Thumb action recognition glove device and method

Abstract

The invention discloses a thumb action recognition glove device and method, and relates to the technical field of man-machine interaction, the glove device comprises a glove body, a first inertial sensor, a second inertial sensor, a data processing unit and a user interface; the glove body is used for being worn on the hand of a user, and the first inertial sensor, the second inertial sensor and the user interface are connected with the data processing unit; the first inertial sensor is arranged on the hand back of the glove body, and the second inertial sensor is arranged on the thumb of the glove body. The method comprises the following steps: acquiring original data; preprocessing the original data to obtain preprocessed data; performing calculation processing on the pre-processed data to obtain a flexion and extension angle between the thumb and the back of the hand; and determining the action of the thumb according to the bending and stretching angle change between the thumb and the hand back. According to the invention, stable recognition of the thumb action can be realized, the angle change of the thumb in the pressing and lifting process can be accurately detected, and the control requirement of actual controlled equipment is met.

Description

Technical Field

[0001] The present invention relates to the technical field of human-computer interaction, and in particular to a thumb motion recognition glove device and method. Background Art

[0002] With the continuous advancement of human-computer interaction technology, the interaction between the virtual world and the real world is becoming closer and closer. Among them, gesture interaction, as the most widely used technology in human-computer interaction, is becoming a natural bridge between users and computer interfaces. Traditional gesture interaction technology mainly relies on machine vision systems. Although machine vision technology has made significant progress in gesture recognition, it requires a large amount of image acquisition and complex image processing, relies on a large amount of data processing and computing power, and usually requires high-performance processors and large-capacity memory to support it. This limits the application scope of machine vision gesture interaction technology on lightweight or embedded devices, making them difficult to apply on small devices or resource-constrained platforms.

[0003] In order to overcome the above problems, gesture interaction technology based on inertial sensors (IMU) has begun to attract attention and application in recent years. Since inertial sensors can measure and monitor acceleration and angular velocity without a large amount of image data, they can realize gesture recognition on small, low-power devices, while monitoring the user's hand posture and movements in real time. This gesture interaction technology based on inertial sensors has high real-time and low power consumption characteristics, making it suitable for mobile devices, wearable devices and other resource-constrained platforms, so as to achieve interaction with computers or other devices. With the development of human-computer interaction technology, gesture interaction technology based on inertial sensors is becoming an important alternative. It can realize a more convenient and efficient user interface, and promote innovation and development in the fields of virtual reality, augmented reality and smart wearable devices.

[0004] However, the current gesture interaction technology based on inertial sensors still has some problems in practical application. One of them is the problem of recognition accuracy and stability when processing thumb movements, especially when detecting the angle change during the process of pressing and lifting the thumb, the recognition accuracy and stability are insufficient. Summary of the invention

[0005] In order to solve some or all of the technical problems existing in the above-mentioned prior art, the present invention provides a thumb motion recognition glove device and method, which solves the problem of thumb motion recognition stability, can accurately detect the angle changes during the thumb pressing and lifting process, and meet the control requirements of the actual controlled equipment.

[0006] The technical solution of the present invention is as follows:

[0007] In a first aspect, a thumb motion recognition glove device is provided, the glove device comprising: a glove body, a first inertial sensor, a second inertial sensor, a data processing unit and a user interface;

[0008] The glove body is used to be worn on a user's hand and to fix the first inertial sensor, the second inertial sensor, the data processing unit and the user interface;

[0009] The first inertial sensor, the second inertial sensor and the user interface are respectively connected to the data processing unit;

[0010] The first inertial sensor is disposed at the back of the glove body, and is used to collect and send a first quaternion, a first acceleration, and a first angular velocity to the data processing unit;

[0011] The second inertial sensor is disposed at the thumb of the glove body, and is used to collect and send a second quaternion, a second acceleration, and a second angular velocity to the data processing unit;

[0012] The data processing unit is used to receive and process the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity to obtain the flexion and extension angle between the thumb and the back of the hand, and to determine the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand;

[0013] The user interface can be connected to an external device for data interaction.

[0014] In a second aspect, a thumb motion recognition method is provided, the method being applied to the thumb motion recognition glove device, the method comprising:

[0015] Acquire original data, the original data including: a first quaternion, a first acceleration, a first angular velocity, a second quaternion, a second acceleration, and a second angular velocity;

[0016] Preprocessing the raw data to obtain preprocessed data, wherein the preprocessed data includes: a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity;

[0017] Calculating and processing the preprocessed data to obtain the flexion and extension angle between the thumb and the back of the hand;

[0018] Determine the movement of the thumb based on the changes in the flexion and extension angle between the thumb and the back of the hand.

[0019] In some optional implementations, obtaining raw data includes:

[0020] Initializing the glove device;

[0021] Using the first inertial sensor, collecting and obtaining the first quaternion, the first acceleration, and the first angular velocity;

[0022] The second quaternion, the second acceleration, and the second angular velocity are acquired by using the second inertial sensor.

[0023] In some optional implementations, preprocessing the raw data to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity includes:

[0024] Performing filtering processing on the first acceleration, the first angular velocity, the second acceleration and the second angular velocity to obtain a first filtered acceleration, a first filtered angular velocity, a second filtered acceleration and a second filtered angular velocity;

[0025] The first filtered acceleration, the first filtered angular velocity, the second filtered acceleration and the second filtered angular velocity are subjected to zero-bias removal processing to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration and a second preprocessed angular velocity.

