CN118135118B

CN118135118B - Three-dimensional modeling attitude data processing method and system

Info

Publication number: CN118135118B
Application number: CN202410544259.6A
Authority: CN
Inventors: 林钦松; 张向晖; 陈兰; 陈康
Original assignee: Xinzhi Technology Jiangsu Co ltd
Current assignee: Xinzhi Technology Jiangsu Co ltd
Filing date: 2024-05-06
Publication date: 2024-07-09
Anticipated expiration: 2044-05-06

Abstract

The invention provides a three-dimensional modeling attitude data processing method and system. Wherein the method comprises the following steps: a user stands on dance equipment, a plurality of gesture view angles of the user are obtained, an initial three-dimensional gesture model is established, and the model is displayed in a first display area; the user selects any one of the demonstration dance in the preset dance group of the second display area, determines the demonstration dance as a target demonstration dance, and divides the target demonstration dance into segments to obtain dance segments corresponding to different preset limb movements; playing the target demonstration dance in a second display area, acquiring the body posture change of the user in real time, and updating the initial three-dimensional posture model according to the body posture change to obtain a current three-dimensional posture model; and comparing the body posture change of the user under the dance segment with the corresponding preset limb action to obtain segment scoring results of the dance segment, determining total scoring results based on the segment scoring results of all the dance segments, and displaying the total scoring results in a third display area. The invention improves the user experience.

Description

Three-dimensional modeling attitude data processing method and system

Technical Field

The present invention relates to data processing technologies, and in particular, to a three-dimensional modeling gesture data processing method and system.

Background

During leisure time, entertainment is indispensable. Entertainment is a means by which people consciously pursue mental balance, mental rest, and therefore, most of them have been invented by careful design. Almost every recreational activity requires special, non-replaceable equipment, a certain specification of field, appliances. For example, a dance device can integrate songs and dances into a game, is a game device with a music rhythm type, can cultivate rhythmicity, enables people to be more confident, and is a first choice for leisure and entertainment of many people.

The inventor finds that the existing dance equipment mostly consists of a screen display area and a sole pedal, and plays games by two feet of a user, so that the hand or head movements are not planned, and certain movement limitations exist. And cannot be finely scored and re-demonstrated for nonstandard actions according to the gesture change of the user.

Disclosure of Invention

Based on the above problems, the present invention has been made to provide a three-dimensional modeling attitude data processing method and system that overcomes or at least partially solves the above problems.

According to an aspect of the present invention, there is provided a three-dimensional modeling attitude data processing method including the steps of: responding to standing of a user on dance equipment, acquiring posture view angles based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on the posture view angles, and sending the initial three-dimensional posture model to a first display area for display;

Responding to the selection of the user on any one of the demonstration chores in the preset chores displayed in the second display area, determining the any one of the demonstration chores as a target demonstration chores, and dividing the target demonstration chores into segments to obtain chores corresponding to different preset limb movements;

Responding to the dance equipment to control the target demonstration dance to play in the second display area, acquiring the body posture change of the user in real time, and updating the initial three-dimensional posture model in real time according to the body posture change of the user to obtain a current three-dimensional posture model;

Comparing the body posture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain segment scoring results corresponding to any dance segment, determining total scoring results based on the segment scoring results of all dance segments, and sending the total scoring results to a third display area for display.

Optionally, in the method according to the present invention, in response to a user standing on a dance device, acquiring perspective views based on a plurality of different perspectives of the user, and establishing an initial three-dimensional gesture model based on the perspective views, and sending the initial three-dimensional gesture model to a first display area for display, including:

acquiring head portrait information of the user;

invoking a preset user head portrait group, wherein the preset user head portrait group comprises different preset head portraits and weight information respectively corresponding to the different preset head portraits;

traversing the preset user head portrait group and determining weight information corresponding to the head portrait information;

Acquiring a gravity value sent by a gravity detection module arranged on the dance equipment, comparing the gravity value with the weight information, and determining that the weight accords with a result;

And when the weight conforming result is conforming, determining that the user stands on dance equipment, acquiring each posture view diagram based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on each posture view diagram, and sending the initial three-dimensional posture model to a first display area for display.

Optionally, in the method according to the present invention, acquiring each of the gesture perspective views based on a plurality of different perspectives of the user, and building an initial three-dimensional gesture model based on each of the gesture perspective views, and sending the initial three-dimensional gesture model to a first display area for display, including:

Acquiring a left-view posture image, a right-view posture image, a front-view posture image and a rear-view posture image based on the user, and forming a posture image group from the left-view posture image, the right-view posture image, the front-view posture image and the rear-view posture image;

Body characteristic recognition is carried out on each posture graph in the posture graph group, body characteristics respectively included in each posture graph are obtained, the body characteristics included in at least two posture graphs are determined to be universal characteristics, and the body characteristics independently included in each posture graph are determined to be independent characteristics;

Acquiring the positions of all the universal features in the corresponding gesture graphs and the independent feature positions of the independent features in the corresponding gesture graphs, and determining feature adjustment positions according to the position differences among the positions of all the universal features;

a preset three-dimensional human body template is called, independent features based on independent feature positions and general features based on feature adjustment positions are respectively built in the preset three-dimensional human body template, and an initial three-dimensional attitude model is obtained;

And sending the initial three-dimensional gesture model to a first display area for display.

