Gesture recognition method, system, computer device and readable storage medium

Abstract

The application provides a gesture recognition method, comprising collecting multiple echo intermediate frequency data sent by a microwave sensor; pre-processing the multiple echo intermediate frequency data to obtain multiple target echo intermediate frequency data; performing fast Fourier transform on the multiple target echo intermediate frequency data to calculate multiple frequency data corresponding to the multiple target echo intermediate frequency data and energy values associated with each frequency data; judging whether to trigger gesture recognition according to the energy values; if gesture recognition is triggered, obtaining to-be-recognized data and obtaining a gesture classification result according to the to-be-recognized data. The application performs gesture recognition through a microwave sensor, effectively improves detection efficiency by using the high-resolution characteristics of the microwave sensor, and effectively improves gesture recognition accuracy by performing twice detection on a to-be-detected object according to the judgment of whether to trigger gesture recognition and the judgment of gesture classification recognition.

Description

Technical Field

[0001] The present invention relates to the field of sensor detection technology, and in particular to a gesture recognition method, system, computer device and computer-readable storage medium. Background Technology

[0002] Gesture recognition, as an important component of human-computer interaction, is widely used in fields such as smart homes and mechanical control. Its research and development affects the naturalness and flexibility of human-computer interaction.

[0003] In wireless gesture recognition, infrared sensors are mainly used to collect signals for gesture recognition. However, gesture recognition methods using infrared sensors have high power consumption, large computational load, and are easily affected by environmental factors such as lighting and obstructions, resulting in low detection efficiency and low gesture recognition accuracy. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a gesture recognition method, system, computer device, and computer-readable storage medium to solve the problems of low detection efficiency and low gesture recognition accuracy of gesture recognition methods using infrared sensing technology.

[0005] The present invention solves the above-mentioned technical problems through the following technical solutions:

[0006] One aspect of the present invention provides a gesture recognition method, comprising:

[0007] Multiple echo intermediate frequency data transmitted by a microwave sensor are collected, wherein the multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor;

[0008] The multiple echo intermediate frequency data are preprocessed to obtain multiple target echo intermediate frequency data;

[0009] A fast Fourier transform is performed on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the intermediate frequency data of the multiple target echoes. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data.

[0010] Determine whether the energy value meets the gesture recognition trigger condition;

[0011] If the energy value meets the gesture recognition trigger condition, a gesture recognition trigger command is generated;

[0012] Based on the gesture recognition trigger command, data to be recognized is acquired, wherein the data to be recognized includes the energy value to be recognized corresponding to the target frequency data, and the target frequency data is the frequency data in the frequency domain data that is greater than a preset frequency threshold; and

[0013] The gesture classification result is obtained based on the data to be identified.

[0014] Optionally, determining whether the energy value meets the gesture recognition trigger condition includes:

[0015] Determine whether any of the energy values ​​exceeds a preset trigger threshold;

[0016] Correspondingly,

[0017] If any of the energy values ​​is greater than the preset trigger threshold, then the gesture recognition trigger command is generated.

[0018] Optionally, the gesture classification result includes a target gesture result, which indicates that the object to be identified is located within a target area; obtaining the gesture classification result based on the data to be identified includes:

[0019] Within a preset time period, determine whether the data to be identified meets the gesture classification and recognition conditions; and

[0020] If the data to be identified meets the gesture classification and recognition conditions, then the target gesture result is generated.

[0021] Optionally, determining whether the data to be identified meets the gesture classification and recognition conditions within a preset time period includes:

[0022] Determine if there is an energy value to be identified that is greater than a preset identification threshold;

[0023] Correspondingly,

[0024] If there is an energy value to be identified that is greater than the preset recognition threshold, then the target gesture result is generated.

[0025] Optionally, the preprocessing of the plurality of echo intermediate frequency data to obtain plurality of target echo intermediate frequency data includes:

[0026] Calculate the average value of the multiple echo intermediate frequency data;

[0027] Calculate the difference between the plurality of echo intermediate frequency data and the average value to obtain plurality of first echo intermediate frequency data; and

[0028] Windowing is applied to the plurality of first echo intermediate frequency data to obtain the plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data.

