CN111462337A - An image processing method, device and computer-readable storage medium - Google Patents

Abstract

The invention discloses an image processing method, a device and a computer-readable storage medium, which relate to the technical field of communications, so as to improve the display effect of an AR group photo image of a real user and a virtual object. The method includes: acquiring a projected image of a user on a display screen; extracting a human body outline in the projected image; acquiring a virtual image of a virtual object according to the human body outline, wherein the outline of the virtual object and the human body outline The matching degree of the image satisfies the first preset requirement; the relative positional relationship between the virtual image and the projected image is determined; and an AR image is obtained according to the projected image, the virtual image and the relative positional relationship. The embodiment of the present invention can improve the display effect of the AR group photo image of the real user and the virtual object.

Description

An image processing method, device and computer-readable storage medium

technical field

The present invention relates to the technical field of image processing, and in particular, to an image processing method, device and computer-readable storage medium.

Background technique

In AR (Augmented Reality, Augmented Reality) photography, the height and movement of virtual objects (such as virtual characters) are fixed. However, in the process of taking a photo of the user and the avatar, different users have different heights and photographing poses. Therefore, in this case, it is a technical problem that needs to be solved how to improve the sense of reality of the real user and the virtual character being photographed together so as to improve the display effect of the AR image.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide an image processing method, a device, and a computer-readable storage medium, so as to improve the display effect of an AR group photo image of a real user and a virtual object.

In a first aspect, an embodiment of the present invention provides an image processing method, including:

Obtain the projected image of the user on the display screen;

extracting the outline of the human body in the projected image;

obtaining a virtual image of a virtual object according to the human body outline, wherein the matching degree between the outline of the virtual object and the human body outline meets a first preset requirement;

determining the relative positional relationship between the virtual image and the projected image;

An AR image is obtained according to the projected image, the virtual image, and the relative positional relationship.

Wherein, the extracting the human body contour in the projection image includes:

Perform image conversion on the projected images respectively to obtain at least one grayscale image;

Calculate the average value of the grayscale image to obtain a background grayscale image;

The difference between each of the grayscale images and the background grayscale image is calculated to obtain the user's body contour.

Wherein, the virtual object includes a virtual character; and the acquiring a virtual image of the virtual object according to the human body outline includes:

determining a first key point on the outline of the human body, wherein the first key point includes at least a head key point and a hand key point;

determining a target contour of the virtual object in candidate images of the virtual object;

Corresponding to the first key point, a second key point is determined on the target contour, wherein the second key point includes at least a head key point and a hand key point;

Based on the first key point and the second key point, calculating the similarity between the human body contour and the target contour;

If the similarity meets the second preset requirement, the candidate image is used as the virtual image.

Wherein, calculating the similarity between the human body contour and the target contour based on the first key point and the second key point includes:

For each first target key point in the first key points, calculate the Euclidean distance between the first target key point and the second target key point, and the second target key point is the second key point The key points corresponding to the first target key points in ;

Based on the obtained Euclidean distance, the similarity between the human body contour and the target contour is calculated.

Wherein, calculating the similarity between the human body contour and the target contour based on the obtained Euclidean distance includes:

Multiply each Euclidean distance by the corresponding weight to obtain the first value corresponding to each Euclidean distance;

Each first numerical value is added to obtain the similarity between the human body contour and the target contour;

Wherein, the method also includes:

The weight is preset, wherein the weight of the Euclidean distance obtained based on the head key point and/or the hand key point is greater than the weight of the Euclidean distance obtained based on other key points.

Wherein, the determining the relative positional relationship between the virtual image and the projected image includes:

determining the distance between the actual photographing position of the user and the projected image;

A depth distance between the virtual image and the projected image is determined based on the distance.

Wherein, determining the depth distance between the virtual image and the projected image according to the distance includes:

The depth distance between the virtual image and the projected image is determined from the distance using the following formula:

Among them, Δd represents the depth distance, the Δθ represents the binocular parallax of the user, D represents the distance between the user's actual photographing position and the user's projected image on the display screen, and P represents the distance between the user's eyes , Δθ, P are constants

In a second aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a program stored on the memory and running on the processor; the processor is configured to read the memory The program in implements the steps in the image processing method described in the first aspect.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, the steps in the image processing method described in the first aspect are .