Optionally, in the method according to the present invention, in response to the selection of any one of the demonstration dance sets displayed in the second display area by the user, determining the any one of the demonstration dance sets as a target dance, and dividing the target demonstration dance into segments to obtain dance segments corresponding to different preset limb movements, including:

Calling a preset dance group and displaying the preset dance group in a second display area, wherein the preset dance group comprises a plurality of demonstration dances with different dance types;

Responding to the interaction of the user for the preset time on any one of the demonstration dancing, completing the selection of the any one of the demonstration dancing, and determining the any one of the demonstration dancing as a target demonstration dancing;

acquiring each image frame forming the target demonstration dance, and determining a preset limb action corresponding to each image frame;

And determining whether preset limb movements corresponding to all the adjacent image frames are identical or not in sequence frame by taking the image frame positioned at the first position as a starting point, and dividing each image frame which is arranged continuously and corresponds to the preset limb movements and is identical into a dance segment to obtain dance segments corresponding to different preset limb movements.

Optionally, in the method according to the present invention, in response to the dance device controlling to play the target demonstration dance in the second display area, a body posture change of the user is obtained in real time, and the initial three-dimensional posture model is updated in real time according to the body posture change of the user, so as to obtain a current three-dimensional posture model, including:

responding to a playing instruction of the user, and controlling the target demonstration dance to be played in the second display area by the dance equipment;

acquiring body posture changes corresponding to the user when the user plays the dance segments in different directions in real time, and processing the body posture changes based on preset limb movements corresponding to the dance segments to obtain limb posture changes;

And updating the initial three-dimensional posture model in real time according to the posture changes of each limb of the user to obtain a current three-dimensional posture model.

Optionally, in the method according to the present invention, processing each of the body posture changes based on each of preset limb movements corresponding to each of the dance segments, to obtain a limb posture change includes:

Determining the physical limbs respectively related based on each preset limb action respectively corresponding to each dance segment;

And processing each body posture change based on the physical limb related to each dance segment, and removing the posture change part which does not relate to the corresponding physical limb in each body posture change to obtain each limb posture change related to the physical limb.

Optionally, in the method according to the present invention, updating the initial three-dimensional posture model in real time according to each limb posture change of the user, to obtain a current three-dimensional posture model includes:

determining a limb model part corresponding to the physical limb in the initial three-dimensional posture model based on the physical limb respectively related to each limb posture change of the user;

And updating the limb model part in the initial three-dimensional posture model in real time according to the change of each limb posture of the user to obtain a current three-dimensional posture model.

Optionally, in the method according to the present invention, comparing the body posture change of the user under any dance segment with a preset limb action corresponding to any dance segment to obtain a segment scoring result corresponding to any dance segment, determining a total scoring result based on each segment scoring result of all dance segments, and sending the total scoring result to a third display area for display, where the method includes:

Comparing the body posture change of the user under any corresponding dance segment with the preset limb action corresponding to any dance segment to obtain a comparison difference value;

when the comparison difference value is larger than a preset value, marking the limb model part corresponding to the entity limb related to the preset limb action in the current three-dimensional gesture model by preset time;

calling a preset scoring table, wherein the scoring table comprises different comparison difference values and segment scoring results respectively corresponding to the different comparison difference values;

traversing the preset scoring table, and determining a segment scoring result corresponding to the comparison difference value;

And obtaining scoring results of all the segments corresponding to all the dance segments respectively, determining a total scoring result based on mean value calculation, and sending the total scoring result to a third display area for display.

Optionally, in the method according to the present invention, in response to the comparison difference value being greater than a preset value, marking a limb model portion of the current three-dimensional posture model corresponding to the physical limb involved in the preset limb action for a preset time, including:

When the comparison difference value is larger than a preset value, sending the preset limb action to a first display area, and performing superposition display for preset time after the current three-dimensional gesture model in a preset frequency gradual change mode;

determining a limb model part corresponding to an entity limb related to the preset limb action in a current three-dimensional gesture model, and acquiring a first pixel value of each first pixel point forming the limb model part and a second pixel value of each second pixel point forming the preset limb action;

calculating an absolute difference between the first pixel value and the second pixel value;

and when the absolute difference value is smaller than a preset threshold value, configuring a second pixel point corresponding to the second pixel value as a third pixel value.