[0029] Optionally, the step of windowing the plurality of first echo intermediate frequency data to obtain the plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data includes:

[0030] The products of the plurality of first echo intermediate frequency data and the preset function are calculated respectively to obtain the plurality of target echo intermediate frequency data.

[0031] Optionally, the microwave sensor acquires the plurality of echo intermediate frequency data at a sampling frequency of 315Hz.

[0032] Another aspect of the present invention provides a gesture recognition system, the system comprising:

[0033] The acquisition module is used to acquire multiple echo intermediate frequency data sent by the microwave sensor, wherein the multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor;

[0034] The preprocessing module is used to preprocess the multiple echo intermediate frequency data to obtain multiple target echo intermediate frequency data;

[0035] The calculation module is used to perform a fast Fourier transform on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the intermediate frequency data of the multiple target echoes. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data.

[0036] The trigger judgment module is used to determine whether the energy value meets the gesture recognition trigger condition;

[0037] The generation module is used to generate a gesture recognition trigger command if the energy value meets the gesture recognition trigger condition.

[0038] The recognition module is used to acquire data to be recognized based on the gesture recognition trigger command, wherein the data to be recognized includes the energy value to be recognized corresponding to target frequency data, and the target frequency data is frequency data in the frequency domain data that is greater than a preset frequency threshold; and

[0039] The classification module is used to obtain gesture classification results based on the data to be identified.

[0040] Another aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the gesture recognition method described above.

[0041] Another aspect of the present invention provides a computer-readable storage medium including a memory, a processor, and a computer program stored on the memory and executable on at least one processor, wherein the at least one processor executes the computer program to implement the steps of the gesture recognition method described above.

[0042] The gesture recognition method, system, computer device, and computer-readable storage medium provided in this invention calculate multiple frequency data corresponding to the multiple target echo intermediate frequency data and the energy value associated with each frequency data by performing a Fast Fourier Transform on the multiple target echo intermediate frequency data; determine whether gesture recognition is triggered based on the energy value; if gesture recognition is triggered, acquire the data to be recognized and obtain the gesture classification result based on the data to be recognized; perform gesture recognition using a microwave sensor, utilizing the high resolution characteristics of the microwave sensor to effectively improve detection efficiency; and perform two detections on the object to be tested based on the determination of whether gesture recognition is triggered and the determination of gesture classification recognition, effectively improving gesture recognition accuracy.

[0043] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the present invention. Attached Figure Description

[0044] Figure 1 An example flowchart of a gesture recognition method according to an embodiment of the present invention is illustrated schematically;

[0045] Figure 2 This illustration shows an example flowchart of the preprocessing of the plurality of echo intermediate frequency data in the gesture recognition method of this invention.

[0046] Figure 3 This illustration shows an example flowchart of determining whether gesture recognition is triggered in the gesture recognition method of this embodiment of the invention;

[0047] Figure 4 This illustration shows an example flowchart of performing gesture recognition classification in the gesture recognition method of this invention.

[0048] Figure 5 This illustration shows an example flowchart of performing gesture recognition classification in the gesture recognition method of this invention.

[0049] Figure 6 A block diagram of a gesture recognition system according to Embodiment 2 of the present invention is shown schematically; and

[0050] Figure 7 The schematic diagram illustrates a hardware architecture of a computer device suitable for implementing a gesture recognition method according to Embodiment 3 of the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0052] It should be noted that the descriptions involving "first," "second," etc., in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0053] In the description of this invention, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are performed, but are only used to facilitate the description of this invention and to distinguish each step, and therefore should not be construed as a limitation of this invention.

[0054] Example 1

[0055] Please see Figure 1 This document illustrates a flowchart of the gesture recognition method according to an embodiment of the present invention. It is understood that the flowchart in this embodiment is not intended to limit the order of the execution steps. The following description uses a computer device as the execution subject, as detailed below:

[0056] like Figure 1 As shown, the gesture recognition method may include steps S100 to S112, wherein:

[0057] Step S100: Collect multiple echo intermediate frequency data sent by the microwave sensor through the ADC controller. The multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor.

