CN109164915B - Gesture recognition method, device, system and equipment - Google Patents

Abstract

The present application discloses a gesture recognition method, device, system and device, wherein the method includes: 101. According to coordinate information corresponding to multiple scattering centers of a human hand sent by gesture radar received in real time, construct a human hand at the current moment 102. Execute step 101 in a loop until the coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar is not received within a preset time interval; 103. Determine different times The coordinate information of the preset scattering center on the virtual hand model of the hand, and connect the coordinate information of the preset scattering center at different times in time sequence to obtain the coordinate change trajectory of the preset scattering center. The scattering center is one of the multiple scattering centers; 104. Obtain the information to be input according to the coordinate change trajectory, and display the content corresponding to the information to be input according to the information to be input.

Description

A gesture recognition method, device, system and device

technical field

The present application relates to the technical field of gesture recognition, a gesture recognition method, apparatus, system and device.

Background technique

With the continuous development of mobile terminal devices and the emergence of virtual reality devices, human-computer interaction has become more and more important. As one of the important branches, gesture recognition has the advantages of adapting to people's living habits and high degree of freedom.

Most of the traditional gesture recognition technologies are based on cameras. However, these gesture recognition technologies have various shortcomings: the interaction method based on optical cameras needs to obtain a large amount of image data with different depths of field, and requires strong data processing capabilities to extract all the data. It needs information, which will take up a lot of hardware resources. At the same time, the optical camera cannot be blocked, and the user's privacy is also at risk of leakage; the shortcomings of the infrared camera are similar to that of the optical camera. interference. Therefore, radar-based human-computer interaction began to emerge, but at present, the human-computer interaction based on radar technology only supports the interactive control of simple gestures, and the stability is poor, the success rate of gesture recognition is low, and complex interactions cannot be performed, which makes the user experience poor. .

SUMMARY OF THE INVENTION

The embodiments of the present application provide a gesture recognition method, device, system and device, which are used for gesture recognition, and solve the problem that the current human-computer interaction equipment based on radar technology supports the interaction control of simple gestures, and has poor stability and low success rate of gesture recognition. , can not carry out complex interaction, making the user experience poor technical problems.

In view of this, a first aspect of the present application provides a gesture recognition method, including:

101. Construct a hand virtual model corresponding to the human hand at the current moment according to the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar received in real time;

106. Perform step 101 in a loop until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within a preset time interval;

103. Determine the coordinate information of the preset scattering centers on the hand virtual model at different times, and connect the coordinate information of the preset scattering centers at different times in a time sequence to obtain the coordinate change trajectory of the preset scattering centers , the preset scattering center is one of the multiple scattering centers;

104. Obtain information to be input according to the coordinate change trajectory, and display content corresponding to the information to be input according to the information to be input.

Preferably, the method further includes:

105. While receiving the coordinate information corresponding to each of the multiple scattering centers sent by the gesture radar, receive motion information corresponding to each of the multiple scattering centers sent by the gesture radar, where the motion information includes: velocity. information, acceleration information and orientation information;

The step 102 is specifically:

102. Repeat steps 101 and 105 until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within a preset time interval;

If the virtual hand model at the first moment has not been constructed, the determining the coordinate information of the preset scattering center on the virtual hand model at the first moment specifically includes:

determining the motion information of the preset scattering center on the hand virtual model at the second moment, and determining the preset scattering on the hand virtual model at the first moment according to the motion information at the second moment The coordinate information of the center, the second time is the previous time of the first time, and the first time is the time period formed from the time when step 101 is executed for the first time to the time when step 101 is executed for the last time. a moment.

Preferably, the information to be input is an image to be input;

The step 104 specifically includes:

104. Obtain the to-be-input image according to the coordinate change trajectory, and display the to-be-input image.

Preferably, the information to be input is text to be input;

The step 104 specifically includes:

104. Obtain the to-be-input text according to the coordinate change trajectory, compare the to-be-input text with a preset text library, obtain a text corresponding to the to-be-input text, and display the text.

A second aspect of the present application provides a gesture recognition device, including:

The model building unit is used for constructing a virtual hand model corresponding to the human hand at the current moment according to the coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar received in real time;

a first circulation unit, configured to repeatedly trigger the model construction unit until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within a preset time interval;

A trajectory determination unit, configured to determine the coordinate information of the preset scattering centers on the hand virtual model at different times, and connect the coordinate information of the preset scattering centers at different times in chronological order to obtain the preset scattering centers The coordinate change trajectory of , the preset scattering center is one of the plurality of scattering centers;

The display unit is configured to obtain the information to be input according to the coordinate change trajectory, and display the content corresponding to the information to be input according to the information to be input.