According to yet another aspect of the present invention, there is provided a three-dimensional modeling attitude data processing system including: the model building module is configured to respond to the situation that a user stands on dance equipment, obtain each posture view angle diagram based on a plurality of different view angles of the user, build an initial three-dimensional posture model based on each posture view angle diagram, and send the initial three-dimensional posture model to a first display area for display;

The segment dividing module is configured to respond to selection of any demonstration dance in the preset dance group displayed in the second display area by the user, determine the any demonstration dance as a target demonstration dance, and divide the target demonstration dance into segments to obtain dance segments corresponding to different preset limb movements;

The model updating module is configured to respond to the dance equipment to control the target demonstration dance to play in the second display area, acquire the body posture change of the user in real time, and update the initial three-dimensional posture model in real time according to the body posture change of the user to obtain a current three-dimensional posture model;

The scoring module is configured to compare the body posture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain segment scoring results corresponding to any dance segment, determine total scoring results based on the segment scoring results of all dance segments, and send the total scoring results to a third display area for display.

According to the scheme of the invention, when a user stands on the dance equipment, a plurality of gesture visual angles of the user can be acquired, an initial three-dimensional gesture model is built according to the gesture visual angles, and then the initial three-dimensional gesture model is displayed in the first display area. The user can randomly select one of the preset dance groups in the second display area, at this time, the invention determines the dance as the target dance, and divides the target dance into segments to obtain dance segments corresponding to different preset limb movements. When the target demonstration dance is played in the second display area, the method and the device acquire the body posture change of the user in real time, and update the initial three-dimensional posture model in real time to acquire the current three-dimensional posture model. And comparing the body posture change of the user with the preset limb actions to obtain a total scoring result of the user, and sending the total scoring result to a third display area for display. According to the method and the device for dividing the dance segments of the display dance according to different preset limb actions, the body posture change of the user is obtained in real time, and user experience is improved to a great extent.

Drawings

FIG. 1 illustrates a flow chart of a three-dimensional modeling pose data processing method according to an embodiment of the invention;

FIG. 2 illustrates a block diagram of a three-dimensional modeling gesture data processing system in accordance with another embodiment of the present invention;

fig. 3 shows a schematic diagram of a computing device 100 according to yet another embodiment of the invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The present inventors have proposed the present invention in order to solve the problems in the prior art described above. One embodiment of the present invention provides a three-dimensional modeling pose data processing method that may be executed in a computing device.

Fig. 1 illustrates a flow chart of a method 200 according to one embodiment of the invention, the method 200 being adapted to be performed in a computing device (e.g., the computing device 100 described below).

As shown in fig. 1, the method 200 is for implementing a three-dimensional modeling gesture data processing method, beginning with step S202, and in step S202, the method includes the following steps:

and responding to standing of the user on the dance equipment, acquiring posture view angles based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on the posture view angles, and sending the initial three-dimensional posture model to a first display area for display.

For example, in this embodiment, a dance apparatus may be understood as a physical game machine, such as a dance machine, having an interactive function, a data processing function, and an information storage function, which is a music rhythm type game apparatus. When a user stands on the dance equipment, the camera can start a shooting function, so that images corresponding to the front, the side and the back of the user, namely, gesture view angles under a plurality of different view angles, are respectively obtained. And the initial three-dimensional gesture model can be established according to the gesture visual angles under different visual angles, and the initial three-dimensional gesture model is sent to a first display area for display, so that a user can watch the initial three-dimensional gesture model corresponding to the gesture of the user based on the first display area, corresponding immersion sense and user experience are improved, wherein the first display area can be understood as the leftmost screen display area of the whole display screen.

It should be noted that, the camera may be separately provided in an independent manner, or may be integrated on the dance device in an integrated manner, and the specific form of the camera is not limited in this embodiment.

Further, the foregoing "in response to a user standing on dance equipment, acquiring perspective views based on the gestures of the user under a plurality of different perspectives, and establishing an initial three-dimensional gesture model based on the perspective views, and sending the initial three-dimensional gesture model to a first display area for display" may further include the following steps:

acquiring head portrait information of the user;

For example, in this embodiment, when a user stands on the dance device, for example, a camera may collect facial images of the user, and then perform corresponding facial recognition based on a server, so as to obtain corresponding head portrait information, and at the same time, the server may call a preset head portrait group of the user, and find weight information corresponding to the head portrait information by traversing the preset head portrait group of the user, so as to further obtain a weight value, that is, a gravity value, sent by a gravity detection module provided on the dance device. The gravity detection module may be understood as a gravity sensor, set up in a table top located on the dance device where the user stands. Comparing the weight value with weight information of a user currently standing on the dance equipment, determining whether the weight information of the user is the same as the weight value on the dance equipment, so as to obtain a weight conforming result, and judging whether a corresponding initial three-dimensional gesture model needs to be established based on the weight conforming result;

For example, the weight conforming result may be conforming or non-conforming, where when the weight conforming result is conforming, that is, the weight information of the user and the gravity value on the dance device are the same or similar, then it may be determined that the user stands on the dance device in a correct posture (for example, the legs are all located on the table of the dance device), at this time, an initial three-dimensional posture model is built based on posture view angles of the user under a plurality of different view angles, and the initial three-dimensional posture model is sent to the first display area for display based on the posture view angles. When the weight conforming result is not conforming, it can be determined that the user is likely to be caused to not stand on the dance device in the correct posture, for example, a situation that one foot stands on the table surface of the dance device and the other foot stands on the ground occurs, and in this case, the corresponding model is not established, so that the user can be helped to adjust the posture, and the corresponding user experience is improved.