[0026] In some optional implementations, filtering the first acceleration, the first angular velocity, the second acceleration, and the second angular velocity to obtain a first filtered acceleration, a first filtered angular velocity, a second filtered acceleration, and a second filtered angular velocity includes:

[0027] Preprocessing the first acceleration and the first angular velocity using a first data preprocessing model to obtain a first filtered acceleration and a first filtered angular velocity;

[0028] Preprocessing the second acceleration and the second angular velocity by using the first data preprocessing model to obtain a second filtered acceleration and a second filtered angular velocity;

[0029] The first data preprocessing model expression is:

[0030]

[0031] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th filtered acceleration at time t, a i,(x,y,z) (tj) represents the i-th acceleration at time tj, p i represents the acceleration correction factor, represents the i-th filtered angular velocity at time t, ω i,(x,y,z)(tj) represents the angular velocity of the i-th moment tj, b i represents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, N represents the number of sampling points, j represents the sampling point index, and tj represents the jth sampling time before time t.

[0032] In some optional implementations, performing de-biasing processing on the first filtered acceleration, the first filtered angular velocity, the second filtered acceleration, and the second filtered angular velocity to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity includes:

[0033] Preprocessing the first filtered acceleration and the first filtered angular velocity by using a second data preprocessing model to obtain a first preprocessed acceleration and a first preprocessed angular velocity;

[0034] Preprocessing the second filtered acceleration and the second filtered angular velocity by using the second data preprocessing model to obtain a second preprocessed acceleration and a second preprocessed angular velocity;

[0035] The second data preprocessing model expression is:

[0036]

[0037] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th preprocessed acceleration at time t, represents the i-th filtered acceleration at time t, a i,(x,y,z) (tj) represents the i-th acceleration at time tj, p i represents the acceleration correction factor, represents the i-th preprocessed angular velocity at time t, represents the i-th filtered angular velocity at time t, ω i,(x,y,z) (tj) represents the angular velocity of the i-th moment tj, b i represents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, M represents the number of sampling points, j represents the sampling point index, and tj represents the jth sampling time before time t.

[0038] In some optional implementations, the calculating and processing the preprocessed data to obtain the flexion and extension angle between the thumb and the back of the hand includes:

[0039] Normalizing the first quaternion and the second quaternion to obtain a first normalized quaternion and a second normalized quaternion;

[0040] Performing bias calculation on the first normalized quaternion and the second normalized quaternion to obtain a biased quaternion;

[0041] Using a quaternion angle calculation model, the biased quaternion is calculated and processed to obtain a quaternion angle between the thumb and the back of the hand;

[0042] Using an angular velocity difference calculation model, calculating and processing the first preprocessed angular velocity and the second preprocessed angular velocity to obtain an angular velocity difference;

[0043] The first preprocessed acceleration, the quaternion angle and the angular velocity difference are processed to obtain a flexion and extension angle between the thumb and the back of the hand.

[0044] In some optional implementations, the normalized expression is:

[0045]

[0046] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the j+1th component of the i-th normalized quaternion, j=0,1,2,3,q i,j represents the j+1th element component of the i-th quaternion, β i Represents the quaternion correction coefficient, q i,0 Represents the first component of the i-th quaternion, q i,1 Represents the second component of the i-th quaternion, q i,2 Represents the third component of the i-th quaternion, q i,3 Represents the 4th component of the i-th quaternion;

[0047] The bias calculation expression is:

[0048]

[0049] Among them, Q(t) represents the bias quaternion at time t, represents the first normalized quaternion at time t, Represents the second normalized quaternion at time t, express The inverse operation of ; the quaternion angle calculation model expression is:

[0050]

[0051] Among them, Angle hf(t) represents the quaternion angle at time t, π represents pi, Q0(t) represents the first component of the biased quaternion at time t, Q1(t) represents the second component of the biased quaternion at time t, Q2(t) represents the third component of the biased quaternion at time t, Q3(t) represents the fourth component of the biased quaternion at time t, arctan represents the calculation of the inverse tangent trigonometric function;

[0052] The angular velocity difference calculation model expression is:

[0053]

[0054] Among them, ω_c(t) represents the angular velocity difference at time t, represents the second pre-processed angular velocity X-axis component at time t, represents the second pre-processed angular velocity Y-axis component at time t, represents the second pre-processed angular velocity Z-axis component at time t, represents the first preprocessed angular velocity X-axis component at time t, represents the first preprocessed angular velocity Y-axis component at time t, Represents the first pre-processed angular velocity Z-axis component at time t.

[0055] In some optional implementations, the processing of the first preprocessed acceleration, the quaternion angle, and the angular velocity difference to obtain the flexion and extension angle between the thumb and the back of the hand includes:

[0056] Analyzing the first preprocessed acceleration to obtain a first preprocessed acceleration Z-axis component;

[0057] Determine whether the Z-axis component of the first preprocessed acceleration is greater than or equal to a first threshold value, and obtain a tilt determination result;

[0058] When the tilt determination result is yes, the quaternion angle is used as the flexion and extension angle between the thumb and the back of the hand;

[0059] When the inclination judgment result is no, further judging whether the angular velocity difference is greater than or equal to a second threshold value, and obtaining a first relative motion judgment result; if the first relative motion judgment result is yes, processing the quaternion angle by using an angle increment calculation model, and obtaining a flexion and extension angle between the thumb and the back of the hand;

[0060] The angle increment calculation model expression is:

[0061] Angle(t)=Angle(t-1)+(Angle hf (t)-Angle hf (t-1));

[0062] Where Angle(t) represents the flexion and extension angle between the thumb and the back of the hand at time t, Angle(t-1) represents the flexion and extension angle between the thumb and the back of the hand at time t-1, and Angle hf (t) represents the quaternion angle at time t, Angle hf (t-1) represents the quaternion angle at time t-1.

