CN115509350A - Method for acquiring gesture control right in multi-person environment, network device and storage medium - Google Patents

Abstract

The present application provides a method for acquiring gesture control rights in a multi-person environment, a network device, and a storage medium, wherein the method includes: acquiring the coordinates (x, y, z); get the multi-person gesture information set in the current frame handlist={hand0, hand1, hand2, ..., handn}; where n represents the number of hands in the current frame, and each gesture in the set includes the hand used to recognize the gesture Internal key point coordinates; determine the number of gestures in the multi-person gesture information set handlist, if it is greater than 1, output the hand closest to the P coordinate in the current frame as the control gesture. In the embodiment of the present application, the gesture of obtaining the control right in the current frame can be recognized in a multi-person gesture environment, so as to avoid confusion in the interactive system.

Description

Method for acquiring gesture control right in multi-person environment, network device and storage medium

technical field

The present application relates to the technical field of communication equipment, and in particular to a method for acquiring gesture control rights in a multi-person environment, network equipment and storage media.

Background technique

Gesture control can realize contactless operation, and its application is becoming more and more extensive. The operation of manual interaction through gesture recognition has gradually become a mainstream control method. However, during the gesture recognition process, the system can only recognize one gesture, and multiple people's gestures may appear in the camera recognition, which leads to system recognition confusion.

Contents of the invention

In order to overcome the problems existing in the related technologies, the present application provides a method for acquiring gesture control rights in a multi-person environment, a network device, and a storage medium.

According to the first aspect of the embodiment of the present application, the method for acquiring gesture control rights in a multi-person environment,

Obtain the coordinates (x, y, z) of the spatial position identification information point P of the acquisition control gesture of the previous frame buffer;

Get the multi-person gesture information set in the current frame handlist={hand0, hand1, hand2,...,handn}; where n represents the number of hands in the current frame, and each gesture in the set contains hand key points for gesture recognition coordinate;

Determine the number of gestures in the multi-person gesture information set handlist. If it is greater than 1, output the hand with the closest distance to the P coordinate in the current frame as the control gesture.

Preferably, determine the number of gestures in the handlist of the multi-person gesture information set, if the number of handlist gestures is equal to 1, output the current gesture as the gesture of obtaining control right, and update the P coordinate;

If the number of handlist gestures is equal to 0, the P coordinate is empty.

Preferably, it also includes judging whether the P coordinate is empty, if it is not empty, judging the number of gestures in the handlist of the multi-person gesture information set, and obtaining the control right gesture; if the P coordinate is empty, traversing the handlist, and each time in order Take the key point coordinates of one of the gestures for gesture conversion;

Determine whether the converted gesture is a control gesture;

If it is a control gesture, update the P coordinates and end the traversal; if it is not a gesture of control, reacquire the key point coordinates of the next gesture in the handlist to perform gesture conversion and determine whether the gesture is a gesture of control.

Preferably, the P coordinates (x, y, z) are obtained from gesture key points through an algorithm.

Preferably, the P coordinates (x, y, z) are obtained from the key points of the gesture through an algorithm, including processing the key points of the gesture through an average value or a weighted algorithm.

Preferably, the P coordinates (x, y, z) are selected from the area enclosed by the key points of the gesture.

Preferably, the P coordinate (x, y, z) is the center of the area enclosed by the key points of the gesture.

Preferably, the gestures in the recognized multi-person gesture information set are set gestures that can obtain control rights.

The second aspect of the present application provides a network device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, it executes a method for acquiring gesture control rights in a multi-person environment.

The third aspect of the present application provides a storage medium, on which computer program instructions are stored, and when the program instructions are executed by a processor, they are used to implement a method for acquiring gesture control rights in a multi-person environment.

The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

In the embodiment of the present application, in a multi-person gesture environment, the gesture of obtaining control right in the current frame can be identified through the adjacent frame comparison algorithm, which avoids confusion in the interactive system.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments consistent with the application and together with the application serve to explain the principles of the application.