Preferably, the device further comprises:

A motion information acquisition unit, configured to receive the motion information corresponding to each of the plurality of scattering centers sent by the gesture radar while receiving the coordinate information corresponding to the plurality of scattering centers sent by the gesture radar, the Motion information includes: speed information, acceleration information and direction information;

The first circulation unit is specifically configured to repeatedly trigger the motion information acquisition unit and the model construction unit until the respective corresponding scattering centers of the human hand sent by the gesture radar are not received within a preset time interval. coordinate information;

If the virtual hand model at the first moment has not been constructed, the determining the coordinate information of the preset scattering center on the virtual hand model at the first moment specifically includes:

determining the motion information of the preset scattering center on the hand virtual model at the second moment, and determining the preset scattering on the hand virtual model at the first moment according to the motion information at the second moment The coordinate information of the center, the second time is the previous time of the first time, and the first time is the time from the time when the model construction unit is triggered for the first time to the time when the model construction unit is triggered for the last time. A moment in the composed time period.

Preferably, the information to be input is an image to be input;

The display unit is specifically configured to obtain the to-be-input image according to the coordinate change trajectory, and to display the to-be-input image.

Preferably, the information to be input is text to be input;

The display unit is specifically configured to obtain the text to be input according to the coordinate change trajectory, compare the text to be input with a preset text library, obtain the text corresponding to the text to be input, and display the text .

A third aspect of the present application provides a gesture recognition system, including: a gesture radar and the above gesture recognition device;

the gesture radar is connected in communication with the gesture recognition device;

The gesture radar is used to transmit radar signals to the human hand in real time;

The gesture radar is further configured to receive echo signals reflected by multiple scattering centers of the human hand, calculate the coordinate information corresponding to each scattering center according to each of the echo signals, and send the multiple scattering centers The coordinate information corresponding to each center is sent to the gesture recognition device.

A fourth aspect of the present application provides a gesture recognition device, the device includes a processor and a memory;

the memory is used to store program code and transmit the program code to the processor;

The processor is configured to execute the above gesture recognition method according to the instructions in the program code.

As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

In the embodiment of the present application, a gesture recognition method is provided, including: because the gesture radar transmits the coordinate information corresponding to the multiple scattering centers of the human hand in real time, it can be constructed according to the received coordinate information corresponding to the multiple scattering centers. The hand virtual model does not receive the coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar within the preset time interval, that is, the user's gesture control operation ends, and there are corresponding A hand virtual model, and then determine the coordinate change trajectory of the preset scattering center according to the coordinate information of the preset scattering center on the hand virtual model at different times. The information to be input can be determined according to the coordinate change trajectory, and finally the information to be input is determined according to the coordinate change trajectory. Display the content corresponding to the information of kangaroos. No matter what the user's hand inputs during the whole recognition process, the user's input content can be obtained accurately according to the coordinate change trajectory of the preset scattering center of the hand virtual model, which solves the current radar-based problem. The human-computer interaction of technology only supports the interactive control of simple gestures, and the stability is poor, the success rate of gesture recognition is low, and complex interactions cannot be performed, which makes the user experience poor technical problems.

Description of drawings

FIG. 1 is a schematic flowchart of a first embodiment of a gesture recognition method in an embodiment of the present application;

FIG. 2 is a schematic flowchart of a second embodiment of a gesture recognition method in an embodiment of the present application;

3 is a schematic structural diagram of an embodiment of a gesture recognition device in an embodiment of the present application;

FIG. 4 is a schematic structural diagram of an embodiment of a gesture recognition system according to an embodiment of the present application.

Detailed ways

The embodiments of the present application provide a gesture recognition method, device, system and device for gesture recognition, which solves the problem that the current human-computer interaction equipment based on radar technology only supports the interaction control of simple gestures, and has poor stability and a success rate of gesture recognition. Low, can not carry out complex interactions, making the user experience poor technical problems.

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Referring to FIG. 1, a schematic flowchart of a first embodiment of a gesture recognition method in an embodiment of the present application includes:

Step 101 , construct a hand virtual model corresponding to the human hand at the current moment according to the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar received in real time.

