the posture template sequence to determine whether the performer's action posture is similar to the set classic template image. Then, facial key point detection is performed based on the preview image, and the detected facial key points are matched with the facial key points in the posture template sequence to determine whether the performer's expression posture is similar to the set classic template image. When the performer's action posture or expression posture in the preview image is similar to the classic template image in the posture template sequence, it is considered that the preview image and the classic template image are matched successfully, and the photo capture command can be executed.

[0204] Step i: Take a photo and capture a frame based on the similarity judgment result in step h.

[0205] When it is determined that the current preview image and the to-be-matched classic template image have similar postures and expressions, the photo capture process starts, and a total of M frames are captured after the current preview frame.

[0206] For a single-person scene, if there is a face, the captured M frames are sorted according to the expression similarity score, and the frame with the highest expression similarity is used as the benchmark fusion image for multi-frame fusion. If there is no face, the captured M frames are sorted according to the human posture similarity score, and the frame with the highest human posture similarity is used as the benchmark fusion image for multi-frame fusion.

[0207] For multi-person scenes, the captured M frames are sorted by expression similarity scores and posture similarity scores according to the individuals. For the i-th person, if there is a face, the frame with the highest expression similarity score of the i-th person in the M frames is selected as the reference fusion image for the i-th person's regional fusion. If there is no face, the frame with the highest posture similarity score of the i-th person in the M frames is selected as the reference fusion image for the i-th person's regional fusion. Each person in the multi-person scene has a corresponding reference fusion image. When fusion of multiple frames, when different human body regions detected by the target are fused, the reference fusion image corresponding to the human body is selected for regional fusion to ensure that all people have the highest expression similarity and posture similarity, and achieve the purpose of noise reduction and image enhancement.

[0208] In this way, by adopting the shooting method provided by some embodiments of the present application, the representative scenes and wonderful moments on the stage can be automatically frozen without the photographer issuing a shooting command, which reduces the difficulty of stage shooting, increases the success rate of stage shooting, and improves the shooting quality and shooting experience. At the same time, according to the posture template image, key point detection area and shooting object selected by the user, the stage picture expected by the user can be automatically frozen, so that the shooting can meet the user's expectations and expectations as much as possible. And when freezing, focus on the expression and posture of the subject selected by the user, so that every performer that the user cares about in the film has a good expression and beautiful posture as much as possible.

[0209] The above-mentioned method embodiments, or various possible implementation methods in each method embodiment, can be executed separately, or, under the premise that there is no contradiction, can also be executed in combination with each other. The specific implementation can be determined according to actual usage requirements, and the embodiments of the present application do not limit this.

[0210] In some embodiments of the present application, the shooting method provided by the shooting device may be executed by a shooting device. In some embodiments of the present application, the shooting device provided by some embodiments of the present application is described by taking the shooting method executed by the shooting device as an example.

[0211] like Fig.12 As shown, some embodiments of the present application provide a shooting device 200, which may include: an acquisition module 201, which can be used to obtain the actual position coordinates of N object key points of the shooting object in the preview image displayed in the shooting preview interface. The shooting module 202 can be used to shoot at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image. Among them, the part posture similarity of the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than the first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

[0212] In some embodiments of the present application, each of the at least one posture template image corresponds to a shooting number. Exemplarily, the shooting module 202 may be specifically configured to shoot at least one image according to the shooting number corresponding to each posture template image.

[0213] In some embodiments of the present application, the shooting module 202 may be specifically configured to shoot at least one image when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence. The posture template sequence includes at least two posture template images, and the posture template sequence includes at least one of the following: an expression posture template sequence, an action posture template sequence, and an expression-action posture template sequence.