In the embodiment of the present invention, the outline of the human body is extracted according to the projected image of the user on the display screen, and the virtual image of the virtual object is obtained according to the outline of the human body. After that, an AR group photo is taken according to the relative positional relationship between the virtual object and the projected image, the projected image and the virtual image. Since the matching degree between the outline of the virtual object and the outline of the human body meets the first preset requirement, and the relative positional relationship between the virtual object and the projected image is considered when taking a group photo, the AR group photo obtained by using the embodiment of the present invention makes the shape of the virtual object , posture and the user's shape and posture are highly matched, thereby enhancing the realism of the image and improving the display effect of the AR image.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative labor.

1 is a flowchart of an image processing method provided by an embodiment of the present invention;

Figure 2 is a schematic diagram of human binocular imaging;

3 is a mathematical schematic diagram of the principle of binocular imaging;

4 is one of the schematic diagrams of taking pictures provided by an embodiment of the present invention;

FIG. 5 is the second schematic diagram of photographing provided by an embodiment of the present invention;

6 is a structural diagram of an image processing apparatus provided by an embodiment of the present invention;

FIG. 7 is a structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Referring to FIG. 1, FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present invention, as shown in FIG. 1, including the following steps:

Step 101: Acquire a projected image of the user on the display screen.

When a user needs to take a picture, a camera is usually used to take a picture, so that the user's image is displayed on the display screen. In this embodiment of the present invention, the displayed image of the user is referred to as a projected image. In this embodiment of the present invention, the projected image needs to include the user's body contour. Preferably, since an AR photo is taken with a virtual object (eg, virtual character, virtual item, etc.), the projected image needs to include the user's complete body contour. The user's body contour can reflect the user's height, standing posture and other information.

Step 102 , extract the outline of the human body in the projection image.

In the embodiment of the present invention, a plurality of projection images of the user are continuously acquired, and then the outline of the human body is determined based on these projection images. Specifically, in this step, image conversion is performed on the obtained multiple projection images to obtain at least one grayscale image. Among them, each projected image has a corresponding grayscale image. Afterwards, the average value of the grayscale images is calculated to obtain a background grayscale image. Finally, the difference between each of the grayscale images and the background grayscale image is calculated to obtain the user's body contour. In this way, the obtained body contour information can be made more accurate.

Taking five images of users continuously taken as an example, the five images are converted into grayscale images and denoted as f _gi (x, y), i=1, 2, 3, 4, 5. Add the grayscale images of the five images according to the following formula (1) and obtain the average value, which is the grayscale image of the background image, denoted as f _b (x, y).

After that, the difference between each grayscale image and the grayscale image of the background image can be obtained to obtain the human body contour information, wherein the human body contour information can be expressed as formula (2):

f _d (x,y)=|f _gi (x, y)-f _b (x, y)| (2)

Among them, f _d (x, y) represents the human body contour information.

Step 103: Acquire a virtual image of a virtual object according to the outline of the human body, wherein the matching degree between the outline of the virtual object and the outline of the human body meets a first preset requirement.

The first preset requirement may be that the matching degree is greater than a preset value, and the preset value may be set according to actual needs.

Taking the virtual object as an avatar as an example, all images of the avatar in the avatar library can be searched, and the current human body contour information can be calculated to match the posture of the avatar most similar to the human body contour. In the matching process, the user's height and hand posture are mainly considered. In the process of using Euclidean distance to calculate the similarity of human body contours, the weight of head pose and hand pose is appropriately increased, so as to focus on the similarity of head and hand. By matching all images, find the image of the avatar that most closely resembles the client's height and pose.

Specifically, in this step, the virtual image of the virtual object can be obtained according to the following process:

Step 1031: Determine a first key point on the human body outline, where the first key point at least includes a head key point and a hand key point.

Here, the first key point can be determined on the contour of the human body by marking. Of course, the first key point may also include other key points on the outline of the human body.