[0063] In some optional implementations, determining the movement of the thumb according to the change in the flexion and extension angle between the thumb and the back of the hand includes:

[0064] Determine whether the angular velocity difference between the second preprocessing angular velocity and the first preprocessing angular velocity is greater than or equal to a third threshold, and obtain a second relative motion situation determination result;

[0065] When the result of the second relative motion situation judgment is yes, further judging whether the flexion and extension angle at the previous moment is greater than or equal to the flexion and extension angle at the current moment, and obtaining a flexion and extension angle change judgment result;

[0066] If the result of the flexion and extension angle change judgment is yes, determining that the action of the thumb is a pressing action;

[0067] If the result of the flexion and extension angle change judgment is no, it is determined that the action of the thumb is a lifting action.

[0068] The main advantages of the technical solution of the present invention are as follows:

[0069] The thumb motion recognition glove device and method of the present invention respectively detects the motion information of the back of the hand and the motion information of the thumb by setting an inertial sensor, and processes the acquired motion information to achieve stable recognition of the thumb motion, solve the problem of stable thumb motion recognition, and can accurately detect the angle change of the thumb during pressing and lifting, thereby meeting the control requirements of the actual controlled equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0071] Figure 1 This is a schematic diagram of the composition of a thumb motion recognition glove device disclosed in an embodiment of the present invention, wherein the glove body is not shown;

[0072] Figure 2 A schematic diagram of the positions of a first inertial sensor and a second inertial sensor of a thumb motion recognition glove device disclosed in an embodiment of the present invention;

[0073] Figure 3 The present invention is a flowchart of a thumb motion recognition method disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0075] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0076] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0077] The present invention discloses a thumb action recognition glove device and method, which solves the problem of thumb action recognition stability, can accurately detect the angle change of the thumb during the pressing and lifting process, and meet the control requirements of the actual controlled equipment. The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0078] Embodiment 1

[0079] refer to Figure 1-2 , Figure 1 This is a schematic diagram of the composition of a thumb motion recognition glove device disclosed in an embodiment of the present invention. Figure 2 The schematic diagram of the positions of the first inertial sensor and the second inertial sensor of a thumb motion recognition glove device disclosed in an embodiment of the present invention. To solve the above technical problems, an embodiment of the present invention provides a thumb motion recognition glove device, the glove device comprising: a glove body, a first inertial sensor 100, a second inertial sensor 200, a data processing unit 300 and a user interface 400;

[0080] The glove body is used to be worn on the user's hand and fix the first inertial sensor 100, the second inertial sensor 200, the data processing unit 300 and the user interface 400;

[0081] The first inertial sensor 100 , the second inertial sensor 200 and the user interface 400 are respectively connected to the data processing unit 300 ;

[0082] The first inertial sensor 100 is disposed on the back of the glove body and is used to collect and send a first quaternion, a first acceleration and a first angular velocity to the data processing unit 300;

[0083] The second inertial sensors 200 are respectively arranged at the thumb of the glove body, and are used to collect and send the second quaternion, the second acceleration and the second angular velocity to the data processing unit 300;

[0084] The data processing unit 300 is used to receive and process the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity, obtain the flexion and extension angle between the thumb and the back of the hand, and determine the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand;

[0085] The user interface 400 can be connected to an external device for data interaction.

[0086] It should be noted that the glove body Figure 1 Not shown.

[0087] It should be noted that when the second inertial sensor 200 is set at the thumb, the X-axis of the second inertial sensor 200 is parallel to the surface of the thumb and points to the direction of the thumb, the Y-axis of the second inertial sensor 200 is parallel to the back of the thumb and points to the side of the thumb, the Z-axis of the second inertial sensor 200 is perpendicular to the back of the thumb and points upward, and the XYZ three-axis directions of the first inertial sensor 100 are the same as the XYZ three-axis directions of the second inertial sensor 200.

[0088] In the embodiment of the present invention, the user interface 400 can be connected to an external device to achieve data interaction between the glove device and the external device. Optionally, the user interface 400 can be a physical interface or a standard wireless Bluetooth or WiFi communication unit.

[0089] In an embodiment of the present invention, the data processing unit 300 uses the user interface 400 as a channel to perform data interaction with a connected external device, and the data interaction includes: receiving data input by the external device, and outputting flexion and extension angle information between the thumb and the back of the hand, and / or thumb movement instructions to the external device.

[0090] It should be noted that the thumb motion recognition glove device provided in the embodiment of the present invention can be applied to a wearable human-computer interaction system and can be connected to a local server or cloud server for human-computer interaction management, etc., which is not limited in the embodiment of the present invention.

[0091] In the embodiment of the present invention, the data processing unit 300 may be a CPU; the data processing unit 300 may be respectively connected to the first inertial sensor 100, the second inertial sensor 200 and the user interface 400 through a communication bus; the data processing unit 300 may be provided with or connected to a memory, and the memory may be used to store the flexion and extension angle information between the thumb and the back of the hand and the thumb movement information obtained by the data processing unit 300; wherein the memory may be a high-speed RAM memory or a ROM memory.