[0214] In some embodiments of the present application, the shooting module 202 can be specifically used to detect the actual position coordinates of the M object key points of the above-mentioned shooting object according to the arrangement order of the posture template images in each posture template sequence; and shoot at least one image when the distance between the actual position coordinates of each object key point in the M object key points and the reference position coordinates of the corresponding reference key points in the M reference key points of the i-th posture template image in the posture template sequence is less than the coordinate distance threshold. Wherein, the position posture similarity of the object part posture composed of the M object key points in each image and the reference part posture composed of the M reference key points of the i-th posture template image is greater than the above-mentioned first similarity threshold; i is a positive integer, i≤the total number of posture template images in each posture template sequence.

[0215] In some embodiments of the present application, the shooting module 202 can be specifically used to detect the actual position coordinates of the M object key points of the above-mentioned shooting object; and shoot at least one image when the distance between the reference position coordinates of each reference key point in the M reference key points of the j-th posture template image in the above-mentioned posture template sequence and the actual position coordinates of the corresponding object key point in the M object key points is less than the coordinate distance threshold. Wherein, the j-th posture template image is any posture template image in the posture template sequence; the object part posture composed of the M object key points in each image and the part posture similarity of the reference part posture composed of the M reference key points of the j-th posture template image is greater than the above-mentioned first similarity threshold; j is a positive integer, j≤the total number of posture template images in each posture template sequence.

[0216] In some embodiments of the present application, the shooting device 200 may also include: a receiving module, which can be used to receive a user's template image selection input for a posture template image set before the shooting module 202 shoots the above-mentioned at least one image; a selection module, which can be used to select a first posture template image from the posture template image set in response to the template image selection input received by the receiving module; the receiving module can also be used to receive a user's area selection input for the first posture template image; a determination module, which can be used to determine the area selected by the area selection input as a key point detection area of ​​the first posture template image in response to the area selection input received by the receiving module; and a detection module, which can be used to perform key point detection on the key point detection area to obtain M reference key points.

[0217] In some embodiments of the present application, when the number of the above-mentioned photographed objects is at least one, the number of the above-mentioned posture template images is one and at least two images are photographed, the photographing device 200 may also include: a determination module, which can be used to determine a reference fusion image from the at least two images for each photographed object after the photographing module 202 photographs the above-mentioned at least one image, and the part posture similarity between the object part posture composed of M object key points in the reference fusion image and the reference part posture composed of M reference key points in the posture template image is greater than a second similarity threshold; a fusion module, which can be used to perform image fusion processing on the at least two images based on the reference fusion image corresponding to each photographed object.

[0218] In some embodiments of the present application, the shooting device 200 may also include: a receiving module, which can be used to receive a user's template image selection input for a posture template image set before the shooting module 202 shoots the above-mentioned at least one image; a processing module, which can be used to select a second posture template image from the posture template image set in response to the template image selection input received by the receiving module, and display at least one reference key point identifier on the second posture template image, wherein each reference key point identifier is used to indicate a reference key point; the receiving module can also be used to receive a key point identifier editing input from the user for the at least one reference key point identifier; the processing module can also be used to perform a key point identifier editing operation in response to the key point identifier editing input received by the receiving module, and the key point identifier editing operation includes at least one of the following: adding at least one reference key point identifier, deleting at least one key point identifier, and adjusting the display position of at least one reference key point identifier.

[0219] In some embodiments of the present application, the above-mentioned M object key points and the above-mentioned M reference key points constitute M pairs of key points, and each pair of key points includes an object key point and a reference key point at a position corresponding to the object key point. Exemplarily, the shooting device 200 may also include: a determination module, which can be used to calculate the Euclidean distance between the object key point and the reference key point in each pair of key points based on the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points before the shooting module 202 shoots the above-mentioned at least one image; and when the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to the distance threshold, determine that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points.

[0220] In the shooting device provided in some embodiments of the present application, since the shooting device can match the key point position coordinates of the object key points of the shooting object in the preview image with the reference key points in the posture template image, and shoot at least one image when the actual position coordinates of M object key points match the reference position coordinates of M reference key points, the shooting device can automatically and accurately capture an image of the user's desired posture that is basically similar to the part composed of the reference key points in the posture template image based on the key point matching operation without the user's shooting input, thereby reducing the difficulty of shooting and increasing the success rate of shooting, without the need to continuously shoot a large number of images through the electronic device, which can reduce the power consumption of the electronic device and extend the use time of the electronic device.