It should be noted that, each preset head portrait in the preset user head portrait group and the weight information corresponding to each preset head portrait may be obtained based on the collection of the server, that is, when the user uses the dance device for the first time, the server may collect the head portrait information and the weight information of the user in advance, and store the head portrait information as the preset head portrait into the preset user head portrait group together, so that the user can obtain the weight information corresponding to the user based on the head portrait information of the user in the current use process or the subsequent use process.

Further, the above method for acquiring the perspective views of each gesture under a plurality of different perspectives of the user, establishing an initial three-dimensional gesture model based on the perspective views of each gesture, and sending the initial three-dimensional gesture model to the first display area for display, further includes the following steps:

For example, in the present embodiment, based on the posture of the user standing on the dance apparatus, the left-view posture chart, the right-view posture chart, the front-view posture chart, and the rear-view posture chart of the user can be acquired by the camera, respectively, and the posture chart groups are formed. And then, body characteristic recognition is carried out on each gesture image in the gesture image group, and each body characteristic included in each gesture image is obtained. For example, the left-view pose image may see the left arm of the user, and the left arm is a physical feature in the left-view pose image. After the physical features included in each posture graph are obtained, the physical features included in at least two posture graphs can be determined to be general features, the physical features independently included in each posture graph are determined to be independent features, for example, the front view posture graph and the rear view posture graph can see the shoulders of the user, and the shoulders are the general features of the front view posture graph and the rear view posture graph. The front-view gesture graph can see the eyes of the user, but in other gesture graphs, the eyes are an independent feature of the front-view gesture graph. Therefore, the positions of the universal features in the corresponding gesture graphs and the positions of the independent features in the corresponding gesture graphs can be obtained.

When the positions of the general feature positions in the corresponding gesture graphs are different, for example, the user has a situation of high and low shoulders, the positions of the user shoulders in the left-view gesture graph and the right-view gesture graph are inconsistent, the position height sum of the left shoulder and the right shoulder needs to be calculated, the height average value of the user shoulders is obtained by dividing the position sum by two, the position sum is used as the general feature position of the user shoulders, and the feature adjustment position is determined according to the position difference between the general feature positions.

After the independent characteristic positions and the characteristic adjustment positions are respectively determined, the server can call a preset three-dimensional human body template, and the independent characteristics of the independent characteristic positions and the general characteristics of the characteristic adjustment positions are respectively built in the preset three-dimensional human body template, so that an initial three-dimensional posture model is obtained; it should be noted that the preset three-dimensional human body template may be understood as a general blank human body template, that is, a template without any physical features and with only human body contours.

In step S204, the following are included:

and responding to the selection of the user on any one of the demonstration dancing in the preset dancing groups displayed in the second display area, determining any one of the demonstration dancing as a target demonstration dancing, and dividing the target demonstration dancing into segments to obtain dancing segments corresponding to different preset limb movements.

For example, in this embodiment, there are a plurality of demonstration dances, that is, preset dance groups, in the second display area. The second display area may be understood as the intermediate screen display area of the overall display screen. The user can select any one of the demonstration dance in the preset dance group to perform dance, and it is noted that a complete demonstration dance is composed of preset limb movements of a plurality of different parts, such as a head dance movement, a leg dance movement or a hand dance movement. After the user selects one of the demonstration dances, the server determines the demonstration dance as a target demonstration dance, and segments the target demonstration dance according to preset limb movements of different parts, for example, segments all the segments belonging to the head dance movements are segmented together, so that dance segments corresponding to different preset limb movements are obtained.

Further, the above-mentioned "responding to the selection of the user to any one of the demonstration dance in the preset dance group displayed in the second display area, determining the any one of the demonstration dance as the target dance, and dividing the target demonstration dance into segments to obtain dance segments corresponding to different preset limb movements" further includes the following steps:

For example, in this embodiment, when the user stands on the dance device, the server may call up the preset dance group and display the preset dance group in the second display area, where the preset dance group includes a plurality of dance demonstrations having different dance types. When the user presses the display screen and maintains the preset time, for example, the preset time is 2 seconds while selecting the presentation dance, the user presses the display screen with a finger for 2 seconds, and then the selection of any presentation dance is completed, and the presentation dance is determined as the target presentation dance. After the target demonstration dance is determined, each image frame forming the target demonstration dance is acquired, and the preset limb actions included in each image frame can be determined through the corresponding picture of each image frame. For example, the target demonstration dance has 5 image frames, the image frames at the first position are used as starting points, whether the preset limb actions corresponding to all the adjacent image frames are the same or not is determined according to the time sequence, and each image frame which is arranged continuously and corresponds to the preset limb actions and is the same is divided into a dance segment. For example, the preset limb movements corresponding to the 5 image frames of the target demonstration dance are respectively a head dance movement, a leg dance movement and a head dance movement, so that the first frame and the second frame can be divided into a dance segment, the third frame and the fourth frame can be divided into a dance segment, and the fifth frame is a dance segment, thereby obtaining dance segments corresponding to different preset limb movements.