[0092] The thumb motion recognition glove device provided in the embodiment of the present invention is equipped with inertial sensors to respectively detect the motion information of the back of the hand and the motion information of the thumb. By processing the acquired motion information, it is possible to achieve stable recognition of thumb motions, solve the problem of stable thumb motion recognition, and accurately detect the angle changes of the thumb during pressing and lifting, thereby meeting the control requirements of the actual controlled equipment.

[0093] Embodiment 2

[0094] refer to Figure 3 , Figure 3 The flowchart of a thumb motion recognition method disclosed in an embodiment of the present invention is as follows. To solve the above technical problems, an embodiment of the present invention provides a thumb motion recognition method, which can be applied to the thumb motion recognition glove device described in the first embodiment.

[0095] like Figure 3 As shown, the thumb action recognition method provided by the embodiment of the present invention includes the following steps 1 to 4:

[0096] Step 1, obtaining original data;

[0097] In the embodiment of the present invention, the original data includes: a first quaternion, a first acceleration, a first angular velocity, a second quaternion, a second acceleration, and a second angular velocity.

[0098] Step 2, performing calculation processing on the original data to obtain preprocessed data;

[0099] In the embodiment of the present invention, the preprocessed data includes: a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity.

[0100] Step 3, calculating and processing the preprocessed data to obtain the flexion and extension angle between the thumb and the back of the hand;

[0101] Step 4, determine the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand;

[0102] In the embodiment of the present invention, the thumb action includes: a pressing action and a lifting action.

[0103] By implementing the thumb motion recognition method provided by the embodiment of the present invention in the thumb motion recognition glove device described in the above embodiment 1, the problem of thumb motion recognition stability can be solved, and the angle change during the thumb pressing and lifting process can be accurately detected to meet the control requirements of the actual controlled equipment.

[0104] Further, in an optional implementation of the embodiment of the present invention, in the above step 1, the obtaining of raw data includes the following steps 101 to 103:

[0105] Step 101, initializing the glove device;

[0106] In an embodiment of the present invention, initializing the glove device includes: turning on the glove device, making the palm of the glove face downward, and the back of the hand parallel to the ground, and maintaining the glove in a specified state for 5-10 seconds. The specified state may be a "clenched fist" state or a "fully extended fingers" state.

[0107] Step 102, using a first inertial sensor to collect and acquire a first quaternion, a first acceleration, and a first angular velocity;

[0108] In the embodiment of the present invention, the first inertial sensor is disposed at the back of the hand, and is used to collect the first quaternion, the first acceleration and the first angular velocity at the back of the hand.

[0109] The first acceleration is the XYZ three-axis acceleration measured by the first inertial sensor, and the first angular velocity is the XYZ three-axis angular velocity measured by the first inertial sensor.

[0110] Step 103, using a second inertial sensor to collect and acquire a second quaternion, a second acceleration, and a second angular velocity;

[0111] In the embodiment of the present invention, the second inertial sensor is disposed at the thumb, and is used to collect the second quaternion, the second acceleration and the second angular velocity at the thumb.

[0112] The second acceleration is the XYZ three-axis acceleration measured by the second inertial sensor, and the second angular velocity is the XYZ three-axis angular velocity measured by the second inertial sensor.

[0113] It should be noted that when the second inertial sensor 200 is set at the thumb, the X-axis of the second inertial sensor 200 is parallel to the surface of the thumb and points to the direction of the thumb, the Y-axis of the second inertial sensor 200 is parallel to the back of the thumb and points to the side of the thumb, the Z-axis of the second inertial sensor 200 is perpendicular to the back of the thumb and points upward, and the XYZ three-axis directions of the first inertial sensor 100 are the same as the XYZ three-axis directions of the second inertial sensor 200.

[0114] In the embodiment of the present invention, by powering on and initializing the glove device before collecting and acquiring the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity, the reliability of the collected data of the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity can be ensured.

[0115] In another optional implementation of the embodiment of the present invention, in the above step 1, the obtaining of raw data includes the following steps 111 to 117:

[0116] Step 111, using a first inertial sensor to collect and obtain a first three-axis angular velocity at time t;

[0117] In the embodiment of the present invention, a first inertial sensor disposed on the back of the hand is used to collect the first three-axis angular velocity at time t.

[0118] Step 112, using a second inertial sensor to collect and obtain a second three-axis angular velocity at time t;

[0119] In the embodiment of the present invention, the second three-axis angular velocity at time t is acquired by using a second inertial sensor disposed at the thumb.

[0120] Step 113, based on the angular velocity calculation model, respectively calculating and processing the first three-axis angular velocity and the second three-axis angular velocity to obtain the hand back angular velocity and the thumb angular velocity;

[0121] In the embodiment of the present invention, the angular velocity calculation model expression is:

[0122]

[0123] Among them, g i (t) represents the angular velocity at time t, i = 1, 2, when i = 1, g i (t) is the angular velocity of the back of the hand, g ix (t) represents the X-axis component of the first three-axis angular velocity at time t, g iy (t) represents the Y-axis component of the first three-axis angular velocity at time t, g iz (t) represents the Z-axis component of the first three-axis angular velocity at time t. When i = 2, gi (t) is the angular velocity of the thumb, g ix (t) represents the X-axis component of the second three-axis angular velocity at time t, g iy (t) represents the Y-axis component of the second three-axis angular velocity at time t, g iz (t) represents the Z-axis component of the second three-axis angular velocity at time t, and t represents the sampling time.