Step 1032: Determine the target contour of the virtual object in the candidate image of the virtual object.

In practical applications, multiple images of multiple virtual objects may be pre-stored, and different virtual objects have different heights, postures, and the like. Here, these images are referred to as candidate images of virtual objects. If the user selects a virtual object to be photographed, candidates of the virtual object selected by the user may be obtained from the pre-stored image directly according to the virtual object selected by the user.

Taking the virtual object as a virtual character as an example, the target contour determined here is the human body contour of the virtual character. The manner of determining the human body contour of the virtual object is not limited in this embodiment of the present invention.

Step 1033: Corresponding to the first key point, determine a second key point on the target contour, where the second key point at least includes a head key point and a hand key point.

"Corresponding to the first key point" means that, according to the position of the first key point in the human body contour, a key point, that is, a second key point, is determined at the corresponding position of the human body contour of the virtual character. In this way, the obtained height, posture, etc. of the virtual object can be made closer to the height and posture of the user. Optionally, the second key point may also include key points of other parts.

Step 1034: Calculate the similarity between the human body contour and the target contour based on the first key point and the second key point.

In this step, the Euclidean distance between each key point is mainly calculated, and then the similarity between the human body contour and the target contour is calculated according to the Euclidean distance.

When calculating the Euclidean distance, the calculation is based on the two key points corresponding to the contour of the human body and the contour of the target. Specifically, for each of the first target key points in the first key points, the Euclidean distance between the first target key point and the second target key point is calculated, and the second target key point is the first target key point. A key point corresponding to the first target key point among the two key points. The first target key point is any one of the first key points. Then, based on the obtained Euclidean distance, the similarity between the human body contour and the target contour is calculated.

For the obtained multiple Euclidean distances, multiply each Euclidean distance by the corresponding weight to obtain the first value corresponding to each Euclidean distance, and then add the first values to obtain the human body contour and the target contour similarity between.

In the process of the embodiment of the present invention, the weights may also be preset, wherein the weights of the Euclidean distance obtained based on the head key points and/or the hand key points are greater than the weights of the Euclidean distances obtained based on other key points. weight.

In the embodiment of the present invention, by increasing the weights corresponding to the head key points or the hand key points, the height and posture of the obtained virtual object can be made closer to the height and posture of the user, thereby further improving the display of the image. Effect.

Step 1035: If the similarity meets the second preset requirement, use the candidate image as the virtual image.

Wherein, the similarity meeting the second preset requirement may be that the similarity is greater than a preset value, and the preset value can be set according to actual needs.

Step 104: Determine the relative positional relationship between the virtual image and the projected image.

In this embodiment of the present invention, the relative positional relationship may be represented by a depth distance between the virtual image and the projected image.

Specifically, in this step, the distance between the actual photographing position of the user and the projected image is determined, and then the depth distance between the virtual image and the projected image is determined according to the distance.

As shown in Figure 2, it is a schematic diagram of human binocular imaging. Since there is a distance of about 60mm between human eyes, when the left and right eyes view objects at their respective angles, the images presented on the retina are different. The brain judges the spatial position of objects according to this difference, so that people can produce stereoscopic vision of objects.

As shown in FIG. 3 , it is a mathematical schematic diagram of the principle of binocular imaging. Referring to Fig. 3, the geometric relationship between binocular disparity and the spatial position of the object is shown in formula (3):

Among them, P is the distance between the eyes of a person, D is the viewing distance, and Δd is the relative depth of the object. Through the above formula, the functional relationship between the parallax of the two eyes and the relative depth (depth distance) of the object can be obtained.

As shown in FIG. 4 , when the user takes a picture, after the standing position, that is, the actual photographing position is determined, the distance D between the actual photographing position of the user and the projected image can be determined. Then, the position of the virtual image is dynamically adjusted according to the projected image of the user on the display screen to better present the stereoscopic view.

Specifically, the depth distance between the virtual image and the projected image is determined according to the following formula (4):

Among them, Δd represents the depth distance, the Δθ represents the binocular parallax of the user, D represents the distance between the user's actual photographing position and the user's projected image on the display screen, and P represents the distance between the user's eyes , Δθ and P are constants.

