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

Abstract

The invention discloses a gesture recognition method, device and equipment and a computer readable storage medium, and relates to the technical field of gesture interaction.The gesture recognition method comprises the steps that user motion information is acquired; identifying a user motion scene according to the user motion information; and according to the user motion scene, updating a gesture recognition threshold value of a preset gesture recognition model, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold value. The technical problem that the success rate of gesture recognition is low due to the fact that a current gesture recognition method is difficult to adapt to different scenes is solved.

Description

Technical Field

[0001] The present application relates to the field of gesture interaction technology, and in particular to a gesture recognition method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of computer, electronic information technology and artificial intelligence technology, gesture interaction technology as an important input control method has gradually gained more and more attention in different industries such as industry, security, and education.

[0003] Gesture recognition is a key technical point of gesture interaction technology. Currently, gesture recognition models usually set corresponding gesture recognition thresholds to determine whether the collected user gesture information matches the preset gesture, thereby identifying the preset gesture corresponding to the user gesture information. However, in real scenarios, user gestures are affected by various environmental factors, and fixed gesture recognition thresholds are difficult to adapt to different scenarios, resulting in a low success rate of gesture recognition. Summary of the invention

[0004] The main purpose of the present application is to provide a gesture recognition method, apparatus, device and computer-readable storage medium, aiming to solve the technical problem that the current gesture recognition method is difficult to adapt to different scenarios, resulting in a low success rate of gesture recognition.

[0005] To achieve the above object, the present application provides a gesture recognition method, which is applied to a gesture recognition device. The gesture recognition method includes:

[0006] Get user movement information;

[0007] According to the user movement information, identifying the user movement scene;

[0008] According to the user motion scene, a gesture recognition threshold of a preset gesture recognition model is updated, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

[0009] Optionally, the step of updating a gesture recognition threshold of a preset gesture recognition model according to the user motion scene includes:

[0010] Obtaining the intensity level of the user's exercise scene;

[0011] According to the severity level, a gesture recognition threshold of a preset gesture recognition model is updated.

[0012] Optionally, the step of updating a gesture recognition threshold of a preset gesture recognition model according to the severity level includes:

[0013] According to the severity level, querying a preset mapping table to obtain a corresponding designated recognition threshold, wherein the severity level is negatively correlated with the designated recognition threshold;

[0014] The gesture recognition threshold of the preset gesture recognition model is updated to the specified recognition threshold.

[0015] Optionally, the step of identifying a user motion scene according to the user motion information includes:

[0016] Matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene;

[0017] The preset motion scene with the smallest motion feature distance is used as the user motion scene.

[0018] Optionally, the user motion information includes motion acceleration and motion angular velocity, and the step of matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene includes:

[0019] Matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene;

[0020] Matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene;

[0021] Based on the acceleration characteristic distance and the angular velocity characteristic distance, the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes are calculated.

[0022] Optionally, the step of matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance between the user motion information and each preset motion scene includes:

[0023] Differences are taken between the maximum value, minimum value and variance of the motion acceleration and the maximum value, minimum value and variance of the acceleration index of the preset motion scene, respectively, and the absolute values ​​are taken to obtain a first maximum value difference, a first minimum value difference and a first variance difference;

[0024] The first maximum value difference, the first minimum value difference and the first variance difference are summed to obtain an acceleration feature distance corresponding to the user motion information and the preset motion scene.

[0025] Optionally, the step of matching the motion angular velocity with an angular velocity index of each preset motion scene to obtain an angular velocity characteristic distance between the user motion information and each preset motion scene includes:

[0026] The maximum value, the minimum value and the variance of the motion angular velocity are respectively subtracted from the maximum value, the minimum value and the variance of the angular velocity index of the preset motion scene and the absolute values ​​are taken to obtain a second maximum value difference, a second minimum value difference and a second variance difference;

[0027] The second maximum value difference, the second minimum value difference and the second variance difference are summed to obtain an angular velocity feature distance corresponding to the user motion information and the preset motion scene.