[0124] Step 114, determining whether the hand back angular velocity and the thumb angular velocity are both less than the angular velocity threshold, and obtaining a determination result;

[0125] In the embodiment of the present invention, the angular velocity threshold is used to determine whether the glove device is in a stationary state. It should be noted that the stationary state does not necessarily mean being motionless. When the movement amplitude of the glove device is small and negligible, the glove device is also regarded as being in a stationary state.

[0126] Therefore, in the embodiment of the present invention, the specific value of the angular velocity threshold is set according to the actual situation, but the value cannot be too large. For example, the angular velocity threshold is a value within the range of 5-6° / s.

[0127] Step 115, when the judgment result is yes, execute steps 116 to 117;

[0128] When the judgment result is no, execute step 111;

[0129] Step 116, using a first inertial sensor to collect and acquire a first quaternion, a first acceleration, and a first angular velocity;

[0130] In the embodiment of the present invention, the first inertial sensor is disposed at the back of the hand, and can collect the first quaternion, the first acceleration and the first angular velocity at the back of the hand.

[0131] Step 117, using a second inertial sensor to collect and acquire a second quaternion, a second acceleration, and a second angular velocity;

[0132] In the embodiment of the present invention, the second inertial sensor is disposed at the thumb, and can collect the second quaternion, the second acceleration and the second angular velocity at the thumb.

[0133] In the embodiment of the present invention, by first determining whether the glove device is in a stationary state before acquiring the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity, the reliability of the collected data of the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity can be ensured.

[0134] Further, in an optional implementation of the embodiment of the present invention, in the above step 2, the raw data is preprocessed to obtain preprocessed data, including the following steps 21-22:

[0135] Step 21, filtering the first acceleration, the first angular velocity, the second acceleration, and the second angular velocity to obtain a first filtered acceleration, a first filtered angular velocity, a second filtered acceleration, and a second filtered angular velocity;

[0136] Step 22, performing zero-bias removal processing on the first filtered acceleration, the first filtered angular velocity, the second filtered acceleration and the second filtered angular velocity to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration and a second preprocessed angular velocity.

[0137] In the embodiment of the present invention, by filtering and de-biasing the acceleration and angular velocity, errors that may be contained in the collected data can be eliminated, and the accuracy of solving the flexion and extension angle and the accuracy of thumb movement detection can be further improved.

[0138] Further, in an optional implementation of the embodiment of the present invention, the filtering of the first acceleration, the first angular velocity, the second acceleration, and the second angular velocity to obtain the first filtered acceleration, the first filtered angular velocity, the second filtered acceleration, and the second filtered angular velocity includes the following steps 211-212:

[0139] Step 211, using a first data preprocessing model, preprocessing the first acceleration and the first angular velocity to obtain a first filtered acceleration and a first filtered angular velocity;

[0140] Step 212: preprocess the second acceleration and the second angular velocity using the first data preprocessing model to obtain a second filtered acceleration and a second filtered angular velocity.

[0141] In the embodiment of the present invention, the first data preprocessing model expression is:

[0142]

[0143] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th filtered acceleration at time t, a i,(x,y,z) (tj) represents the i-th acceleration at time tj, p i represents the acceleration correction factor, represents the i-th filtered angular velocity at time t, ω i,(x,y,z) (tj) represents the angular velocity of the i-th moment tj, b irepresents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, N represents the number of sampling points, j represents the sampling point index, and tj represents the jth sampling time before time t.

[0144] In the embodiment of the present invention, the acceleration correction coefficient p i Used to correct the acceleration measurement error of the inertial sensor, angular velocity correction coefficient b i Used to correct the angular velocity measurement error of the inertial sensor, the acceleration correction coefficient p i and angular velocity correction factor b i The specific value of is set according to the actual situation. For example, when the inertial sensor does not have acceleration measurement error and angular velocity measurement error, the acceleration correction coefficient p i and angular velocity correction factor b i Both are set to 1.

[0145] It should be noted that the number of sampling points N is set according to the actual situation. For example, it is set to 10, which means that the data of the last 10 consecutive sampling points before time t are taken as the input value of the average sampling.

[0146] In the embodiment of the present invention, by using the first data preprocessing model to filter the acceleration and angular velocity, errors that may be contained in the collected data can be eliminated, and the accuracy of solving the flexion and extension angle and the accuracy of thumb movement detection can be further improved.

[0147] Further, in an optional implementation of the embodiment of the present invention, the first filtered acceleration, the first filtered angular velocity, the second filtered acceleration, and the second filtered angular velocity are subjected to zero-bias processing to obtain the first preprocessed acceleration, the first preprocessed angular velocity, the second preprocessed acceleration, and the second preprocessed angular velocity, including the following steps 221-222:

[0148] Step 221, using a second data preprocessing model, preprocessing the first filtered acceleration and the first filtered angular velocity to obtain a first preprocessed acceleration and a first preprocessed angular velocity;

[0149] Step 222: Preprocess the second filtered acceleration and the second filtered angular velocity using a second data preprocessing model to obtain a second preprocessed acceleration and a second preprocessed angular velocity.