Wherein, when determining the D value, the distance between a certain point of the human body and the point corresponding to the point in the projected image may be used as the D value. Δd may be the distance between a certain point in the projected image and a certain point in the virtual image, for example, a point on the user's toe and a point on the virtual character's toe in the projected image, and the like.

In the final composite photo of AR co-shooting, the most obvious influence on the composite effect is the relative depth distance between the user's projection and the virtual star. Based on formula (4), the depth distance is dynamically adjusted to achieve the optimal photo effect.

For example, in order to ensure the best visual effect when the user and the avatar perform AR co-shot, it is necessary to adjust the appearance position of the avatar in real time according to the actual position of the user standing, that is, determine Δd according to the value of D. As shown in Fig. 5, in different times of taking pictures, based on the distance D obtained in the user's real scene, the appearance position of the virtual character is adjusted in real time according to formula 4, that is, Δd is determined, so as to ensure that the projected image of the virtual character and the user are relatively relative to each other. The position is indicated by line 51, that is, the best viewing distance effect is achieved.

Step 105: Obtain an AR image according to the projected image, the virtual image, and the relative positional relationship.

After the position of the virtual image is determined, the projected image and the virtual image can be synthesized to obtain an AR image. Wherein, the specific synthesis method is not limited in the embodiments of the present invention.

In the embodiment of the present invention, the outline of the human body is extracted according to the projected image of the user on the display screen, and the virtual image of the virtual object is obtained according to the outline of the human body. After that, an AR group photo is taken according to the relative positional relationship between the virtual object and the projected image, the projected image and the virtual image. Since the matching degree between the outline of the virtual object and the outline of the human body meets the first preset requirement, and the relative positional relationship between the virtual object and the projected image is considered when taking a group photo, the AR group photo obtained by using the embodiment of the present invention makes the shape of the virtual object , posture and the user's shape and posture are highly matched, thereby enhancing the realism of the image and improving the display effect of the AR image.

The embodiment of the present invention also provides an image processing apparatus. Referring to FIG. 6, FIG. 6 is a structural diagram of an image processing apparatus provided by an embodiment of the present invention. Since the principle of the image processing apparatus for solving the problem is similar to the image processing method in the embodiment of the present invention, the implementation of the image processing apparatus may refer to the implementation of the method, and the repetition will not be repeated.

As shown in FIG. 6 , the image processing apparatus 600 includes:

The first acquisition module 601 is used to acquire the projected image of the user on the display screen; the first extraction module 602 is used to extract the outline of the human body in the projected image; the second acquisition module 603 is used to, according to the outline of the human body, Acquiring a virtual image of a virtual object, wherein the matching degree between the outline of the virtual object and the outline of the human body meets a first preset requirement; a first determination module 604 is configured to determine the difference between the virtual image and the projected image The fourth obtaining module 605 is configured to obtain an AR image according to the projected image, the virtual image and the relative positional relationship.

Optionally, the first extraction module 602 may include:

a conversion sub-module for performing image conversion on the projected images respectively to obtain at least one grayscale image; a first calculation submodule for calculating the average value of the grayscale images to obtain a background grayscale image; the second The calculation sub-module is configured to calculate the difference between each of the grayscale images and the background grayscale images to obtain the user's body contour.

Optionally, the virtual object includes a virtual character; the second obtaining module 603 includes:

The first determination sub-module is used to determine the first key point on the outline of the human body, wherein the first key point includes at least the head key point and the hand key point; the second determination sub-module is used for the The target contour of the virtual object is determined in the candidate image of the virtual object; the third determination sub-module is used to determine the second key point on the target contour corresponding to the first key point, wherein the first key point is The two key points include at least head key points and hand key points; a first calculation sub-module is used to calculate the distance between the human body contour and the target contour based on the first key point and the second key point the similarity; the fourth determination sub-module is configured to use the candidate image as the virtual image if the similarity meets the second preset requirement.