In step S206, the following are included:

and responding to the dance equipment to control the target demonstration dance to play in the second display area, acquiring the body posture change of the user in real time, and updating the initial three-dimensional posture model in real time according to the body posture change of the user to obtain a current three-dimensional posture model.

For example, in this embodiment, after the user selects any one of the demonstration dances to dance, the second display area of the dance device plays the target demonstration dance. When a user starts dancing, the dance motions made by the user can be acquired in real time through the camera, namely, the body posture changes of the corresponding user are acquired. The three-dimensional posture model needs to be ensured to be changed along with the body posture change of the user, namely the initial three-dimensional posture model needs to be updated in real time according to the body posture change of the user, so that the current three-dimensional posture model is obtained. In this embodiment, the camera may acquire the dance motion of the user in real time and display the dance motion in the first display area. Namely, the user can watch the body posture change of the user in real time, so that the experience sense during the game is greatly improved.

Further, the foregoing "playing the target demonstration dance in the second display area in response to the dance device control, acquiring the body posture change of the user in real time, and updating the initial three-dimensional posture model in real time according to the body posture change of the user to obtain the current three-dimensional posture model" further includes the following steps:

For example, in this embodiment, when a user sends a play instruction by clicking a preset play button of a display screen, the dance device controls to play a target demonstration dance in the second display area, and in the playing process, the body posture change of the user under different dance segments is obtained in real time. The server processes the acquired body posture changes of the user again based on the preset limb movements corresponding to the dance segments respectively, and the body posture changes of the user are obtained. For example, when the dance segment presets the limb movements as the head dance movements, only the head dance movements are identified and acquired in the body posture change of the dance segment, so that the head posture change is obtained. And updating the initial three-dimensional posture model in real time according to the acquired limb posture changes of the user to obtain the current three-dimensional posture model. According to the embodiment, the limb posture change of the user in each different dance segment can be accurately obtained, and the workload of equipment is saved.

Further, the above-mentioned "processing each of the body posture changes based on each of the preset limb movements corresponding to each of the dance segments, respectively, to obtain a limb posture change" further includes the steps of:

For example, in this embodiment, each preset limb movement may respectively relate to a corresponding physical limb, for example, when the dance segment preset limb movement is a head dance movement, the physical limb related in the dance segment is the head, so that in the process of processing the body posture change based on the preset limb movement, the posture change part of the body posture change of the dance segment, which is not related to the physical limb, can be directly removed, so that each limb posture change related to the physical limb can be directly obtained.

Further, the above method for updating the initial three-dimensional posture model in real time according to the posture change of each limb of the user to obtain the current three-dimensional posture model further includes the following steps:

For example, in this embodiment, the server determines, in the initial three-dimensional posture model, a limb model portion corresponding to the physical limb based on the physical limb related to each limb posture change of the user, for example, the physical limb of the dance segment is a head, and then the head model portion in the initial three-dimensional posture model is a limb model portion corresponding to the dance segment. And updating the limb model part in the initial three-dimensional posture model in real time according to the limb posture changes of the user, so that the current three-dimensional posture model is obtained, namely, only the part corresponding to the entity limb in the initial three-dimensional posture model is required to be updated, and compared with the traditional integral updating mode, certain equipment calculation amount can be saved, and the corresponding data processing efficiency is improved.

In step S208, the following are included:

For example, in this embodiment, after the user completes all limb movements of the target demonstration dance, the server compares the body posture change of the user under a certain dance segment with the preset limb movements of the dance segment, and scores the user according to the difference between the body posture change of the user and the preset limb movements, so as to obtain the segment scoring result of the dance segment. And further scoring each dance segment in this manner to determine an overall scoring result, and transmitting the overall scoring result to a third display area for display, wherein the third display area may be understood as the rightmost screen display area of the overall display. According to the embodiment, each dance segment can be rapidly scored, the total scoring result is determined based on the scoring result of each dance segment, the total scoring result is very objective, and a user can see the scoring process of each dance segment, and the scoring is a scoring mode which can be accepted by the user.