[0028] The present application also provides a gesture recognition device, which is applied to a gesture recognition device, and the gesture recognition device includes:

[0029] An acquisition module is used to obtain user movement information;

[0030] An identification module, used to identify a user's sports scene according to the user's sports information;

[0031] The updating module is used to update the gesture recognition threshold of the preset gesture recognition model according to the user motion scene, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

[0032] Optionally, the update module is also used to:

[0033] Obtaining the intensity level of the user's exercise scene;

[0034] According to the severity level, a gesture recognition threshold of a preset gesture recognition model is updated.

[0035] Optionally, the update module is also used to:

[0036] According to the severity level, querying a preset mapping table to obtain a corresponding designated recognition threshold, wherein the severity level is negatively correlated with the designated recognition threshold;

[0037] The gesture recognition threshold of the preset gesture recognition model is updated to the specified recognition threshold.

[0038] Optionally, the identification module is further configured to:

[0039] Matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene;

[0040] The preset motion scene with the smallest motion feature distance is used as the user motion scene.

[0041] Optionally, the user motion information includes motion acceleration and motion angular velocity, and the identification module is further used to:

[0042] Matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene;

[0043] Matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene;

[0044] Based on the acceleration characteristic distance and the angular velocity characteristic distance, the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes are calculated.

[0045] Optionally, the identification module is further configured to:

[0046] Differences are taken between the maximum value, minimum value and variance of the motion acceleration and the maximum value, minimum value and variance of the acceleration index of the preset motion scene, respectively, and the absolute values ​​are taken to obtain a first maximum value difference, a first minimum value difference and a first variance difference;

[0047] The first maximum value difference, the first minimum value difference and the first variance difference are summed to obtain an acceleration feature distance corresponding to the user motion information and the preset motion scene.

[0048] Optionally, the identification module is further configured to:

[0049] The maximum value, the minimum value and the variance of the motion angular velocity are respectively subtracted from the maximum value, the minimum value and the variance of the angular velocity index of the preset motion scene and the absolute values ​​are taken to obtain a second maximum value difference, a second minimum value difference and a second variance difference;

[0050] The second maximum value difference, the second minimum value difference and the second variance difference are summed to obtain an angular velocity feature distance corresponding to the user motion information and the preset motion scene.

[0051] The present application also provides a gesture recognition device, which includes: a memory, a processor, and a program of a gesture recognition method stored in the memory and executable on the processor. When the program of the gesture recognition method is executed by the processor, the steps of the gesture recognition method described above can be implemented.

[0052] The present application also provides a computer-readable storage medium, on which is stored a program for implementing the gesture recognition method. When the program of the gesture recognition method is executed by a processor, the steps of the gesture recognition method as described above are implemented.

[0053] The present application also provides a computer program product, including a computer program, which implements the steps of the gesture recognition method as described above when the computer program is executed by a processor.

[0054] The present application provides a gesture recognition method, apparatus, device and computer-readable storage medium, which can obtain user motion information and then identify the user motion scene according to the user motion information. Then, according to the different user motion scenes, the gesture recognition threshold of the preset gesture recognition model is updated, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold. Therefore, the present application adaptively adjusts the gesture recognition threshold of the preset gesture recognition model according to the different user motion scenes, so that the updated gesture recognition threshold matches the current user motion scene, effectively improving the fault tolerance of gesture recognition and improving the success rate of gesture recognition. Therefore, the present application solves the technical problem that the current gesture recognition method is difficult to adapt to different scenes, resulting in a low success rate of gesture recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 This is a flow chart of the first embodiment of the gesture recognition method of the present application;

[0058] Figure 2 This is a flow chart of the second embodiment of the gesture recognition method of the present application;

[0059] Figure 3 This is a flowchart of a third embodiment of the gesture recognition method of the present application;

[0060] Figure 4 This is a schematic diagram of the structure of a gesture recognition device in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present application.

[0062] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of this application.

[0064] Reference Figure 1 , Figure 1 This is a flowchart of the first embodiment of the gesture recognition method of the present application. The present application provides a gesture recognition method. In the first embodiment of the gesture recognition method of the present application, the gesture recognition method includes:

[0065] Step S100, obtaining user movement information;

[0066] In this embodiment, it should be noted that the gesture recognition method is applied to a gesture recognition device, and the gesture recognition device may be an AR (Augmented Reality) device, a VR (Virtual Reality) device, a smart wearable device, or other device that has gesture recognition requirements.