Optionally, the first calculation submodule includes:

a first calculation unit, configured to calculate the Euclidean distance between the first target key point and the second target key point for each first target key point in the first key point, the second target key point is the key point corresponding to the first target key point in the second key point; the second calculation unit is configured to calculate the similarity between the human body contour and the target contour based on the obtained Euclidean distance.

Optionally, the second computing unit includes:

The first calculation subunit is used to multiply each Euclidean distance by the corresponding weight to obtain the first value corresponding to each Euclidean distance; the second calculation subunit is used to add each first value to obtain the human body similarity between the contour and the target contour.

Optionally, the second computing unit may further include: a setting sub-module, configured to preset the weight, wherein the weight of the Euclidean distance obtained based on the head key point and/or the hand key point is greater than the weight based on the head key point and/or the hand key point. The weight of the Euclidean distance obtained by other key points.

Optionally, the first determining module 604 includes:

The first determination submodule is used to determine the distance between the actual photographing position of the user and the projected image; the second determination submodule is used to determine the distance between the virtual image and the projected image according to the distance depth distance.

Optionally, the second determination sub-module is configured to, using the following formula, determine the depth distance between the virtual image and the projected image according to the distance:

Among them, Δd represents the depth distance, the Δθ represents the binocular parallax of the user, D represents the distance between the user's actual photographing position and the user's projected image on the display screen, and P represents the distance between the user's eyes , Δθ and P are constants.

The apparatus provided in the embodiment of the present invention can execute the foregoing method embodiments, and the implementation principles and technical effects thereof are similar, and details are not described herein again in this embodiment.

As shown in FIG. 7 , an electronic device according to an embodiment of the present invention includes: a processor 700 configured to read a program in a memory 710 and execute the following processes:

Obtain the projected image of the user on the display screen;

extracting the outline of the human body in the projected image;

obtaining a virtual image of a virtual object according to the human body outline, wherein the matching degree between the outline of the virtual object and the human body outline meets a first preset requirement;

determining the relative positional relationship between the virtual image and the projected image;

An augmented reality AR image is obtained according to the projected image, the virtual image, and the relative positional relationship.

7, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 700 and various circuits of memory represented by memory 710 are linked together. The bus architecture may also link together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and, therefore, will not be described further herein. The bus interface provides the interface. The processor 700 is responsible for managing the bus architecture and general processing, and the memory 710 may store data used by the processor 700 in performing operations.

The processor 700 is responsible for managing the bus architecture and general processing, and the memory 710 may store data used by the processor 700 in performing operations.

The processor 700 is further configured to read the program, and perform the following steps:

Perform image conversion on the projected images respectively to obtain at least one grayscale image;

Calculate the average value of the grayscale image to obtain a background grayscale image;

The difference between each of the grayscale images and the background grayscale image is calculated to obtain the user's body contour.

The virtual object includes a virtual character; the processor 700 is further configured to read the program, and perform the following steps:

determining a first key point on the outline of the human body, wherein the first key point includes at least a head key point and a hand key point;

determining a target contour of the virtual object in candidate images of the virtual object;

Corresponding to the first key point, a second key point is determined on the target contour, wherein the second key point includes at least a head key point and a hand key point;

Based on the first key point and the second key point, calculating the similarity between the human body contour and the target contour;

If the similarity meets the second preset requirement, the candidate image is used as the virtual image.

The processor 700 is further configured to read the program, and perform the following steps:

For each first target key point in the first key points, calculate the Euclidean distance between the first target key point and the second target key point, and the second target key point is the second key point The key points corresponding to the first target key points in ;

Based on the obtained Euclidean distance, the similarity between the human body contour and the target contour is calculated.

The processor 700 is further configured to read the program, and perform the following steps:

Multiply each Euclidean distance by the corresponding weight to obtain the first value corresponding to each Euclidean distance;

The respective first values are added to obtain the similarity between the human body contour and the target contour.

The processor 700 is further configured to read the program, and perform the following steps:

The weight is preset, wherein the weight of the Euclidean distance obtained based on the head key point and/or the hand key point is greater than the weight of the Euclidean distance obtained based on other key points.