It should be noted that different parts of the human hand (such as fingers, back of the hand, etc.) have different echo signals to the gesture radar, that is, one echo signal corresponds to one hand part, according to the real-time received gesture radar. The coordinate information corresponding to each of the multiple scattering centers is used to construct a virtual hand model corresponding to the human hand at the current moment.

Step 102: Step 101 is executed cyclically until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within the preset time interval.

It should be noted that if the coordinate information of the multiple scattering centers of the human hand sent by the gesture radar is not received within the preset time interval, it means that the user's gesture control operation ends.

It can be understood that, the preset time interval can be set as required, which is not specifically limited here.

Step 103: Determine the coordinate information of the preset scattering centers on the hand virtual model at different times, and connect the coordinate information of the preset scattering centers at different times in time sequence to obtain the coordinate change trajectory of the preset scattering centers, and the preset scattering centers is one of multiple scattering centers.

It should be noted that, because the hand virtual model is established in real time, after determining the coordinate information of the preset scattering centers on the hand virtual model at different times, connect the coordinate information of the preset scattering centers at different times in chronological order to obtain The coordinate change trajectory of the preset scattering center is the movement change trajectory of the hand virtual model, that is, the coordinate change trajectory input by the user through gestures. It is understandable that the preset scattering center may be a point corresponding to the finger, and it is also understandable that a point corresponding to another part may also be set as the preset scattering center, which is specifically determined according to the user's input habits and the like.

Step 104: Obtain the information to be input according to the coordinate change trajectory, and display the content corresponding to the information to be input according to the information to be input.

In this embodiment, since the gesture radar transmits the coordinate information corresponding to the multiple scattering centers of the human hand in real time, a virtual hand model can be constructed according to the received coordinate information corresponding to the multiple scattering centers until the preset time interval. The coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar has not been received, that is, the user's gesture control operation has ended. The coordinate information of the preset scattering center on the hand virtual model is used to determine the coordinate change trajectory of the preset scattering center. The information to be input can be determined according to the coordinate change trajectory. Finally, the content corresponding to the information of the kangaroo is displayed according to the information to be input. The entire identification process No matter what the user's hand inputs, the user's input content can be accurately obtained according to the coordinate change trajectory of the preset scattering center of the hand virtual model, which solves the problem that the current human-computer interaction based on radar technology only supports the interaction of simple gestures. Control, poor stability, low success rate of gesture recognition, and inability to perform complex interactions, making the user experience poor technical problems.

The above is a first embodiment of a gesture recognition method provided by an embodiment of the present application, and the following is a second embodiment of a gesture recognition method provided by an embodiment of the present application.

Please refer to FIG. 2 , a schematic flowchart of a second embodiment of a gesture recognition method in an embodiment of the present application, including:

Step 201 , construct a hand virtual model corresponding to the human hand at the current moment according to the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar received in real time.

It should be noted that the content of step 201 is the same as that of step 101 in the first embodiment of the present application. For a specific description, please refer to the content of step 101 of the first embodiment, which will not be repeated here.

Step 202: While receiving the coordinate information corresponding to each of the multiple scattering centers sent by the gesture radar, receive motion information corresponding to each of the multiple scattering centers sent by the gesture radar, where the motion information includes speed information, acceleration information and direction information.

It should be noted that because the reflection of each part of the hand is weak, and because human beings are living organisms, the reflection intensity of each part is very unstable, and it is easy to lose the target, resulting in the failure of the hand model to be constructed. When the target is lost at one moment, that is, the virtual model of the hand at the first moment is not constructed, the coordinate information of the preset scattering center at this moment can be determined from the motion information at the previous moment.

Step 203: Steps 201 and 202 are executed cyclically until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within a preset time interval.

Step 204: If the virtual hand model at the first moment has not been constructed, determine the motion information of the preset scattering center on the virtual hand model at the second moment, and determine the virtual hand at the first moment according to the motion information at the second moment. The coordinate information of the scattering center is preset on the model, the second time is the previous time of the first time, and the first time is a time period consisting of the time when step 201 is performed for the first time to the time when step 201 is performed for the last time. time.

It should be noted that if the virtual model of the hand at the first moment is not constructed, because the position of the preset scattering center will not change suddenly, it will be near the position of the previous moment, and the movement direction has a high probability to continue along the previous movement direction. The movement speed is also gradually changed or unchanged. At this time, if the speed information, acceleration information and direction information at the previous moment relative to the first moment are known, the coordinate information of the preset scattering center at the first moment is determined. The preset scattering center is one of a plurality of scattering centers.