For example, the segment scoring results can be correspondingly obtained based on the difference condition of the body posture change of the user and the preset limb actions, that is, the larger the difference is, the lower the corresponding scoring result is, and the smaller the difference is, the more the corresponding scoring result is, the higher the corresponding scoring result is; after the scoring result of each dance segment is determined, the corresponding total scoring result can be obtained by summing up the numerical values corresponding to each scoring result, so that not only can each dance segment be scored correspondingly, but also the whole dance segment can be scored correspondingly, and the corresponding user experience is improved; it should be noted that the specific scoring method may be implemented by the following scheme.

Further, the above-mentioned "comparing the body gesture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain a segment scoring result corresponding to any dance segment, determining a total scoring result based on each segment scoring result of all dance segments, and sending the total scoring result to a third display area for display", further includes the following steps:

For example, in this embodiment, the server may compare the body gesture change of the user under any dance segment with the preset limb motion corresponding to the dance segment, where the comparison content may include the motion amplitude, the position, and so on, so as to obtain the comparison difference value. And comparing the comparison difference value with a preset value, wherein the preset value can be preset by a server and can be understood as a qualified line. When the comparison difference value is larger than the preset value, it can be understood that the difference between the body posture change of the user and the preset limb action is too large, at this time, the preset time is marked on the limb model part corresponding to the physical limb related to the preset limb action in the current three-dimensional posture model, for example, the current preset limb action is the head, the preset time is 3 seconds, and the head is marked for 3 seconds in the current three-dimensional posture model, so that the user can clearly know which limb action in the dance segment is not standard enough. In addition, in this embodiment, a preset scoring table is also set up, where specific scores corresponding to different comparison difference values are found in the preset scoring table, that is, the scoring table includes score results of fragments corresponding to different comparison difference values and different comparison difference values respectively. And after the comparison difference value is obtained, determining a fragment grading result corresponding to the comparison difference value in a preset grading table. And after obtaining the segment scoring results of each dance segment, calculating the average value of the scoring results of all segments, so as to obtain the total scoring result, and sending the total scoring result to a third display area for display.

In the process of performing corresponding motion comparison, openCV may be used to perform motion analysis on preset limb motions corresponding to each dance segment in advance, so as to determine corresponding preset motion feature points (such as arm bending degrees, leg bending degrees, body forward inclination degrees, etc.); similarly, openCV may be used to perform motion analysis on the body gesture change of the user under each dance segment, so as to determine corresponding gesture motion feature points, and by comparing each gesture feature point with each corresponding preset motion feature point, the motion difference value (for example, the motion difference value of the degree of bending of the arm, the motion difference value of the degree of bending of the leg, and the motion difference value of the degree of forward tilting of the body) of each preset motion feature point of the user is determined, for example, when the preset motion feature point of the preset limb motion includes 30 degrees of bending of the arm, and the gesture motion feature point in the body gesture change of the corresponding user is 60 degrees of bending of the arm, then the absolute difference value (30-60 degrees of absolute value, that is, 30 degrees) between the gesture feature point and the gesture feature point may be used as the corresponding motion difference value;

after obtaining all the action difference values corresponding to the same dance segment, in order to facilitate subsequent unified calculation, corresponding normalization calculation can be performed on each action difference value, and then corresponding comparison difference values are obtained by performing average calculation on each action difference value subjected to normalization calculation.

It should be noted that, the OpenCV used in the above solution is a cross-platform computer vision and machine learning software library issued based on apache2.0 license (open source), and may run on Linux, windows, android and Mac OS operating systems. Many general algorithms in terms of image processing and computer vision can be implemented; since OpenCV is the prior art, the specific calculation principle of OpenCV will not be described in detail in this embodiment.

Further, the foregoing "in response to the comparison difference value being greater than a preset value, marking the limb model portion corresponding to the physical limb involved in the preset limb action in the current three-dimensional posture model for a preset time" further includes the following steps:

For example, in this embodiment, when the comparative difference value of a certain dance segment is greater than the preset value, the preset limb motion of the dance segment is sent to the first display area for display, and the overlapping display of the preset time is performed in a mode of gradual change of the preset frequency lining below the current three-dimensional gesture model. For example, the preset frequency is once 2 seconds, the preset time is 6 seconds, and the preset limb actions are displayed in a superimposed manner within 6 seconds at a frequency of gradually changing once for 2 seconds, namely 3 preset limb actions are displayed; in order to further improve the markability, the limb model portion corresponding to the physical limb related to the preset limb action may be further marked based on the current three-dimensional gesture model, and the marking process includes: determining a limb model part corresponding to a physical limb related to a preset limb action in a current three-dimensional gesture model, wherein pixels forming the limb model part are first pixels, pixels forming the preset limb model part are second pixels, and obtaining first pixel values of the first pixels forming the limb model part and second pixel values of the second pixels forming the preset limb action to calculate a difference value between the first pixel values and the second pixel values, and calculating an absolute value of the difference value, namely an absolute difference value. And when the absolute difference value is smaller than a preset threshold value, configuring a second pixel point corresponding to the second pixel value as a third pixel value. The step can ensure that the pixel values of the limb model part and the preset limb actions are not close, namely the display colors are not similar, so that a user can more clearly watch the current three-dimensional gesture model and the preset limb actions.