[0058] The echo intermediate frequency data is the waveform obtained by the microwave sensor (i.e., radar) emitting an electromagnetic wave at a fixed transmission frequency, reflecting it back from the object under test (such as a human hand), and receiving it. The mixing formula is: If 混 = sin[(ω1-ω2)], where: ω1 is the transmit frequency, ω2 is the receive frequency, If 混This is represented as the waveform signal corresponding to the echo intermediate frequency data. Since microwave sensors work by detecting moving objects, they cannot detect stationary objects. Therefore, the echo intermediate frequency signal reflects the velocity reflected back by the object being measured.

[0059] Currently, infrared sensors are commonly used for speed detection in the market. However, infrared sensors can only detect a single point or a certain angle range, resulting in a small detection range and low efficiency. Furthermore, they cannot detect objects under strong light or high temperatures, leading to limited applicability and practicality. In contrast to existing infrared sensor technologies, the microwave sensor used in this invention offers the following advantages: a large detection range; an aesthetically pleasing design; easy installation without requiring additional hardware; high detection efficiency; strong applicability; high practicality; high integration; small size; low power consumption; and low cost.

[0060] In an exemplary embodiment, to ensure the integrity of the sampled data, the microwave sensor acquires the multiple echo intermediate frequency data at a sampling frequency of 315Hz. To improve the frequency resolution while ensuring the integrity of the sampled data, the number of sampling points is set to 32, and the frequency resolution is set to 9.84375.

[0061] Step S102: Preprocess the multiple echo intermediate frequency data to obtain multiple target echo intermediate frequency data.

[0062] To present the data more clearly and analyze it more efficiently, this embodiment preprocesses the acquired multiple echo intermediate frequency data by removing DC and applying a window (such as a Hanning window). Windowing the acquired data reduces spectral leakage. Please refer to [link to relevant documentation]. Figure 2 The preprocessing of the plurality of echo intermediate frequency data to obtain a plurality of target echo intermediate frequency data includes: step S200, calculating the average value of the plurality of echo intermediate frequency data; step S202, calculating the difference between the plurality of echo intermediate frequency data and the average value to obtain a plurality of first echo intermediate frequency data; and step S204, windowing the plurality of first echo intermediate frequency data to obtain the plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data.

[0063] For example, since the DC signal is a fixed value, it is necessary to sum multiple echo intermediate frequency (IF) data points to obtain the total sum of the echo IF data. Then, the ratio of the total sum of the echo IF data points to the number of echo IF data points acquired in this acquisition is calculated. The difference between each echo IF data point and the ratio is calculated for each echo IF data point to obtain multiple first echo IF data points. The first echo IF data points can be calculated using the following formula:

[0064]

[0065] In this formula, x k The y represents the acquired echo intermediate frequency (IF) data, where N is the number of echo IF data points acquired in this study; k This is the intermediate frequency data for the first echo.

[0066] For example, the step of windowing the plurality of first echo intermediate frequency (IF) data to obtain the plurality of target echo IF data corresponding to the plurality of first echo IF data can also be achieved through the following operation: calculating the product of each of the plurality of first echo IF data with a preset function to obtain the plurality of target echo IF data. For instance, applying a Hanning window to the plurality of first echo IF data can be understood as multiplying each first echo IF data by a preset function to obtain the product corresponding to each first echo IF data, i.e., the target echo IF data. The target echo IF data can be calculated using the following formula:

[0067]

[0068] In this formula, x k This represents the first echo intermediate frequency (IF) data, where N is the number of echo IF data points acquired in this study; y k For target echo intermediate frequency data.

[0069] Step S104: Perform a fast Fourier transform on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the intermediate frequency data of the multiple target echoes. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data.