It can be understood that this embodiment only describes the determination of the coordinate information of the first moment according to the motion information of the moment before the first moment, and the determination of the first moment according to the motion information of the next moment of the first moment can also be used here. coordinate information. For a specific implementation process, reference may be made to the foregoing process, which is not repeated here.

Step 205 : Determine the coordinate information of the preset scattering centers on the hand virtual model at different times, connect the coordinate information of the preset scattering centers at different times in time sequence, and obtain the coordinate change trajectory of the preset scattering centers.

It should be noted that the time sequence is from front to back, but it can be understood that the time sequence may also be from back to front.

Step 206: Obtain the information to be input according to the coordinate change trajectory, and display the content corresponding to the information to be input according to the information to be input.

It should be noted that, when the information to be input is an image to be input, in order to diversify the image, the image to be input can be obtained directly according to the coordinate change trajectory, and the image to be input is displayed. It can be understood that because the virtual model of the hand is 3D, the corresponding image to be input at this time may be 2D or 3D, which is specifically determined according to the actual coordinate change trajectory. When the information to be input is the text to be input, the text to be input is obtained according to the coordinate change trajectory, the text to be input is compared with the preset text library, the text corresponding to the text to be input is obtained, and the text is displayed. It can be understood that the preset character library includes, but is not limited to, Chinese characters, English characters, numeric characters, and the like.

It can be understood that, after determining the speed information at each moment, such as inputting text or graphics, when the speed is fast, it corresponds to a thinner line, and when the speed is slow, it corresponds to a thicker line, which can restore the input content to the greatest extent. The specific implementation can be as follows: setting the preset diameter of the corresponding coordinate change trajectory at the preset speed, and then setting the coordinate change trajectory at the speed according to the ratio of different speeds to the preset speed.

In this embodiment, since the gesture radar transmits the coordinate information corresponding to the multiple scattering centers of the human hand in real time, a virtual hand model can be constructed according to the received coordinate information corresponding to the multiple scattering centers until the preset time interval. The coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar has not been received, that is, the user's gesture control operation has ended. The coordinate information of the preset scattering center on the hand virtual model is used to determine the coordinate change trajectory of the preset scattering center. The information to be input can be determined according to the coordinate change trajectory. Finally, the content corresponding to the information of the kangaroo is displayed according to the information to be input. The entire identification process No matter what the user's hand inputs, the user's input content can be accurately obtained according to the coordinate change trajectory of the preset scattering center of the hand virtual model, which solves the problem that the current human-computer interaction based on radar technology only supports the interaction of simple gestures. Control, poor stability, low success rate of gesture recognition, and inability to perform complex interactions, making the user experience poor technical problems.

The above is the second embodiment of a gesture recognition method provided by an embodiment of the present application, and the following is an embodiment of a gesture recognition device provided by an embodiment of the present application.

Please refer to FIG. 3 , which is a schematic structural diagram of an embodiment of a gesture recognition device in an embodiment of the present application, including:

The model building unit 301 is configured to construct a virtual hand model corresponding to the human hand at the current moment according to the coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar received in real time;

The first circulation unit 302 is used to repeatedly trigger the model construction unit 301 until the coordinate information corresponding to the multiple scattering centers of the human hand sent by the gesture radar is not received within the preset time interval;

The trajectory determination unit 303 is used to determine the coordinate information of the preset scattering centers on the hand virtual model at different times, and connect the coordinate information of the preset scattering centers at different times in a time sequence to obtain the coordinate change trajectory of the preset scattering centers, The preset scattering center is one of multiple scattering centers;

The display unit 304 is configured to obtain the information to be input according to the coordinate change trajectory, and display the content corresponding to the information to be input according to the information to be input.

Further, the device also includes:

The motion information acquisition unit 305 is configured to receive the motion information corresponding to each of the plurality of scattering centers sent by the gesture radar while receiving the coordinate information corresponding to each of the plurality of scattering centers sent by the gesture radar, and the motion information includes: speed information, acceleration information and orientation information;

The first circulation unit 302 is specifically used to repeatedly trigger the motion information acquisition unit 305 and the model construction unit 301, until the coordinate information corresponding to each of the multiple scattering centers of the human hand sent by the gesture radar is not received within the preset time interval;

If the virtual hand model at the first moment has not been constructed, determining the coordinate information of the preset scattering center on the virtual hand model at the first moment specifically includes:

Determine the motion information of the preset scattering center on the hand virtual model at the second moment, and determine the coordinate information of the preset scattering center on the hand virtual model at the first moment according to the motion information at the second moment, and the second moment is the first time. The moment before a moment, the first moment is a moment in the time period formed from the moment when the model construction unit is triggered for the first time to the moment when the model construction unit is triggered for the last time.