[0221] The shooting device in some embodiments of the present application may be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than a terminal. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc. It may also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiments of the present application.

[0222] The shooting device in some embodiments of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0223] The shooting devices provided in some embodiments of the present application can implement the various processes implemented in the above-mentioned method embodiments and achieve the same technical effects. To avoid repetition, they will not be described here.

[0224] like Fig.13As shown, some embodiments of the present application further provide an electronic device 100, including a processor 101 and a memory 102, wherein the memory 102 stores programs or instructions that can be executed on the processor 101, and when the program or instructions are executed by the processor 101, the various steps of the above-mentioned shooting method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0225] It should be noted that the electronic devices in some embodiments of the present application include mobile electronic devices and non-mobile electronic devices.

[0226] Fig.14 A schematic diagram of the hardware structure of an electronic device for implementing some embodiments of the present application.

[0227] like Fig.14 As shown, the electronic device 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010 and other components.

[0228] Those skilled in the art will appreciate that the electronic device 1000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1010 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Fig.14 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0229] The processor 1010 may be used to obtain the actual position coordinates of N object key points of the photographed object in the preview image displayed in the shooting preview interface; and to shoot at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image. The similarity between the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than a first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

[0230] In some embodiments of the present application, each of the at least one posture template image corresponds to a shooting number. Exemplarily, the processor 1010 may be specifically configured to shoot at least one image according to the shooting number corresponding to each posture template image.

[0231] In some embodiments of the present application, the processor 1010 may be specifically configured to capture at least one image when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence. The posture template sequence includes at least two posture template images, and the posture template sequence includes at least one of the following: an expression posture template sequence, an action posture template sequence, and an expression-action posture template sequence.

[0232] In some embodiments of the present application, the processor 1010 can be specifically used to detect the actual position coordinates of the M object key points of the above-mentioned photographed object according to the arrangement order of the posture template images in each posture template sequence; and take at least one image when the distance between the actual position coordinates of each object key point in the M object key points and the reference position coordinates of the corresponding reference key point in the M reference key points of the i-th posture template image in the posture template sequence is less than the coordinate distance threshold. Wherein, the position posture similarity of the object part posture composed of the M object key points in each image and the reference part posture composed of the M reference key points of the i-th posture template image is greater than the above-mentioned first similarity threshold; i is a positive integer, i≤the total number of posture template images in each posture template sequence.

[0233] In some embodiments of the present application, the processor 1010 can be specifically used to detect the actual position coordinates of the M object key points of the photographed object; and take at least one image when the distance between the reference position coordinates of each reference key point in the M reference key points of the j-th posture template image in the above-mentioned posture template sequence and the actual position coordinates of the corresponding object key point in the M object key points is less than the coordinate distance threshold. Wherein, the j-th posture template image is any posture template image in the posture template sequence; the position posture similarity of the object part posture composed of the M object key points in each image and the reference part posture composed of the M reference key points of the j-th posture template image is greater than the above-mentioned first similarity threshold; j is a positive integer, j≤the total number of posture template images in each posture template sequence.

[0234] In some embodiments of the present application, the user input unit 1007 can be used to receive a user's template image selection input for a set of posture template images before the processor 1010 captures the above-mentioned at least one image; the processor 1010 can also be used to select a first posture template image from the set of posture template images in response to the template image selection input received by the user input unit 1007; the user input unit 1007 can also be used to receive a user's area selection input for the first posture template image; the processor 1010 can also be used to determine the area selected by the area selection input as a key point detection area of ​​the first posture template image in response to the area selection input received by the user input unit 1007; and perform key point detection on the key point detection area to obtain M reference key points.