[0070] In an exemplary embodiment, the velocity components and energy values ​​of multiple target echo intermediate frequency data, along with the frequency data associated with the energy values, are calculated using a Fast Fourier Transform (FFT). In the FFT, the spacing between adjacent spectral lines is:

[0071]

[0072] Where: fs is the sampling frequency, and the spectral line spacing determines the frequency resolution d of the FFT. f When the spectral line spacing is large, useful information will be lost due to the picket fence effect. Therefore, in this embodiment of the invention, the sampling frequency of the microwave sensor is set to 315 Hz, and the number of sampling points is set to 32, so the frequency resolution is set to:

[0073] According to the Doppler effect, the corresponding formula is: Among them, f D: Doppler frequency or difference frequency; f0: radar transmission frequency; v: velocity range of the object under test; c0: speed of light; α: angle between the actual direction of motion of the object under test and the line connecting the microwave sensor and the object under test.

[0074] For example, using the formula corresponding to the Doppler effect, it can be calculated that when the target echo intermediate frequency signal outputs a 38.6Hz sine wave, the Doppler velocity is 1m / s. Combining this with frequency resolution, the following can be calculated: This can be understood as the frequency resolution of a velocity component corresponding to the intermediate frequency data of the target echo being 0.255 m / s.

[0075] Step S106: Determine whether the energy value meets the gesture recognition trigger condition.

[0076] In this invention, after data sampling and performing a Fast Fourier Transform (FFT), the transformed data needs to be analyzed and judged for subsequent detection. Taking a smart water dispenser as an example, the smart water dispenser includes the microwave sensor, the object to be measured is a person, and the gesture recognition method is used to identify whether a person intends to place a water cup at the target location of the smart water dispenser based on their gestures. To save the energy consumption of the computer equipment, before identifying whether a person intends to place a water cup at the target location of the smart water dispenser based on their gestures, a gesture recognition trigger condition can be set in the method. This gesture recognition trigger condition is used to determine whether someone is approaching the smart water dispenser, triggering gesture recognition; otherwise, gesture recognition is not triggered, thus saving computer equipment resources.

[0077] Step S108: If the energy value meets the gesture recognition trigger condition, then generate a gesture recognition trigger command.

[0078] To save on computer resources, please refer to Figure 3The execution of the gesture recognition trigger operation may further include steps S300 to S302, wherein: step S300, determining whether any energy value among the energy values ​​is greater than a preset trigger threshold; step S302, if any energy value among the energy values ​​is greater than the preset trigger threshold, generating the gesture recognition trigger command. In this embodiment, the preset trigger threshold is set to 400. If any energy value among the energy values ​​is greater than 400, it is determined that the object to be tested is within the target distance of the microwave sensor, where the target distance is the distance between the microwave sensor and the object to be tested. Taking a smart water dispenser as an example, the target distance can be set to 1 meter. If any energy value among the energy values ​​is greater than 400, it is considered that someone is approaching the target distance of the smart water dispenser, and a gesture recognition trigger command is generated to enable the computer device to perform gesture recognition and classification on the object to be tested. Taking a smart water dispenser as an example, it can be understood that when a person is within the target distance of the smart water dispenser, the gesture recognition operation is triggered, wherein the preset distance includes all distances radiating outward from the front of the smart water dispenser by 1 meter as the endpoint.

[0079] Step S110: Based on the gesture recognition trigger command, obtain the data to be recognized, wherein the data to be recognized includes the energy value to be recognized corresponding to the target frequency data, and the target frequency data is the frequency data in the frequency domain data that is greater than a preset frequency threshold.

[0080] In this embodiment, the preset frequency threshold can be set to 70Hz. The energy value corresponding to frequency data greater than 70Hz is the energy value to be identified, i.e., the data to be identified.

[0081] Step S112: Obtain gesture classification results based on the data to be identified.