[0150] In the embodiment of the present invention, the second data preprocessing model expression is:

[0151]

[0152] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th preprocessed acceleration at time t, represents the i-th filtered acceleration at time t, a i,(x,y,z) (tj) represents the i-th acceleration at time tj, p i represents the acceleration correction factor, represents the i-th preprocessed angular velocity at time t, represents the i-th filtered angular velocity at time t, ω i,(x,y,z) (tj) represents the angular velocity of the i-th moment tj, b i represents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, M represents the number of sampling points, j represents the sampling point index, and tj represents the jth sampling time before time t.

[0153] In the embodiment of the present invention, the acceleration correction coefficient p i Used to correct the acceleration measurement error of the inertial sensor, angular velocity correction coefficient b i Used to correct the angular velocity measurement error of the inertial sensor, the acceleration correction coefficient p i and angular velocity correction factor b i The specific value of is set according to the actual situation. For example, when the inertial sensor does not have acceleration measurement error and angular velocity measurement error, the acceleration correction coefficient p i and angular velocity correction factor b i Both are set to 1.

[0154] It should be noted that the number of sampling points M is set according to the actual situation. For example, it is set to 200, which means that the data of the last 200 consecutive sampling points before time t are taken as the input value of the average sampling; or it can be taken as the actual number of sampling points between the initialization of the glove device and the current time t, which means that 200 sampling points are taken continuously from the initialization of the glove device to obtain the average value as its deviation.

[0155] In the embodiment of the present invention, by using the second data preprocessing model to perform zero-bias processing on acceleration and angular velocity, errors that may be contained in the collected data can be eliminated, and the accuracy of solving the flexion and extension angle and the accuracy of thumb movement detection can be further improved.

[0156] Furthermore, in an optional implementation of the embodiment of the present invention, considering that the hand has the following characteristics when in motion:

[0157] When the hand makes a rolling or pitching motion, the motion data collected by the first inertial sensor on the back of the hand must not be zero, and the motion data collected by the second inertial sensor on the thumb is also not zero. The back of the hand is in absolute motion relative to the earth, and the thumb is in involved motion relative to the earth.

[0158] Whether in motion or at rest, when the angle between the back of the hand and the thumb changes, theoretically the combined acceleration and angular velocity of the thumb should be greater than the combined acceleration and angular velocity of the back of the hand, and in general the changing trend of the angle is relatively correct.

[0159] Based on the above features, in an embodiment of the present invention, in the above step 3, the calculation and processing of the pre-processed data to obtain the flexion and extension angle between the thumb and the back of the hand includes the following steps 31 to 35:

[0160] Step 31, normalizing the first quaternion and the second quaternion to obtain a first normalized quaternion and a second normalized quaternion;

[0161] Step 32, performing bias calculation on the first normalized quaternion and the second normalized quaternion to obtain a biased quaternion;

[0162] Step 33, using the quaternion angle calculation model, calculating and processing the biased quaternion to obtain the quaternion angle between the thumb and the back of the hand;

[0163] Step 34, using the angular velocity difference calculation model, calculating and processing the first preprocessed angular velocity and the second preprocessed angular velocity to obtain the angular velocity difference;

[0164] Step 35, processing the first preprocessed acceleration, the quaternion angle and the angular velocity difference to obtain the flexion and extension angle between the thumb and the back of the hand.

[0165] In the embodiment of the present invention, by using the above process to solve the flexion and extension angle between the thumb and the back of the hand, the accuracy of solving the flexion and extension angle can be further improved.

[0166] Further, in an optional implementation of the embodiment of the present invention, in the above step S31, the normalization processing expression is:

[0167]

[0168] Where i represents the inertial sensor index, i=1,2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the j+1th component of the i-th normalized quaternion, j=0,1,2,3,q i,j represents the j+1th element component of the i-th quaternion, β i Represents the quaternion correction coefficient, q i,0Represents the first element component of the i-th quaternion, q i,1 Represents the second component of the i-th quaternion, q i,2 Represents the third component of the i-th quaternion, q i,3 Represents the 4th component of the i-th quaternion.

[0169] It should be noted that the quaternion correction coefficient β i Used to correct the quaternion measurement error of the inertial sensor, the quaternion correction coefficient β i The specific value of is set according to the actual situation. For example, when the inertial sensor does not have quaternion measurement error, the quaternion correction coefficient β i Set to 1.

[0170] In the above step S32, the offset calculation expression is:

[0171]

[0172] Among them, Q(t) represents the bias quaternion at time t, represents the first normalized quaternion at time t, Represents the second normalized quaternion at time t, express The inverse operation of .

[0173] In the above step 33, the quaternion angle calculation model expression is:

[0174]

[0175] Among them, Angle hf (t) represents the quaternion angle at time t, π represents pi, Q0(t) represents the first component of the biased quaternion at time t, Q1(t) represents the second component of the biased quaternion at time t, Q2(t) represents the third component of the biased quaternion at time t, Q3(t) represents the fourth component of the biased quaternion at time t, and arctan represents the calculation of the inverse tangent trigonometric function.

[0176] In the above step 34, the angular velocity difference calculation model expression is:

[0177]

[0178]

[0179] Among them, ω_c(t) represents the angular velocity difference at time t, represents the second pre-processed angular velocity X-axis component at time t, represents the second pre-processed angular velocity Y-axis component at time t, represents the second pre-processed angular velocity Z-axis component at time t, represents the first preprocessed angular velocity X-axis component at time t, represents the first preprocessed angular velocity Y-axis component at time t, Represents the first pre-processed angular velocity Z-axis component at time t.