According to the scheme of the invention, when a user stands on the dance equipment, a plurality of gesture visual angles of the user can be acquired, an initial three-dimensional gesture model is built according to the gesture visual angles, and then the initial three-dimensional gesture model is displayed in the first display area. The user can randomly select one of the preset dance groups in the second display area, at this time, the invention determines the dance as the target dance, and divides the target dance into segments to obtain dance segments corresponding to different preset limb movements. When the target demonstration dance is played in the second display area, the method and the device acquire the body posture change of the user in real time, and update the initial three-dimensional posture model in real time to acquire the current three-dimensional posture model. And comparing the body posture change of the user with the preset limb actions to obtain a total scoring result of the user, and sending the total scoring result to a third display area for display. According to the invention, the dance segments of the display dance can be divided according to different preset limb movements, and the body posture change of the user is obtained in real time, so that the variety of the user movements is greatly improved.

Another embodiment of the present invention provides a three-dimensional modeling gesture data processing system, fig. 2 is a block diagram of a corresponding device thereof, the system comprising:

the model building module is configured to respond to the situation that a user stands on dance equipment, obtain each posture view angle diagram based on a plurality of different view angles of the user, build an initial three-dimensional posture model based on each posture view angle diagram, and send the initial three-dimensional posture model to a first display area for display;

Fig. 3 illustrates a block diagram of a computing device 100 according to yet another embodiment of the invention. As shown in FIG. 3, in a basic configuration 102, computing device 100 typically includes a system memory 106 and one or more processors 104. The memory bus 108 may be used for communication between the processor 104 and the system memory 106.

Depending on the desired configuration, the processor 104 may be any type of processing including, but not limited to: microprocessor (μp), microcontroller (μc), digital information processor (DSP), or any combination thereof. The processor 104 may include one or more levels of caches, such as a first level cache 110 and a second level cache 112, a processor core 114, and registers 116. The example processor core 114 may include an Arithmetic Logic Unit (ALU), a Floating Point Unit (FPU), a digital signal processing core (DSP core), or any combination thereof. The example memory controller 118 may be used with the processor 104, or in some implementations, the memory controller 118 may be an internal part of the processor 104.

Depending on the desired configuration, system memory 106 may be any type of memory including, but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. Physical memory in a computing device is often referred to as volatile memory, RAM, and data in disk needs to be loaded into physical memory in order to be read by processor 104. The system memory 106 may include an operating system 120, one or more applications 122, and program data 124. The application 122 is actually a plurality of program instructions for instructing the processor 104 to perform a corresponding operation. In some implementations, the application 122 may be arranged to execute instructions on an operating system by the one or more processors 104 using the program data 124 in some implementations. Operating system 120 may be, for example, linux, windows or the like, which includes program instructions for handling basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for implementing various functions desired by the user, and the application 122 may be, for example, a browser, instant messaging software, a software development tool (e.g., integrated development environment IDE, compiler, etc.), or the like, but is not limited thereto. When an application 122 is installed into computing device 100, a driver module may be added to operating system 120.

When the computing device 100 starts up running, the processor 104 reads the program instructions of the operating system 120 from the memory 106 and executes them. Applications 122 run on top of operating system 120, utilizing interfaces provided by operating system 120 and underlying hardware to implement various user-desired functions. When a user launches the application 122, the application 122 is loaded into the memory 106, and the processor 104 reads and executes the program instructions of the application 122 from the memory 106.

Computing device 100 also includes storage device 132, storage device 132 including removable storage 136 and non-removable storage 138, both removable storage 136 and non-removable storage 138 being connected to storage interface bus 134.

Computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to basic configuration 102 via bus/interface controller 130. The example output device 142 includes a graphics processing unit 148 and an audio processing unit 150. They may be configured to facilitate communication with various external devices such as a display or speakers via one or more a/V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboard, mouse, pen, voice input device, touch input device) or other peripherals (e.g., printer, scanner, etc.) via one or more I/O ports 158. An example communication device 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via one or more communication ports 164 over a network communication link.

The network communication link may be one example of a communication medium. Communication media may typically be embodied by computer readable instructions, data structures, program modules, and may include any information delivery media in a modulated data signal, such as a carrier wave or other transport mechanism. A "modulated data signal" may be a signal that has one or more of its data set or changed in such a manner as to encode information in the signal. By way of non-limiting example, communication media may include wired media such as a wired network or special purpose network, and wireless media such as acoustic, radio Frequency (RF), microwave, infrared (IR) or other wireless media. The term computer readable media as used herein may include both storage media and communication media.