Further, the information to be input is an image to be input;

The display unit 304 is specifically configured to obtain the to-be-input image according to the coordinate change trajectory, and to display the to-be-input image.

Further, the information to be input is the text to be input;

The display unit 304 is specifically configured to obtain the text to be input according to the coordinate change track, compare the text to be input with a preset text library, obtain the text corresponding to the text to be input, and display the text. It can be understood that the preset character library includes, but is not limited to, Chinese characters, English characters, numeric characters, and the like.

The above is an embodiment of a gesture recognition apparatus provided by an embodiment of the present application, and the following is an embodiment of a gesture recognition system provided by an embodiment of the present application.

Please refer to FIG. 4 , which is a schematic structural diagram of a gesture recognition system in an embodiment of the present application, including: a gesture radar 401 and the gesture recognition device 402 in the third embodiment;

The gesture radar 401 is connected in communication with the gesture recognition device 402;

Gesture radar 401, used to transmit radar signals to human hands in real time;

The gesture radar 401 is also used for receiving echo signals corresponding to the reflections of multiple scattering centers of the human hand, calculating the coordinate information corresponding to each scattering center according to each echo signal, and sending the respective coordinate information corresponding to the multiple scattering centers to Gesture recognition device 402 .

It should be noted that the gesture radar 401 uses a linear frequency modulated continuous wave radar signal, and works in the V-band (55GHz-65GHz). The basic principle of chirp continuous wave radar is to mix the transmitted signal and the echo signal to obtain a difference frequency signal, and the difference frequency signal can be processed and analyzed to obtain the relative distance, relative angle and relative speed. Get coordinate information. It can be understood that the gesture radar 401 is a module, which can be directly installed in a gesture recognition device, such as a TV set or a mobile phone; it can also be made into an external module and connected to the gesture recognition device through USB. At the same time, it can be understood that the personnel do not need to wear anything when operating, and they only need to operate with bare hands, and only need to be within the detectable range of the gesture radar 401 . It can be understood that, in order to obtain the angle information of the target, the gesture radar can be set to have multiple receiving channels.

An embodiment of the present application also provides a gesture recognition device, which includes a processor and a memory: the memory is used to store program codes, and transmit the program codes to the processor, and the processor is used to execute the foregoing implementations according to instructions in the program codes Examples of gesture recognition methods, thereby performing various functional applications as well as data processing.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

The terms "first", "second", "third", "fourth", etc. (if any) in the description of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the application described herein can, for example, be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

It should be understood that, in this application, "at least one (item)" refers to one or more, and "a plurality" refers to two or more. "And/or" is used to describe the relationship between related objects, indicating that there can be three kinds of relationships, for example, "A and/or B" can mean: only A, only B, and both A and B exist , where A and B can be singular or plural. The character "/" generally indicates that the associated objects are an "or" relationship. "At least one item(s) below" or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (a) of a, b or c, can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c" ", where a, b, c can be single or multiple.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a readable storage medium. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art, or all or part of the technical solution, and the software product is stored in a storage medium, Several instructions are included to cause a device (which may be a person, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (full English name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic Various media that can store program codes, such as discs or optical discs.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (8)

1. A gesture recognition method, comprising:

101. according to the coordinate information which is sent by the gesture radar and corresponds to the plurality of scattering centers of the human hand and received in real time, a hand virtual model corresponding to the human hand at the current moment is built;

102. step 101 is executed in a circulating manner until coordinate information which is sent by the gesture radar and corresponds to each of the plurality of scattering centers of the human hand is not received within a preset time interval;

103. determining coordinate information of preset scattering centers on the hand virtual model at different moments, and connecting the coordinate information of the preset scattering centers at different moments according to a time sequence to obtain a coordinate change track of the preset scattering centers, wherein the preset scattering centers are one of the scattering centers;

104. obtaining information to be input according to the coordinate change track, and displaying the content corresponding to the information to be input according to the information to be input;

the method further comprises the following steps: 105;