[0067] In this embodiment, it should also be noted that the user motion information may include the user's moving speed, acceleration, angular velocity, action, and other information describing the user's motion state.

[0068] As an example, the user's motion information may be obtained by detecting the user through a motion detection sensor (such as a speed sensor, an inertial sensor, etc.).

[0069] Step S200, identifying a user motion scene according to the user motion information;

[0070] In this embodiment, it should be noted that the user motion scene is the user motion type corresponding to the user motion information. Exemplarily, the user motion scene can be divided into a steady state, a slight motion and a violent motion according to the intensity of the motion, or it can be divided into more categories of motion scenes from low to high according to the intensity of the motion, such as a primary motion state, a secondary motion state, a tertiary motion state, a quaternary motion state, and a quintuple motion state. Of course, the user motion scene can also be a specific motion category, such as walking, jogging, running, etc.

[0071] In this embodiment, the user motion information can be matched with each preset motion scene to obtain the motion feature distance corresponding to the user motion information and each preset motion scene, and the preset motion scene with the smallest motion feature distance is used as the user motion scene. As an example, the acceleration and angular velocity in the user motion information can be matched with the acceleration index and angular velocity index in the preset motion scene to obtain the motion feature distance corresponding to the user motion information and each preset motion scene, and the preset motion scene with the smallest motion feature distance (that is, the preset motion scene closest to the user motion information) is used as the user motion scene. As another example, the action in the user motion information can be matched with the preset posture in the preset motion scene to obtain the motion feature distance corresponding to the user motion information and each preset motion scene, and the preset motion scene with the smallest motion feature distance is used as the user motion scene.

[0072] Step S300: updating a gesture recognition threshold of a preset gesture recognition model according to the user motion scene, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

[0073] In this embodiment, it should be noted that the more intense the user's movement, the lower the accuracy of the gesture action. Therefore, there is a negative correlation between the intensity of the user's movement scene and the gesture recognition threshold. That is, the higher the intensity of the user's movement scene, the lower the gesture recognition threshold needs to be to match the gesture recognition of the user's movement scene.

[0074] In this embodiment, it should be noted that the preset gesture recognition model is a model for gesture recognition, which can be at least one of a gesture recognition model based on a general deep network, a gesture recognition model based on a long short-term memory neural network, a gesture recognition model based on a template matching method, etc. The gesture recognition threshold is a threshold used by the preset gesture recognition model to distinguish whether the user gesture information matches the preset gesture. It can be understood that the preset gesture recognition model can be mounted on the gesture recognition device or on a server, so that the gesture recognition device can access the preset gesture recognition model on the server through a network connection.

[0075] In this embodiment, the preset mapping table can be queried to obtain the corresponding designated recognition threshold according to the intensity level of the user's motion scene, wherein the preset mapping table includes the corresponding relationship between the intensity level and the designated recognition threshold, and the intensity level is negatively correlated with the designated recognition threshold, that is, the higher the intensity level, the lower the designated recognition threshold. Then, the gesture recognition threshold of the preset gesture recognition model is updated to the designated recognition threshold, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold. As another example, the corresponding relationship between the intensity level and the designated recognition threshold can also be described in the form of an operation function. Then, according to the intensity level of the user's motion scene and the preset operation function, the corresponding designated recognition threshold can be calculated, and then the gesture recognition threshold of the preset gesture recognition model is updated to the designated recognition threshold, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

[0076] In the first embodiment of the present application, by acquiring user motion information, the user motion scene can be identified based on the user motion information. Then, according to the different user motion scenes, the gesture recognition threshold of the preset gesture recognition model is updated, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold. Therefore, this embodiment adaptively adjusts the gesture recognition threshold of the preset gesture recognition model according to the different user motion scenes, so that the updated gesture recognition threshold matches the current user motion scene, effectively improving the fault tolerance of gesture recognition and improving the success rate of gesture recognition. Therefore, this embodiment solves the technical problem that the current gesture recognition method is difficult to adapt to different scenes, resulting in a low success rate of gesture recognition.