Computing device 100 also includes a storage interface bus 134 that is coupled to bus/interface controller 130. The storage interface bus 134 is coupled to the storage device 132, and the storage device 132 is adapted to store data. An example storage device 132 may include removable storage 136 (e.g., CD, DVD, U disk, removable hard disk, etc.) and non-removable storage 138 (e.g., hard disk drive HDD, etc.).

In computing device 100 according to the present invention, application 122 includes a plurality of program instructions to perform method 200.

The various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions of the methods and apparatus of the present invention, may take the form of program code (i.e., instructions) embodied in tangible media, such as removable hard drives, U-drives, floppy diskettes, CD-ROMs, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.

In the case of program code execution on programmable computers, the computing device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code; the processor is configured to perform the method of the invention in accordance with instructions in said program code stored in the memory.

By way of example, and not limitation, readable media comprise readable storage media and communication media. The readable storage medium stores information such as computer readable instructions, data structures, program modules, or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of readable media.

In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with examples of the invention. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It should be appreciated that the teachings of the present invention as described herein may be implemented in a variety of programming languages and that the foregoing description of specific languages is provided for disclosure of preferred embodiments of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Furthermore, some of the embodiments are described herein as methods or combinations of method elements that may be implemented by a processor of a computer system or by other means of performing the functions. Thus, a processor with the necessary instructions for implementing the described method or method element forms a means for implementing the method or method element. Furthermore, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is for carrying out the functions performed by the elements for carrying out the objects of the invention.

As used herein, unless otherwise specified the use of the ordinal terms "first," "second," "third," etc., to describe a general object merely denote different instances of like objects, and are not intended to imply that the objects so described must have a given order, either temporally, spatially, in ranking, or in any other manner.

While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.

Claims

1. The three-dimensional modeling attitude data processing method is characterized by comprising the following steps of:

Responding to standing of a user on dance equipment, acquiring posture view angles based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on the posture view angles, and sending the initial three-dimensional posture model to a first display area for display;

comparing the body posture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain a segment scoring result corresponding to any dance segment, determining a total scoring result based on each segment scoring result of all dance segments, and sending the total scoring result to a third display area for display;

Wherein, responding to a user standing on dance equipment, acquiring each posture view angle diagram based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on each posture view angle diagram, and sending the initial three-dimensional posture model to a first display area for display, wherein the method comprises the following steps:

acquiring head portrait information of the user;

when the weight conforming result is conforming, determining that the user stands on dance equipment, acquiring each posture view diagram based on a plurality of different view angles of the user, establishing an initial three-dimensional posture model based on each posture view diagram, and sending the initial three-dimensional posture model to a first display area for display;

The method for acquiring the gesture view angles based on the user at a plurality of different view angles comprises the steps of establishing an initial three-dimensional gesture model based on the gesture view angles, and sending the initial three-dimensional gesture model to a first display area for display, wherein the steps include:

2. The three-dimensional modeling attitude data processing method according to claim 1, characterized by comprising the steps of:

Responding to the selection of the user on any one of the demonstration dancing in the preset dancing groups displayed in the second display area, determining any one of the demonstration dancing as a target dancing, and dividing the target demonstration dancing into segments to obtain dancing segments corresponding to different preset limb movements, wherein the method comprises the following steps:

3. The three-dimensional modeling attitude data processing method according to claim 1, characterized by comprising the steps of:

Responding to the dance equipment to control the target demonstration dance to play in the second display area, acquiring the body posture change of the user in real time, and updating the initial three-dimensional posture model in real time according to the body posture change of the user to obtain a current three-dimensional posture model, wherein the method comprises the following steps:

4. A three-dimensional modeling attitude data processing method according to claim 3, comprising the steps of:

processing each body posture change based on each preset limb movement corresponding to each dance segment respectively to obtain a limb posture change, wherein the processing comprises the following steps:

5. The three-dimensional modeling attitude data processing method according to claim 4, characterized by comprising the steps of:

Updating the initial three-dimensional posture model in real time according to the posture change of each limb of the user to obtain a current three-dimensional posture model, wherein the method comprises the following steps:

6. The three-dimensional modeling attitude data processing method according to claim 5, characterized by comprising the steps of:

Comparing the body posture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain a segment scoring result corresponding to any dance segment, determining a total scoring result based on each segment scoring result of all dance segments, and sending the total scoring result to a third display area for display, wherein the method comprises the following steps:

7. The three-dimensional modeling attitude data processing method according to claim 6, characterized by comprising the steps of:

And when the comparison difference value is larger than a preset value, marking the limb model part corresponding to the entity limb related to the preset limb action in the current three-dimensional gesture model for preset time, wherein the method comprises the following steps:

8. A three-dimensional modeling pose data processing system, comprising:

The scoring module is configured to compare the body posture change of the user under any dance segment corresponding to the preset limb action corresponding to any dance segment to obtain segment scoring results corresponding to any dance segment, determine total scoring results based on the segment scoring results of all dance segments, and send the total scoring results to a third display area for display;

wherein the model building module is further configured to:

acquiring head portrait information of the user;