105. receiving, while receiving the coordinate information, sent by the gesture radar, corresponding to each of the plurality of scattering centers, motion information, sent by the gesture radar, corresponding to each of the plurality of scattering centers, where the motion information includes: speed information, acceleration information, and direction information;

the step 102 specifically includes:

102. circularly executing the steps 101 and 105 until coordinate information which is sent by the gesture radar and corresponds to each of the plurality of scattering centers of the human hand is not received within a preset time interval;

if the virtual hand model at the first moment is not constructed, determining coordinate information of a preset scattering center on the virtual hand model at the first moment, specifically comprising:

and determining motion information of the preset scattering center on the virtual hand model at a second moment, and determining coordinate information of the preset scattering center on the virtual hand model at the first moment according to the motion information at the second moment, wherein the second moment is a previous moment of the first moment, and the first moment is a moment in a time period from the moment of executing the step 101 for the first time to the moment of executing the step 101 for the last time.

2. The method according to claim 1, wherein the information to be input is an image to be input;

the step 104 specifically includes:

104. and obtaining the image to be input according to the coordinate change track, and displaying the image to be input.

3. The method according to claim 1, wherein the information to be input is a text to be input;

the step 104 specifically includes:

104. and obtaining the characters to be input according to the coordinate change track, comparing the characters to be input with a preset character library to obtain characters corresponding to the characters to be input, and displaying the characters.

4. A gesture recognition apparatus, comprising:

the model building unit is used for building a hand virtual model corresponding to the human hand at the current moment according to the real-time received coordinate information corresponding to the plurality of scattering centers of the human hand and sent by the gesture radar;

the first circulation unit is used for repeatedly triggering the model construction unit until coordinate information which is sent by the gesture radar and corresponds to each of the plurality of scattering centers of the human hand is not received within a preset time interval;

the trajectory determining unit is used for determining coordinate information of preset scattering centers on the hand virtual model at different moments, and connecting the coordinate information of the preset scattering centers at different moments according to a time sequence to obtain a coordinate change trajectory of the preset scattering centers, wherein the preset scattering center is one of the scattering centers;

the display unit is used for obtaining information to be input according to the coordinate change track and displaying the content corresponding to the information to be input according to the information to be input;

the device further comprises:

a motion information obtaining unit, configured to receive, while receiving the coordinate information, sent by the gesture radar, corresponding to each of the multiple scattering centers, motion information, sent by the gesture radar, corresponding to each of the multiple scattering centers, where the motion information includes: speed information, acceleration information, and direction information;

the first circulation unit is specifically used for repeatedly triggering the motion information acquisition unit and the model construction unit until coordinate information which is sent by the gesture radar and corresponds to the plurality of scattering centers of the human hand is not received within a preset time interval; if the virtual hand model at the first moment is not constructed, determining coordinate information of a preset scattering center on the virtual hand model at the first moment, specifically comprising:

and determining the motion information of the preset scattering center on the hand virtual model at a second moment, and determining the coordinate information of the preset scattering center on the hand virtual model at the first moment according to the motion information at the second moment, wherein the second moment is a previous moment of the first moment, and the first moment is a moment in a time period formed by a moment from the moment of triggering the model construction unit for the first time to the moment of triggering the model construction unit for the last time.

5. The apparatus according to claim 4, wherein the information to be input is an image to be input;

the display unit is specifically configured to obtain the image to be input according to the coordinate change trajectory and display the image to be input.

6. The device of claim 4, wherein the information to be input is a text to be input;

the display unit is specifically configured to obtain the characters to be input according to the coordinate change trajectory, compare the characters to be input with a preset character library to obtain characters corresponding to the characters to be input, and display the characters.

7. A gesture recognition system, comprising: a gesture radar and a gesture recognition apparatus according to any one of the preceding claims 4 to 6;

the gesture radar is in communication connection with the gesture recognition device; the gesture radar is used for transmitting a radar signal to the hand of the human body in real time; the gesture radar is further configured to receive echo signals reflected by a plurality of scattering centers of the human hand correspondingly, calculate coordinate information corresponding to each scattering center according to each echo signal, and send the coordinate information corresponding to each scattering center to the gesture recognition device.

8. A gesture recognition device, the device comprising a processor and a memory;

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to perform the gesture recognition method of any one of claims 1 to 3 according to instructions in the program code.

Images