Fig. 1 is the schematic flow chart shown in embodiment 1 of the present application;

Fig. 2 is the schematic flow chart shown in embodiment 2 of the present application;

FIG. 3 is a schematic flow diagram of Embodiment 3 of the present application.

detailed description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

In order to solve the problems existing in the background technology, Embodiment 1 of the present application provides a method for acquiring gesture control rights in a multi-person environment, as shown in FIG. 1 , including:

Obtain the coordinates (x, y, z) of the spatial position identification information point P of the acquisition control gesture in the previous frame cache.

Get the multi-person gesture information set in the current frame handlist={hand0, hand1, hand2,...,handn}; where n represents the number of hands in the current frame, and each gesture in the set contains hand key points for gesture recognition coordinate;

Determine the number of gestures in the multi-person gesture information set handlist. If it is greater than 1, output the hand with the closest distance to the P coordinate in the current frame as the control gesture.

The video captured by the camera is composed of consecutive frames, and the changes of adjacent frames are usually relatively small. Here we take SD video as an example to illustrate the reason. The frame rate of the SD camera is 30fps, and the interval between each frame is 0.33ms. Analyzing the data of adjacent frames, it can be found that in a very short period of time (0.33ms), even if the user's hand is in the process of dynamic operation, the data changes of adjacent frames are still very small. Therefore, in the above-mentioned embodiment, the adjacent frame comparison method is used to determine the gesture of acquiring the control right in the current frame by using the cached coordinates of the spatial position identification information point P of the gesture of acquiring the control right in the previous frame. Realize that in the multi-person gesture environment, the gesture of obtaining control right in the current frame can be recognized, and the confusion of the interactive system is avoided.

Embodiment 2, as shown in Figure 2, on the basis of the above-mentioned embodiment, judge the number of gestures in the handlist of the multi-person gesture information set, if the number of handlist gestures is equal to 1, output the current gesture as the gesture of obtaining control right, and the P coordinate Update to the P coordinate of the current frame.

If the number of handlist gestures is equal to 0, the P coordinate is empty.

Of course, other methods can also be used to deal with the situation that the number of gestures in the handlist of the multi-person gesture information set is less than or equal to 1, which will not be repeated here.

The embodiment of the present application also includes judging whether the P coordinate is empty, if it is not empty, it means that the current gesture control right has been occupied, and the multi-person gesture information set handlist is processed through the aforementioned adjacent frame comparison algorithm to obtain the control right gesture . If the P coordinate is empty, it means that the current gesture control right is not occupied. By traversing the handlist, and taking the key point coordinates of one of the gestures in order to perform gesture conversion.

Determine whether the converted gesture is a control gesture;

If it is a control gesture, update the P coordinates and end the traversal; if it is not a control gesture, reacquire the key point coordinates of the next gesture in the handlist to perform gesture conversion and determine whether to acquire the control gesture. Example 3 is shown in Figure 3 Show.

The P coordinates (x, y, z) in the embodiment of the present application are acquired by an algorithm from gesture key points. For example, it can be obtained by calculating the average value of gesture key points or by a weighted algorithm of each key point weight.

The P coordinates (x, y, z) in the embodiment of the present application are selected from the area enclosed by the key points of the gesture. For example, the P coordinate (x, y, z) is the center of the area enclosed by the key points of the gesture.

The gestures in the multi-person gesture information set identified in this application are set gestures that can obtain control rights.

First of all, it needs to be explained, how to obtain gesture control? Users perform certain gestures to gain control. If no one has obtained the current gesture control right, the gesture control right will be obtained directly. If the gesture control right has been occupied, it is necessary to wait for the gesture control right to be released before obtaining the gesture control right.