[0077] Further, refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the gesture recognition method of the present application.

[0078] In another embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to above and will not be described in detail later. The step of updating the gesture recognition threshold of the preset gesture recognition model according to the user motion scene in step S300 includes:

[0079] Step S310, obtaining the intensity level of the user's exercise scene;

[0080] Step S320: updating a gesture recognition threshold of a preset gesture recognition model according to the severity level.

[0081] In this embodiment, it should be noted that the intensity level is used to characterize the intensity of the movement of the user's movement scene, and the higher the intensity level, the more intense the movement.

[0082] The more intense the user's movement, the lower the accuracy of the gesture. Therefore, in this embodiment, the intensity of the user's movement scene can be determined by obtaining the intensity level of the user's movement scene. Then, the gesture recognition threshold of the preset gesture recognition model can be updated according to the intensity level. The higher the intensity level of the user's movement scene, the lower the updated gesture recognition threshold will be.

[0083] The step of updating the gesture recognition threshold of the preset gesture recognition model according to the severity level in step S320 includes:

[0084] Step S321, according to the severity level, querying a preset mapping table to obtain a corresponding designated recognition threshold, wherein the severity level is negatively correlated with the designated recognition threshold;

[0085] Step S322: updating the gesture recognition threshold of the preset gesture recognition model to the designated recognition threshold.

[0086] In this embodiment, it should be noted that the preset mapping table includes the corresponding relationship between the severity level and the specified recognition threshold, and the severity level is negatively correlated with the specified recognition threshold, that is, the higher the severity level, the lower the specified recognition threshold.

[0087] In this embodiment, the corresponding designated recognition threshold is obtained by querying the preset mapping table according to the intensity level, wherein the intensity level is negatively correlated with the designated recognition threshold. Then, the gesture recognition threshold of the preset gesture recognition model is updated to the designated recognition threshold. Thus, the updated gesture recognition threshold matches the user motion scene, effectively improving the fault tolerance rate of gesture recognition and also improving the success rate of gesture recognition.

[0088] In the second embodiment of the present application, the intensity level of the user's motion scene is obtained; and then the gesture recognition threshold of the preset gesture recognition model is updated according to the intensity level. Thus, the updated gesture recognition threshold matches the intensity level of the user's motion scene, effectively improving the fault tolerance rate of gesture recognition and also improving the success rate of gesture recognition.

[0089] Further, refer to Figure 3 , Figure 3 This is a flowchart of the third embodiment of the gesture recognition method of the present application.

[0090] In another embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description and will not be described in detail later. The step of identifying the user's motion scene according to the user's motion information in step S200 includes:

[0091] Step S210, matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene;

[0092] Step S220: taking the preset motion scene with the smallest motion feature distance as the user motion scene.

[0093] In this embodiment, it should be noted that the preset sports scene is a pre-set user sports scene.

[0094] This embodiment can obtain the motion feature distances corresponding to the user motion information and each preset motion scene by matching the user motion information with the preset motion index of each preset motion scene. The preset motion index is the motion information corresponding to the preset motion scene, such as an acceleration index, an angular velocity index, a moving speed index, etc. The motion feature distance is the distance value between the feature vector corresponding to the user motion information and the feature vector corresponding to the preset motion index of the preset motion scene, which can characterize the matching degree between the user motion information and each preset motion scene. The smaller the motion feature distance, the higher the matching degree. Then the preset motion scene with the smallest motion feature distance (i.e., the preset motion scene with the highest matching degree) can be used as the user motion scene.

[0095] The user motion information includes motion acceleration and motion angular velocity. The step of matching the user motion information with each preset motion scene in step S220 to obtain the motion feature distance corresponding to the user motion information and each preset motion scene includes:

[0096] Step S221, matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene;

[0097] Step S222, matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene;

[0098] Step S223: calculating and obtaining the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes based on the acceleration characteristic distance and the angular velocity characteristic distance.