[0082] In this invention, by analyzing the data to be identified, a gesture classification result can be quickly generated based on the current hand gesture movement of the object under test; this facilitates a response from the computer device based on the gesture classification result. The gesture classification result includes a target gesture result, which indicates that the object under test is located within a target area; to enable rapid gesture recognition and classification and improve detection efficiency; please refer to... Figure 4The gesture recognition and classification operation may include the following steps S400-S402, wherein: step S400, within a preset time, it is determined whether the data to be recognized meets the gesture classification and recognition conditions; and step S402, if the data to be recognized meets the gesture classification and recognition conditions, the target gesture result is generated. In this embodiment, the target gesture result indicates that the object to be tested is detected in the target area. Taking a smart water dispenser as an example, after the target gesture result is generated within the preset time, the computer device can control the smart water dispenser's water dispensing button to unlock, putting the water dispensing button in a triggered state. If the water dispensing button is not triggered within the preset trigger time (e.g., 30 seconds), steps S100-S108 are re-entered. The gesture classification result also includes a non-target gesture result, which indicates that the object to be tested is not detected in the target area. If the data to be recognized does not meet the gesture classification and recognition conditions, the object to be tested is not detected in the target area, and steps S100-S108 are re-entered.

[0083] To improve detection efficiency, in an exemplary embodiment, the gesture classification and recognition condition is to determine whether the energy value to be recognized is greater than a preset recognition threshold; please refer to... Figure 5 The recognition and classification of gestures can be achieved through the following steps: Step S500, determining whether there is a target energy value greater than a preset recognition threshold; Step S502, if there is a target energy value greater than the preset recognition threshold, then generating the target gesture result. In this embodiment, the preset recognition threshold can be set to 80. If there is a target energy value greater than 80, and the calculated physical velocity of the object being tested is higher than 1.2 m / s, then a target gesture result is generated. Taking a smart water dispenser as an example, the target gesture result is represented by the object being tested holding a cup and being located within the target area.

[0084] In other exemplary embodiments, the gesture recognition method can also be applied to smart IoT home scenarios such as smart toilets.

[0085] The gesture recognition scheme based on microwave sensors in this embodiment of the invention has at least the following beneficial effects:

[0086] (1) It is not sensitive to changes in the environment and can be used in dim light, strong light and other occasions; it has strong anti-interference ability and can support all-weather operation;

[0087] (2) By capturing motion gestures within its field of view using microwave sensors, the computational complexity of computer equipment is reduced and the detection efficiency is improved;

[0088] (3) Based on the high resolution characteristics of microwave sensors, the accuracy of gesture recognition is effectively increased;

[0089] (4) Based on the gesture recognition trigger conditions and gesture classification recognition conditions, the object to be tested is detected twice, which effectively improves the gesture recognition accuracy.

[0090] Example 2

[0091] Please continue reading. Figure 6 This diagram illustrates the program modules of a gesture recognition system 60 according to an embodiment of the present invention. In this embodiment, the gesture recognition system 60 may include or be divided into one or more program modules. One or more program modules are stored in an embedded memory chip and executed by one or more processors to complete the present invention and implement the aforementioned gesture recognition method. The program module referred to in this embodiment of the present invention refers to a series of computer program instruction segments capable of performing a specific function, which is more suitable than the program itself for describing the execution process of the gesture recognition system 60 in the storage medium. The following description will specifically introduce the functions of each program module in this embodiment:

[0092] The system includes: a data acquisition module 600, a preprocessing module 602, a calculation module 604, a trigger judgment module 606, a generation module 608, a recognition module 610, and a classification module 612, wherein:

[0093] The acquisition module 600 is used to acquire multiple echo intermediate frequency data sent by the microwave sensor, wherein the multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor.

[0094] Preprocessing module 602 is used to preprocess the plurality of echo intermediate frequency data to obtain plurality of target echo intermediate frequency data;

[0095] The calculation module 604 is used to perform a fast Fourier transform on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the intermediate frequency data of the multiple target echoes. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data.

[0096] Trigger judgment module 606 is used to determine whether the energy value meets the gesture recognition trigger condition;

[0097] The generation module 608 is used to generate a gesture recognition trigger command if the energy value meets the gesture recognition trigger condition.