How to release gesture control? Including active release and passive release. Active release means that the user who has the gesture control right executes the "close control" gesture, and then actively releases the gesture control right. Passive release refers to the automatic release of the gesture control right when the operating hand of the user with the gesture control right leaves the range of the virtual operation frame within a certain period of time. When the gesture control right is released, set the P coordinate to be empty.

Is it possible to grab gesture control?

In order to avoid being interrupted during the operation, once the gesture control right is obtained by someone, other users cannot snatch the gesture control right. Only when the user who has the gesture control right releases it actively or passively, other users can regain the gesture control right.

For example, obtaining the gesture control right in the embodiment of the present application may be to straighten five fingers and face the screen. Gesture controls can be turned off by pointing five fingers or even facing away from the screen. The passive release can be that the gesture leaves the screen for a set time, etc. Of course, the gesture control authority here may also be other gestures and is not limited to the examples given.

The embodiment of the present application also provides a network device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, it executes the above-mentioned method for acquiring gesture control rights in a multi-person environment.

The embodiment of the present application also provides a storage medium, on which computer program instructions are stored, and when the program instructions are executed by a processor, they are used to implement the above-mentioned method for acquiring gesture control rights in a multi-person environment.

It should be understood that the present application is not limited to the precise constructions which have been described above and shown in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

The above are only preferred embodiments of the application, and are not intended to limit the application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the application shall be included in the protection of the application. within range.

Claims (10)

1. A multi-user environment gesture control right acquisition method is characterized in that,

acquiring a spatial position identification information point P coordinate (x, y, z) of a control right acquisition gesture cached in the previous frame; acquiring a multi-person gesture information set handle = { hand0, hand1, hand2, \8230; \ hand n } in a current frame; wherein n represents the number of hands in the current frame, and each gesture in the set comprises hand key point coordinates for recognizing the gesture;

and acquiring the number of the gestures through a multi-person gesture information set handle, and if the number of the handles is greater than 1, outputting the hand closest to the P coordinate in the current frame as a gesture for acquiring the control right.

2. The multi-person environment gesture control right acquisition method according to claim 1, wherein if the number of gestures in a handlest is equal to 1, outputting a current gesture as an acquisition control right gesture, and updating a P coordinate;

if the number of handlists gestures is equal to 0, the P coordinate is null.

3. The multi-person environment gesture control right acquisition method according to claim 2, further comprising judging whether the P coordinate is empty, and if not, judging the number of gestures in a multi-person gesture information set handleist to obtain an acquisition control right gesture; if the P coordinate is empty, traversing the handlest, and sequentially taking the key point coordinate of one gesture at a time to perform gesture conversion;

judging whether the converted gesture is a gesture for acquiring control right;

if the control right gesture is obtained, updating the P coordinate, and ending traversal; if the gesture is not the gesture for acquiring the control right, the key point coordinate of the next gesture in the handlest is acquired again to perform gesture conversion and judge whether the gesture for acquiring the control right is acquired.

4. The multi-person environment gesture control right acquisition method according to claim 1, wherein the P coordinate (x, y, z) is obtained by a gesture key point through an algorithm.

5. The method for acquiring multi-person environment gesture control right according to claim 4, wherein the P coordinate (x, y, z) is obtained from the gesture key point through an algorithm, including processing the gesture key point through an average value or a weighted algorithm.

6. The method of claim 1, wherein the P coordinate (x, y, z) is selected from an area surrounded by gesture key points.

7. The method of claim 6, wherein the P coordinate (x, y, z) is the center of an area surrounded by the gesture key points.

8. The method as claimed in claim 1, wherein the gesture in the recognized multi-person gesture information set is a gesture for setting the control right to be obtained.

9. Network device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to perform a method for acquiring control right of a multi-person environment gesture according to any one of claims 1 to 8.

10. Storage medium having stored thereon computer program instructions for implementing a method of multi-person environment gesture control right acquisition as claimed in any one of claims 1 to 8 when executed by a processor.

Images