[0099] In this embodiment, the user motion information includes motion acceleration and motion angular velocity, the motion acceleration is the acceleration of the user when exercising, and the motion angular velocity is the angular velocity of the user when exercising.

[0100] Since acceleration and angular velocity can characterize the intensity of user motion to a certain extent. Therefore, in this embodiment, the acceleration of the motion can be matched with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene. The acceleration characteristic distance is the distance value between the characteristic vector corresponding to the motion acceleration and the characteristic vector corresponding to the acceleration index of the preset motion scene, which can characterize the matching degree of the user motion information and each preset motion scene in terms of acceleration. The smaller the acceleration characteristic distance, the higher the matching degree in terms of acceleration. Secondly, the angular velocity of the motion is matched with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene. The angular velocity characteristic distance is the distance value between the characteristic vector corresponding to the angular velocity of the motion and the characteristic vector corresponding to the angular velocity index of the preset motion scene, which can characterize the matching degree of the user motion information and each preset motion scene in terms of angular velocity. The smaller the angular velocity characteristic distance, the higher the matching degree in terms of angular velocity. Finally, the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes can be calculated based on the acceleration characteristic distance and the angular velocity characteristic distance. Exemplarily, the acceleration characteristic distance and the angular velocity characteristic distance can be respectively assigned a first weight coefficient k1 and a second weight coefficient k2 and then added to obtain the motion characteristic distance. The acceleration characteristic distance and the angular velocity characteristic distance can also be directly added to obtain the motion characteristic distance. The motion characteristic distance can characterize the matching degree between the user motion information and each preset motion scene.

[0101] The step of matching the motion acceleration with the acceleration index of each preset motion scene in step S222 to obtain the acceleration characteristic distance between the user motion information and each preset motion scene includes:

[0102] Step A10, respectively subtracting the maximum value, minimum value and variance of the motion acceleration from the maximum value, minimum value and variance of the acceleration index of the preset motion scene and taking absolute values ​​to obtain a first maximum value difference, a first minimum value difference and a first variance difference;

[0103] Step A20: summing the first maximum value difference, the first minimum value difference and the first variance difference to obtain an acceleration feature distance corresponding to the user motion information and the preset motion scene.

[0104] In this embodiment, it should be noted that the motion acceleration includes the maximum value, minimum value and variance of the motion acceleration. The acceleration index also includes the maximum value, minimum value and variance of the acceleration index.

[0105] In this embodiment, the maximum value, minimum value and variance of the motion acceleration are respectively subtracted from the maximum value, minimum value and variance of the acceleration index of the preset motion scene and the absolute value is taken to obtain a first maximum value difference, a first minimum value difference and a first variance difference. It can be understood that the first maximum value difference, the first minimum value difference and the first variance difference are all absolute values. Then the first maximum value difference, the first minimum value difference and the first variance difference are summed to obtain the acceleration characteristic distance corresponding to the user motion information and the preset motion scene. In this embodiment, the acceleration characteristic distance is calculated by the maximum value, the minimum value and the variance of the motion acceleration. Compared with the method of directly using the motion acceleration value, the obtained acceleration characteristic distance has a higher accuracy.

[0106] The step of matching the motion angular velocity with the angular velocity index of each preset motion scene in step S223 to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene includes:

[0107] Step B10, respectively subtracting the maximum value, minimum value and variance of the motion angular velocity from the maximum value, minimum value and variance of the angular velocity index of the preset motion scene and taking the absolute value to obtain a second maximum value difference, a second minimum value difference and a second variance difference;

[0108] Step B20, summing the second maximum value difference, the second minimum value difference and the second variance difference to obtain an angular velocity feature distance corresponding to the user motion information and the preset motion scene.

[0109] In this embodiment, it should be noted that the motion angular velocity includes the maximum value, minimum value and variance of the motion angular velocity. The angular velocity index also includes the maximum value, minimum value and variance of the angular velocity index.