[0098] The recognition module 610 is used to acquire data to be recognized based on the gesture recognition trigger command, wherein the data to be recognized includes an energy value to be recognized corresponding to target frequency data, and the target frequency data is frequency data in the frequency domain data that is greater than a preset frequency threshold; and

[0099] The classification module 612 is used to obtain the gesture classification result based on the data to be identified.

[0100] In an exemplary embodiment, the trigger judgment module 606 is further configured to determine whether any energy value in the energy values ​​is greater than a preset trigger threshold; correspondingly, the generation module 608 is further configured to generate the gesture recognition trigger command if any energy value in the energy values ​​is greater than the preset trigger threshold.

[0101] In an exemplary embodiment, the gesture classification result includes a target gesture result, which indicates that the object to be tested is located within a target area; the classification module 612 is further configured to: determine whether the data to be identified meets the gesture classification recognition conditions within a preset time; and if the data to be identified meets the gesture classification recognition conditions, generate a target gesture result.

[0102] In an exemplary embodiment, the classification module 612 is further configured to: determine whether there is an energy value to be identified that is greater than a preset identification threshold; if there is an energy value to be identified that is greater than the preset identification threshold, then generate the target gesture result.

[0103] In an exemplary embodiment, the preprocessing module 602 is further configured to: calculate the average value of the plurality of echo intermediate frequency data; calculate the difference between the plurality of echo intermediate frequency data and the average value respectively to obtain a plurality of first echo intermediate frequency data; and window the plurality of first echo intermediate frequency data to obtain a plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data.

[0104] In an exemplary embodiment, the preprocessing module 602 is further configured to: calculate the product of the plurality of first echo intermediate frequency data and a preset function respectively, so as to obtain the plurality of target echo intermediate frequency data.

[0105] In an exemplary embodiment, the microwave sensor acquires the plurality of echo intermediate frequency data at a sampling frequency of 315 Hz.

[0106] Example 3

[0107] Figure 7 This diagram schematically illustrates the hardware architecture of a computer device 10000 suitable for implementing a gesture recognition method according to Embodiment 3 of the present invention. In this embodiment, the computer device 10000 is a device capable of automatically performing score calculations and / or information processing according to pre-set or stored instructions. For example, it may be a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server, or cabinet server (including independent servers or server clusters composed of multiple servers), gateway, etc. Figure 7As shown, the computer device 10000 includes, but is not limited to, at least the following: a memory 10010, a processor 10020, and a network interface 10030 that can communicate and be linked to each other via a system bus. Wherein:

[0108] The memory 10010 includes at least one type of computer-readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 10000. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is typically used to store the operating system and various application software installed on the computer device 10000, such as the program code for gesture recognition methods. In addition, the memory 10010 can also be used to temporarily store various types of data that have been output or will be output.

[0109] In some embodiments, processor 10020 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. Processor 10020 is typically used to control the overall operation of computer device 10000, such as performing control and processing related to data interaction or communication with computer device 10000. In this embodiment, processor 10020 is used to run program code stored in memory 10010 or process data.

[0110] Network interface 10030 may include a wireless network interface or a wired network interface, which is typically used to establish a communication link between computer device 10000 and other computer devices. For example, network interface 10030 is used to connect computer device 10000 to an external terminal via a network, establishing a data transmission channel and communication link between computer device 10000 and the external terminal. The network may be an intranet, the Internet, Global System for Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, or other wireless or wired networks.

[0111] It should be pointed out that, Figure 7 Only computer devices with components 10010-10030 are shown; however, it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.

[0112] In this embodiment, the gesture recognition method stored in memory 10010 can be further divided into one or more program modules and executed by a processor (processor 10020 in this embodiment) to complete the embodiment of the present invention.

[0113] Example 4

[0114] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by at least one processor, implements the steps of the gesture recognition method in the embodiments.

[0115] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device. Of course, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the gesture recognition method in this embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

[0116] Obviously, those skilled in the art should understand that the modules or steps of the above-described embodiments of the present invention can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of the present invention are not limited to any particular hardware and software combination.