[0180] In the embodiment of the present invention, by processing the data using the above formula and model, the accuracy of solving the flexion and extension angle can be further improved.

[0181] Further, in an optional implementation of the embodiment of the present invention, in the above step 35, the first preprocessed acceleration, the quaternion angle and the angular velocity difference are processed to obtain the flexion and extension angle between the thumb and the back of the hand, including the following steps 351-354:

[0182] Step 351, analyzing the first preprocessed acceleration to obtain a Z-axis component of the first preprocessed acceleration;

[0183] Step 352, determining whether the Z-axis component of the first preprocessed acceleration is greater than or equal to a first threshold, and obtaining a tilt determination result;

[0184] Step 353, when the tilt determination result is yes, the quaternion angle is used as the flexion and extension angle between the thumb and the back of the hand;

[0185] Step 354, when the inclination judgment result is no, further judge whether the angular velocity difference is greater than or equal to the second threshold value to obtain the first relative motion situation judgment result. If the first relative motion situation judgment result is yes, use the angle increment calculation model to process the quaternion angle to obtain the flexion and extension angle between the thumb and the back of the hand.

[0186] In the embodiment of the present invention, in the above step 354, the angle increment calculation model expression is:

[0187] Abgle(t)=Abgle(t-1)+(Angle hf (t)-Angle hf (t-1));

[0188] Where Angle(t) represents the flexion and extension angle between the thumb and the back of the hand at time t, Angle(t-1) represents the flexion and extension angle between the thumb and the back of the hand at time t-1, and Angle hf (t) represents the quaternion angle at time t, Angle hf (t-1) represents the quaternion angle at time t-1.

[0189] It should be noted that the first threshold is set according to the actual situation, and the function of the first threshold is to determine the tilt degree of the back of the hand. The second threshold is set according to the actual situation, and the function of the second threshold is to determine whether the thumb has a movement change relative to the back of the hand.

[0190] In the embodiment of the present invention, the first threshold is set as: 0.5<first threshold<1.

[0191] When the Z-axis component of the first preprocessed acceleration is greater than or equal to the first threshold, it means that the back of the hand is currently facing upward and the tilt is small. At this time, the Euler angle has a small follow-up, and the quaternion angle is directly used as the flexion and extension angle between the thumb and the back of the hand, that is,

[0192] Angle(t)=Angle hf (t);

[0193] When the Z-axis component of the first preprocessed acceleration is less than the first threshold, it means that the back of the hand is currently in a tilted state, and the tilt degree is relatively large (it can be understood that the roll angle or pitch angle of the back of the hand is relatively large at this time). On this basis, if the angular velocity difference is greater than or equal to the second threshold, it means that the thumb has moved relative to the back of the hand at this time, and the flexion and extension angle between the thumb and the back of the hand is calculated using the above-mentioned angle increment calculation model.

[0194] Further, in the embodiment of the present invention, if the result of the first relative motion situation judgment is no, that is, the angular velocity difference is less than the second threshold, it means that at this time, the thumb basically does not move relative to the back of the hand, and the flexion and extension angle between the thumb and the back of the hand can be ignored.

[0195] In the embodiment of the present invention, by solving the flexion and extension angle between the thumb and the back of the hand in the above manner, the accuracy of solving the flexion and extension angle can be further improved.

[0196] Further, in an optional implementation of the embodiment of the present invention, in the above step 4, the step of determining the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand includes the following steps 41 to 44:

[0197] Step 41, determining whether the angular velocity difference between the second preprocessing angular velocity and the first preprocessing angular velocity is greater than or equal to a third threshold, and obtaining a second relative motion situation determination result;

[0198] Step 42, when the second relative motion situation judgment result is yes, further judging whether the flexion and extension angle at the previous moment is greater than or equal to the flexion and extension angle at the current moment, and obtaining the flexion and extension angle change judgment result;

[0199] Step 43, if the result of the flexion and extension angle change judgment is yes, then determining that the action of the thumb is a pressing action;

[0200] Step 44: If the result of the flexion and extension angle change judgment is no, then it is determined that the action of the thumb is a lifting action.

[0201] It should be noted that the third threshold is specifically set according to actual conditions, and the value of the third threshold is greater than the value of the second threshold.

[0202] In the embodiment of the present invention, when the angular velocity difference is greater than or equal to the third threshold, it means that the thumb has a large movement change relative to the back of the hand, and the thumb action is determined according to the change in the flexion and extension angles at the previous and next moments. When the angular velocity difference is less than the third threshold, that is, the result of the second relative motion situation judgment is no, it means that the movement change of the thumb relative to the back of the hand is small, and it can be regarded that the thumb has not performed a pressing action or a lifting action.

[0203] It can be seen that the thumb motion recognition method provided by the embodiment of the present invention can realize stable recognition of thumb motions, solve the problem of stable thumb motion recognition, and can accurately detect the angle changes during the process of pressing and lifting the thumb, thereby meeting the control requirements of the actual controlled equipment.