[0110] In this embodiment, the maximum value, minimum value and variance of the motion angular velocity are respectively subtracted from the maximum value, minimum value and variance of the angular velocity index of the preset motion scene and the absolute value is taken to obtain the second maximum value difference, the second minimum value difference and the second variance difference. It can be understood that the second maximum value difference, the second minimum value difference and the second variance difference are all absolute values. Then the second maximum value difference, the second minimum value difference and the second variance difference are summed to obtain the angular velocity characteristic distance corresponding to the user motion information and the preset motion scene. In this embodiment, the angular velocity characteristic distance is calculated by the maximum value, the minimum value and the variance of the motion angular velocity. Compared with the method of directly using the motion angular velocity value, the angular velocity characteristic distance obtained is more accurate.

[0111] In the third embodiment of the present application, the user motion information is matched with each preset motion scene to obtain the motion feature distances corresponding to the user motion information and each preset motion scene, so that the matching degree between the user motion information and each preset motion scene can be determined. Then, the preset motion scene with the smallest motion feature distance (i.e., the preset motion scene with the highest matching degree) is taken as the user motion scene. Thus, the user motion scene corresponding to the user motion information can be identified.

[0112] Reference Figure 4 , Figure 4 The present application also provides a gesture recognition device, which is applied to a gesture recognition device. The gesture recognition device includes:

[0113] An acquisition module 10 is used to acquire user movement information;

[0114] The identification module 20 is used to identify the user's sports scene according to the user's sports information;

[0115] The updating module 30 is used to update the gesture recognition threshold of the preset gesture recognition model according to the user motion scene, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

[0116] Optionally, the updating module 30 is further configured to:

[0117] Obtaining the intensity level of the user's exercise scene;

[0118] According to the severity level, a gesture recognition threshold of a preset gesture recognition model is updated.

[0119] Optionally, the updating module 30 is further configured to:

[0120] According to the severity level, querying a preset mapping table to obtain a corresponding designated recognition threshold, wherein the severity level is negatively correlated with the designated recognition threshold;

[0121] The gesture recognition threshold of the preset gesture recognition model is updated to the specified recognition threshold.

[0122] Optionally, the identification module 20 is further configured to:

[0123] Matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene;

[0124] The preset motion scene with the smallest motion feature distance is used as the user motion scene.

[0125] Optionally, the user motion information includes motion acceleration and motion angular velocity, and the identification module 20 is further configured to:

[0126] Matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene;

[0127] Matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene;

[0128] Based on the acceleration characteristic distance and the angular velocity characteristic distance, the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes are calculated.

[0129] Optionally, the identification module 20 is further configured to:

[0130] Differences are taken between the maximum value, minimum value and variance of the motion acceleration and the maximum value, minimum value and variance of the acceleration index of the preset motion scene, respectively, and the absolute values ​​are taken to obtain a first maximum value difference, a first minimum value difference and a first variance difference;

[0131] The first maximum value difference, the first minimum value difference and the first variance difference are summed to obtain an acceleration feature distance corresponding to the user motion information and the preset motion scene.

[0132] Optionally, the identification module 20 is further configured to:

[0133] The maximum value, the minimum value and the variance of the motion angular velocity are respectively subtracted from the maximum value, the minimum value and the variance of the angular velocity index of the preset motion scene and the absolute values ​​are taken to obtain a second maximum value difference, a second minimum value difference and a second variance difference;

[0134] The second maximum value difference, the second minimum value difference and the second variance difference are summed to obtain an angular velocity feature distance corresponding to the user motion information and the preset motion scene.

[0135] The gesture recognition device provided by the present application adopts the gesture recognition method in the above-mentioned embodiments, which solves the technical problem that the current gesture recognition method is difficult to adapt to different scenarios, resulting in a low success rate of gesture recognition. Compared with the prior art, the beneficial effects of the gesture recognition device provided by the embodiment of the present application are the same as the beneficial effects of the gesture recognition method provided by the above-mentioned embodiment, and the other technical features in the gesture recognition device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0136] like Figure 5 As shown, Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0137] Specifically, the gesture recognition device may be an AR (Augmented Reality) device, a VR (Virtual Reality) device, a smart wearable device, or other device that has gesture recognition requirements.

[0138] like Figure 5 As shown, the gesture recognition device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0139] Those skilled in the art will understand that Figure 5 The device structure shown in the figure does not constitute a limitation on the gesture recognition device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0140] like Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a gesture recognition application.