The processor 700 is further configured to read the program, and perform the following steps:

determining the distance between the actual photographing position of the user and the projected image;

A depth distance between the virtual image and the projected image is determined based on the distance.

The processor 700 is further configured to read the program, and perform the following steps:

The depth distance between the virtual image and the projected image is determined from the distance using the following formula:

Among them, Δd represents the depth distance, the Δθ represents the binocular parallax of the user, D represents the distance between the user's actual photographing position and the user's projected image on the display screen, and P represents the distance between the user's eyes , Δθ and P are constants.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above image processing method embodiments can be implemented, and the same technology can be achieved. The effect, in order to avoid repetition, is not repeated here. The computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk, or an optical disk.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. According to this understanding, the technical solutions of the present invention essentially or the parts that contribute to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of the present invention, without departing from the spirit of the present invention and the scope protected by the claims, many forms can be made, which all belong to the protection of the present invention.

Claims (10)

1. An image processing method, comprising:

acquiring a projection image of a user on a display screen;

extracting a human body contour in the projection image;

acquiring a virtual image of a virtual object according to the human body contour, wherein the matching degree of the contour of the virtual object and the human body contour meets a first preset requirement;

determining a relative positional relationship between the virtual image and the projection image;

and obtaining an augmented reality AR image according to the projection image, the virtual image and the relative position relation.

2. The method of claim 1, wherein the projection image is at least one; the extracting the human body contour in the projection image comprises:

respectively carrying out image conversion on the projected images to obtain at least one gray image;

calculating the average value of the gray level images to obtain a background gray level image;

and calculating the difference between each gray level image and the background gray level image to obtain the human body contour of the user.

3. The method of claim 1, wherein the virtual object comprises a virtual character; the acquiring of the virtual image of the virtual object according to the human body contour includes:

determining first key points on the human body contour, wherein the first key points at least comprise head key points and hand key points;

determining a target contour of the virtual object in a candidate image of the virtual object;

determining second key points on the target contour corresponding to the first key points, wherein the second key points at least comprise head key points and hand key points;

calculating the similarity between the human body contour and the target contour based on the first key point and the second key point;

and if the similarity meets a second preset requirement, taking the candidate image as the virtual image.

4. The method of claim 3, wherein said calculating a similarity between the human body contour and the target contour based on the first keypoint and the second keypoint comprises:

calculating Euclidean distances between first target key points and second target key points for each first target key point in the first key points, wherein the second target key points are key points corresponding to the first target key points in the second key points;

and calculating the similarity between the human body contour and the target contour based on the obtained Euclidean distance.

5. The method according to claim 4, wherein the calculating the similarity between the human body contour and the target contour based on the obtained Euclidean distance comprises:

multiplying each Euclidean distance by the corresponding weight value respectively to obtain a first numerical value corresponding to each Euclidean distance;

and adding the first numerical values to obtain the similarity between the human body contour and the target contour.

6. The method of claim 5, further comprising:

and presetting the weight, wherein the weight of the Euclidean distance obtained based on the head key point and/or the hand key point is larger than the weight of the Euclidean distance obtained based on other key points.

7. The method of claim 1, wherein said determining a relative positional relationship between said virtual image and said projected image comprises:

determining a distance between an actual photographing position of the user and the projected image;

determining a depth distance between the virtual image and the projected image according to the distance.

8. The method of claim 7, wherein said determining a depth distance between said virtual image and said projected image based on said distance comprises:

determining a depth distance between the virtual image and the projected image from the distance using the following formula:

wherein Δ D represents the depth distance, Δ θ represents the binocular parallax of the user, D represents the distance between the actual photographing position of the user and the projection image of the user on the display screen, P represents the distance between the eyes of the user, and Δ θ, P are constants.

9. An electronic device, comprising: a memory, a processor, and a program stored on the memory and executable on the processor; characterized in that the processor, for reading the program in the memory, implements the steps in the image processing method according to any one of claims 1 to 8.

10. A computer-readable storage medium for storing a computer program, characterized in that the computer program, when being executed by a processor, is adapted to carry out the steps of the image processing method according to any one of claims 1 to 8.

Images