[0235] In some embodiments of the present application, when the number of the above-mentioned photographed objects is at least one, the number of the above-mentioned posture template images is one and at least two images are photographed, the processor 1010 can also be used to determine a baseline fusion image from the at least two images for each photographed object after taking the above-mentioned at least one image, and the similarity between the object part posture composed of M object key points in the baseline fusion image and the reference part posture composed of M reference key points in the posture template image is greater than a second similarity threshold; the fusion module can be used to perform image fusion processing on the at least two images based on the baseline fusion image corresponding to each photographed object.

[0236] In some embodiments of the present application, the user input unit 1007 may also be used to receive a user's template image selection input for a set of posture template images before the processor 1010 captures the above-mentioned at least one image; the processor 1010 may also be used to select a second posture template image from the set of posture template images in response to the template image selection input received by the user input unit 1007, and display at least one reference key point identifier on the second posture template image, wherein each reference key point identifier is used to indicate a reference key point; the user input unit 1007 may also be used to receive a user's key point identifier editing input for the at least one reference key point identifier; the processor 1010 may also be used to perform a key point identifier editing operation in response to the key point identifier editing input received by the user input unit 1007, wherein the key point identifier editing operation includes at least one of the following: adding at least one reference key point identifier, deleting at least one key point identifier, and adjusting the display position of at least one reference key point identifier.

[0237] In some embodiments of the present application, the above-mentioned M object key points and the above-mentioned M reference key points constitute M pairs of key points, and each pair of key points includes an object key point and a reference key point at a position corresponding to the object key point. The processor 1010 can also be used to calculate the Euclidean distance between the object key point and the reference key point in each pair of key points based on the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points before taking the above-mentioned at least one image; and when the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to the distance threshold, determine that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points.

[0238] In the electronic device provided in some embodiments of the present application, since the electronic device can match the key point position coordinates of the object key points of the photographed object in the preview image with the reference key points in the posture template image, and capture at least one image when the actual position coordinates of M object key points match the reference position coordinates of M reference key points, an image of the user's desired posture that is basically similar to the part composed of the reference key points in the posture template image can be automatically and accurately captured based on the key point matching operation, without the need for user input, thereby reducing the difficulty of shooting and increasing the success rate of shooting, without the need to continuously capture a large number of images through the electronic device, which can reduce the power consumption of the electronic device and extend the use time of the electronic device.

[0239] It should be understood that in some embodiments of the present application, the input unit 1004 may include a graphics processor (GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0240] The memory 1009 can be used to store software programs and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1009 in some embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0241] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.

[0242] Some embodiments of the present application also provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned shooting method embodiment is implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0243] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0244] Some embodiments of the present application further provide a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned shooting method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0245] It should be understood that the chip mentioned in some embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0246] Some embodiments of the present application provide a computer program / program product, which is stored in a storage medium. The program / program product is executed by at least one processor to implement the various processes of the above-mentioned shooting method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0247] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0248] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0249] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A shooting method, characterized in that: The method comprises: Obtaining actual position coordinates of N object key points of the photographed object in the preview image displayed on the shooting preview interface; When actual position coordinates of M object key points among the N object key points match reference position coordinates of M reference key points of at least one posture template image, capturing at least one image; Among them, the part posture similarity between the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than a first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

2. The method according to claim 1, characterized in that Each posture template image in the at least one posture template image corresponds to a number of shots; The capturing of at least one image comprises: At least one image is taken according to the number of shots corresponding to each posture template image.

3. The method according to claim 1, characterized in that The method of capturing at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image comprises: When the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence, capturing at least one image; The posture template sequence includes at least two posture template images, and the posture template sequence includes at least one of the following: an expression posture template sequence, an action posture template sequence, and an expression-action posture template sequence.