[0141] exist Figure 5 In the device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client and communicate data with the client; and the processor 1001 can be used to call the gesture recognition program stored in the memory 1005 to implement the operations in the gesture recognition method provided in the above embodiment.

[0142] In addition, an embodiment of the present application further proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the operations in the gesture recognition method provided in the above embodiment are implemented. The specific steps are not repeated here.

[0143] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such actual relationship or order between these entities / operations / objects; the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0144] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, and the units described as separate components may or may not be physically separated. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0145] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0146] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server or network device, etc.) to execute the methods described in each embodiment of the present application.

[0147] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A gesture recognition method, characterized in that: The gesture recognition method comprises: Get user movement information; According to the user movement information, identifying the user movement scene; According to the user motion scene, a gesture recognition threshold of a preset gesture recognition model is updated, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

2. The gesture recognition method according to claim 1, characterized in that: The step of updating the gesture recognition threshold of the preset gesture recognition model according to the user motion scene includes: Obtaining the intensity level of the user's exercise scene; According to the severity level, a gesture recognition threshold of a preset gesture recognition model is updated.

3. The gesture recognition method according to claim 2, characterized in that: The step of updating the gesture recognition threshold of the preset gesture recognition model according to the severity level includes: According to the severity level, querying a preset mapping table to obtain a corresponding designated recognition threshold, wherein the severity level is negatively correlated with the designated recognition threshold; The gesture recognition threshold of the preset gesture recognition model is updated to the specified recognition threshold.

4. The gesture recognition method according to claim 1, characterized in that: The step of identifying the user's motion scene according to the user's motion information includes: Matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene; The preset motion scene with the smallest motion feature distance is used as the user motion scene.

5. The gesture recognition method according to claim 4, characterized in that: The user motion information includes motion acceleration and motion angular velocity. The step of matching the user motion information with each preset motion scene to obtain motion feature distances corresponding to the user motion information and each preset motion scene includes: Matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance corresponding to the user motion information and each preset motion scene; Matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene; Based on the acceleration characteristic distance and the angular velocity characteristic distance, the motion characteristic distances corresponding to the user motion information and each of the preset motion scenes are calculated.

6. The gesture recognition method according to claim 5, characterized in that: The step of matching the motion acceleration with the acceleration index of each preset motion scene to obtain the acceleration characteristic distance between the user motion information and each preset motion scene includes: Differences are taken between the maximum value, minimum value and variance of the motion acceleration and the maximum value, minimum value and variance of the acceleration index of the preset motion scene, respectively, and the absolute values ​​are taken to obtain a first maximum value difference, a first minimum value difference and a first variance difference; The first maximum value difference, the first minimum value difference and the first variance difference are summed to obtain an acceleration feature distance corresponding to the user motion information and the preset motion scene.

7. The gesture recognition method according to claim 5, characterized in that: The step of matching the motion angular velocity with the angular velocity index of each preset motion scene to obtain the angular velocity characteristic distance corresponding to the user motion information and each preset motion scene includes: The maximum value, the minimum value and the variance of the motion angular velocity are respectively subtracted from the maximum value, the minimum value and the variance of the angular velocity index of the preset motion scene and the absolute values ​​are taken to obtain a second maximum value difference, a second minimum value difference and a second variance difference; The second maximum value difference, the second minimum value difference and the second variance difference are summed to obtain an angular velocity feature distance corresponding to the user motion information and the preset motion scene.

8. A gesture recognition device, characterized in that: The gesture recognition device comprises: An acquisition module is used to obtain user movement information; An identification module, used to identify a user's sports scene according to the user's sports information; The updating module is used to update the gesture recognition threshold of the preset gesture recognition model according to the user motion scene, so that the preset gesture recognition model performs gesture recognition based on the updated gesture recognition threshold.

9. A gesture recognition device, characterized in that: The gesture recognition device comprises: a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the computer program is executed by the processor, the steps of the gesture recognition method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a gesture recognition program, and when the gesture recognition program is executed by a processor, the steps of the gesture recognition method according to any one of claims 1 to 7 are implemented.

Images