[0117] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A gesture recognition method, characterized in that, include: Multiple echo intermediate frequency data transmitted by a microwave sensor are collected, wherein the multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor; The multiple echo intermediate frequency data are preprocessed to obtain multiple target echo intermediate frequency data; A fast Fourier transform is performed on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the multiple target echo intermediate frequency data. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data. Determine whether the energy value meets the gesture recognition trigger condition; If the energy value meets the gesture recognition trigger condition, a gesture recognition trigger command is generated; Based on the gesture recognition trigger command, data to be recognized is obtained, wherein the data to be recognized includes the energy value to be recognized corresponding to the target frequency data, and the target frequency data is the frequency data in the frequency domain data that is greater than a preset frequency threshold; and Based on the data to be identified, a gesture classification result is obtained. The gesture classification result includes a target gesture result, which indicates that the object to be identified is located within a target area. The step of determining whether the energy value meets the gesture recognition trigger condition includes: Determine whether any of the energy values ​​exceeds a preset trigger threshold; Correspondingly, If any of the energy values ​​is greater than the preset trigger threshold, the object under test is determined to be within the target distance of the microwave sensor, and the gesture recognition trigger command is generated. The process of obtaining gesture classification results based on the data to be identified includes: Within a preset time period, determine whether there is an energy value to be identified that is greater than a preset identification threshold; If there is an energy value to be identified that is greater than the preset recognition threshold, then the target gesture result is generated.

2. The gesture recognition method according to claim 1, characterized in that, The preprocessing of the plurality of echo intermediate frequency data to obtain plurality of target echo intermediate frequency data includes: Calculate the average value of the multiple echo intermediate frequency data; Calculate the difference between the plurality of echo intermediate frequency data and the average value to obtain plurality of first echo intermediate frequency data; and Windowing is applied to the plurality of first echo intermediate frequency data to obtain the plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data.

3. The gesture recognition method according to claim 2, characterized in that, The step of windowing the plurality of first echo intermediate frequency data to obtain the plurality of target echo intermediate frequency data corresponding to the plurality of first echo intermediate frequency data includes: The products of the plurality of first echo intermediate frequency data and the preset function are calculated respectively to obtain the plurality of target echo intermediate frequency data.

4. The gesture recognition method according to claim 1, characterized in that, The microwave sensor acquires the multiple echo intermediate frequency data at a sampling frequency of 315Hz.

5. A gesture recognition system, characterized in that, The system includes: The acquisition module is used to acquire multiple echo intermediate frequency data sent by the microwave sensor, wherein the multiple echo intermediate frequency data are signals reflected by the object under test and received by the microwave sensor; The preprocessing module is used to preprocess the multiple echo intermediate frequency data to obtain multiple target echo intermediate frequency data; The calculation module is used to perform a fast Fourier transform on the intermediate frequency data of the multiple target echoes to calculate the frequency domain data corresponding to the intermediate frequency data of the multiple target echoes. The frequency domain data includes multiple frequency data and the energy value associated with each frequency data. The trigger judgment module is used to determine whether the energy value meets the gesture recognition trigger condition; it is also used to determine whether any energy value is greater than a preset trigger threshold. The generation module is configured to generate a gesture recognition trigger command if the energy value meets the gesture recognition trigger condition; and is also configured to: determine that the object to be tested is within the target distance of the microwave sensor and generate the gesture recognition trigger command if any energy value is greater than the preset trigger threshold. The recognition module is used to acquire data to be recognized based on the gesture recognition trigger command, wherein the data to be recognized includes the energy value to be recognized corresponding to target frequency data, and the target frequency data is frequency data in the frequency domain data that is greater than a preset frequency threshold; and The classification module is used to obtain a gesture classification result based on the data to be identified, the gesture classification result including a target gesture result, the target gesture result indicating that the object to be identified is located within a target area; it is also used to: determine whether there is a target energy value greater than a preset recognition threshold within a preset time; if there is a target energy value greater than the preset recognition threshold, then generate the target gesture result.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the gesture recognition method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, It contains a computer program that can be executed by at least one processor to perform the steps of the gesture recognition method according to any one of claims 1 to 4.

Images