4. The method according to claim 3, characterized in that The capturing of at least one image when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence comprises: Detecting the actual position coordinates of M object key points of the photographed object according to the arrangement order of the posture template images in each posture template sequence; When the distance between the actual position coordinate of each object key point in the M object key points and the reference position coordinate of the corresponding reference key point in the M reference key points of the i-th posture template image in the posture template sequence is less than the coordinate distance threshold, taking at least one image; Among them, the object part posture composed of M object key points in each image and the reference part posture composed of M reference key points in the i-th posture template image have a posture similarity greater than the first similarity threshold; i is a positive integer, i≤the total number of posture template images in each posture template sequence.

5. The method according to claim 3, characterized in that: The capturing of at least one image when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence comprises: Detecting the actual position coordinates of M object key points of the photographed object; When the distance between the reference position coordinate of each reference key point among the M reference key points of the j-th posture template image in the posture template sequence and the actual position coordinate of the corresponding object key point among the M object key points is less than a coordinate distance threshold, capturing at least one image; Among them, the j-th posture template image is any posture template image in the posture template sequence; the object part posture composed of M object key points in each image and the reference part posture composed of M reference key points of the j-th posture template image have a similarity greater than the first similarity threshold; j is a positive integer, j≤the total number of posture template images in each posture template sequence.

6. The method according to claim 1, characterized in that Before capturing at least one image, the method further includes: receiving a template image selection input from a user for a set of posture template images; In response to the template image selection input, selecting a first pose template image from the pose template image set; receiving a user's input of region selection for the first posture template image; In response to the region selection input, determining the region selected by the region selection input as a key point detection region of the first posture template image; Key point detection is performed on the key point detection area to obtain M reference key points.

7. The method according to claim 1, characterized in that In the case where the number of the photographed objects is at least one, the number of the posture template images is one, and at least two images are photographed, after photographing at least one image, the method further includes: For each photographed object, determining a reference fusion image from the at least two images, wherein a part posture similarity between an object part posture composed of M object key points in the reference fusion image and a reference part posture composed of M reference key points in the posture template image is greater than a second similarity threshold; Based on the reference fusion image corresponding to each photographed object, image fusion processing is performed on the at least two images.

8. The method according to claim 1, characterized in that Before capturing at least one image, the method further includes: receiving a template image selection input from a user for a set of posture template images; In response to the template image selection input, a second pose template image is selected from the pose template image set, and at least one reference key point identifier is displayed on the second pose template image, wherein each reference key point identifier is used to indicate a reference key point; receiving a key point mark editing input of the at least one reference key point mark by a user; In response to the key point marker editing input, a key point marker editing operation is performed, and the key point marker editing operation includes at least one of the following: adding at least one reference key point marker, deleting at least one key point marker, and adjusting the display position of at least one reference key point marker.

9. The method according to claim 1, characterized in that: The M object key points and the M reference key points form M pairs of key points, each pair of key points includes an object key point and a reference key point at a position corresponding to the object key point; Before capturing at least one image, the method further includes: Based on the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points, calculating the Euclidean distance between the object key point and the reference key point in each pair of key points; When the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to the distance threshold, it is determined that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points.

10. A photographing device, characterized in that: include: An acquisition module, used to acquire actual position coordinates of N object key points of the photographed object in the preview image displayed on the shooting preview interface; a shooting module, configured to shoot at least one image when the actual position coordinates of M object key points among the N object key points match the reference position coordinates of M reference key points of at least one posture template image; Among them, the part posture similarity between the object part posture composed of the M object key points and the reference part posture composed of the M reference key points is greater than a first similarity threshold; N is an integer greater than 1, M is a positive integer, and M≤N.

11. The device according to claim 10, characterized in that Each posture template image in the at least one posture template image corresponds to a number of shots; The shooting module is specifically used to shoot at least one image according to the number of shots corresponding to each posture template image.

12. The device according to claim 10, characterized in that The shooting module is specifically used to shoot at least one image when the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points of the posture template image in at least one posture template sequence; The posture template sequence includes at least two posture template images, and the posture template sequence includes at least one of the following: an expression posture template sequence, an action posture template sequence, and an expression-action posture template sequence.

13. The device according to claim 12, characterized in that The shooting module is specifically used to detect the actual position coordinates of M object key points of the shooting object according to the arrangement order of the posture template images in each posture template sequence; and shoot at least one image when the distance between the actual position coordinates of each object key point in the M object key points and the reference position coordinates of the corresponding reference key point in the M reference key points of the i-th posture template image in the posture template sequence is less than the coordinate distance threshold; Among them, the object part posture composed of M object key points in each image and the reference part posture composed of M reference key points in the i-th posture template image have a posture similarity greater than the first similarity threshold; i is a positive integer, i≤the total number of posture template images in each posture template sequence.

14. The device according to claim 12, characterized in that The shooting module is specifically used to detect the actual position coordinates of the M object key points of the shooting object; and shoot at least one image when the distance between the reference position coordinates of each reference key point in the M reference key points of the j-th posture template image in the posture template sequence and the actual position coordinates of the corresponding object key point in the M object key points is less than the coordinate distance threshold; Among them, the j-th posture template image is any posture template image in the posture template sequence; the object part posture composed of M object key points in each image and the reference part posture composed of M reference key points of the j-th posture template image have a similarity greater than the first similarity threshold; j is a positive integer, j≤the total number of posture template images in each posture template sequence.

15. The device according to claim 10, characterized in that The device also includes: A receiving module, configured to receive a template image selection input of a gesture template image set from a user before the shooting module shoots the at least one image; A selection module, configured to select a first posture template image from the posture template image set in response to the template image selection input received by the receiving module; The receiving module is further used to receive a user's input of a region selection of the first posture template image; a determination module, configured to determine, in response to the region selection input received by the receiving module, the region selected by the region selection input as a key point detection region of the first posture template image; The detection module is used to perform key point detection on the key point detection area to obtain M reference key points.

16. The device according to claim 10, characterized in that In the case where the number of the photographed objects is at least one, the number of the posture template images is one, and at least two images are photographed, the device further includes: a determination module, configured to determine, for each photographed object, a reference fusion image from the at least two images after the photographing module photographs the at least one image, wherein a part posture similarity between an object part posture composed of M object key points in the reference fusion image and a reference part posture composed of M reference key points in the posture template image is greater than a second similarity threshold; The fusion module is used to perform image fusion processing on the at least two images based on the reference fusion image corresponding to each photographed object.

17. The device according to claim 10, characterized in that The device also includes: A receiving module, configured to receive a template image selection input of a gesture template image set from a user before the shooting module shoots the at least one image; a processing module, configured to select a second posture template image from the posture template image set in response to the template image selection input received by the receiving module, and display at least one reference key point identifier on the second posture template image, wherein each reference key point identifier is used to indicate a reference key point; The receiving module is further used to receive a key point mark editing input of the at least one reference key point mark by a user; The processing module is also used to perform a key point marker editing operation in response to the key point marker editing input received by the receiving module, and the key point marker editing operation includes at least one of the following: adding at least one reference key point marker, deleting at least one key point marker, and adjusting the display position of at least one reference key point marker.

18. The device according to claim 10, characterized in that The M object key points and the M reference key points form M pairs of key points, each pair of key points includes an object key point and a reference key point at a position corresponding to the object key point; The device also includes: A determination module is used to calculate the Euclidean distance between the object key point and the reference key point in each pair of key points based on the actual position coordinates of the M object key points and the reference position coordinates of the M reference key points before the shooting module shoots the at least one image; and determine that the actual position coordinates of the M object key points match the reference position coordinates of the M reference key points when the Euclidean distance between the object key point and the reference key point of each pair of key points is less than or equal to a distance threshold.

19. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the shooting method according to any one of claims 1 to 9 are implemented.

20. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the shooting method according to any one of claims 1 to 9 are implemented.

Images