[0204] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0205] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0206] Finally, it should be noted that the thumb motion recognition glove device and method disclosed in the embodiments of the present invention disclose only the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A thumb motion recognition glove device, characterized in that: The glove device comprises: a glove body, a first inertial sensor, a second inertial sensor, a data processing unit and a user interface; The glove body is used to be worn on a user's hand and to fix the first inertial sensor, the second inertial sensor, the data processing unit and the user interface; The first inertial sensor, the second inertial sensor and the user interface are respectively connected to the data processing unit; The first inertial sensor is disposed on the back of the glove body, and is used to collect and send a first quaternion, a first acceleration and a first angular velocity to the data processing unit; The second inertial sensor is disposed at the thumb of the glove body, and is used to collect and send a second quaternion, a second acceleration, and a second angular velocity to the data processing unit; The data processing unit is used to receive and process the first quaternion, the first acceleration, the first angular velocity, the second quaternion, the second acceleration and the second angular velocity to obtain the flexion and extension angle between the thumb and the back of the hand, and to determine the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand; The user interface can be connected to an external device for data interaction.

2. A thumb motion recognition method, characterized in that: Applied to the thumb motion recognition glove device according to claim 1, the method comprises: Acquire original data, the original data including: a first quaternion, a first acceleration, a first angular velocity, a second quaternion, a second acceleration, and a second angular velocity; Preprocessing the raw data to obtain preprocessed data, wherein the preprocessed data includes: a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity; Calculating and processing the preprocessed data to obtain the flexion and extension angle between the thumb and the back of the hand; Determine the movement of the thumb based on the changes in the flexion and extension angle between the thumb and the back of the hand.

3. The thumb motion recognition method according to claim 2, characterized in that: The obtaining of original data comprises: Initializing the glove device; Using the first inertial sensor, collecting and obtaining the first quaternion, the first acceleration, and the first angular velocity; The second quaternion, the second acceleration, and the second angular velocity are acquired by using the second inertial sensor.

4. The thumb motion recognition method according to claim 2, characterized in that: The preprocessing of the raw data to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration and a second preprocessed angular velocity includes: Performing filtering processing on the first acceleration, the first angular velocity, the second acceleration and the second angular velocity to obtain a first filtered acceleration, a first filtered angular velocity, a second filtered acceleration and a second filtered angular velocity; The first filtered acceleration, the first filtered angular velocity, the second filtered acceleration and the second filtered angular velocity are subjected to zero-bias removal processing to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration and a second preprocessed angular velocity.

5. The thumb motion recognition method according to claim 4, characterized in that: The filtering the first acceleration, the first angular velocity, the second acceleration and the second angular velocity to obtain a first filtered acceleration, a first filtered angular velocity, a second filtered acceleration and a second filtered angular velocity comprises: Preprocessing the first acceleration and the first angular velocity using a first data preprocessing model to obtain a first filtered acceleration and a first filtered angular velocity; Preprocessing the second acceleration and the second angular velocity by using the first data preprocessing model to obtain a second filtered acceleration and a second filtered angular velocity; The first data preprocessing model expression is: Wherein, i represents the inertial sensor index, i=1, 2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th filtered acceleration at time t, a i，(x，y，z) (tj) represents the i-th acceleration at time tj, pi represents the acceleration correction coefficient, represents the i-th filtered angular velocity at time t, ω i，(x，y，z) (tj) represents the angular velocity of the i-th moment tj, b i represents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, N represents the number of sampling points, j represents the sampling point index, and tj represents the last sampling time before t.

6. The thumb motion recognition method according to claim 4, characterized in that: The step of performing a zero-bias removal process on the first filtered acceleration, the first filtered angular velocity, the second filtered acceleration, and the second filtered angular velocity to obtain a first preprocessed acceleration, a first preprocessed angular velocity, a second preprocessed acceleration, and a second preprocessed angular velocity includes: Preprocessing the first filtered acceleration and the first filtered angular velocity by using a second data preprocessing model to obtain a first preprocessed acceleration and a first preprocessed angular velocity; Preprocessing the second filtered acceleration and the second filtered angular velocity by using the second data preprocessing model to obtain a second preprocessed acceleration and a second preprocessed angular velocity; The second data preprocessing model expression is: Wherein, i represents the inertial sensor index, i=1, 2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the i-th preprocessed acceleration at time t, represents the i-th filtered acceleration at time t, a i，(x，y，z) (tj) represents the i-th acceleration at time tj, p i represents the acceleration correction factor, represents the i-th preprocessed angular velocity at time t, represents the i-th filtered angular velocity at time t, ω i，(x，y，z) (tj) represents the angular velocity of the i-th moment tj, b i represents the angular velocity correction coefficient, x represents the X-axis of the inertial sensor, y represents the Y-axis of the inertial sensor, z represents the Z-axis of the inertial sensor, M represents the number of sampling points, j represents the sampling point index, and tj represents the jth sampling time before time t.

7. The thumb motion recognition method according to claim 2, characterized in that: The calculating and processing the preprocessed data to obtain the flexion and extension angle between the thumb and the back of the hand includes: Normalizing the first quaternion and the second quaternion to obtain a first normalized quaternion and a second normalized quaternion; Performing bias calculation on the first normalized quaternion and the second normalized quaternion to obtain a biased quaternion; Using a quaternion angle calculation model, the biased quaternion is calculated and processed to obtain a quaternion angle between the thumb and the back of the hand; Using an angular velocity difference calculation model, calculating and processing the first preprocessed angular velocity and the second preprocessed angular velocity to obtain an angular velocity difference; The first preprocessed acceleration, the quaternion angle and the angular velocity difference are processed to obtain a flexion and extension angle between the thumb and the back of the hand.

8. The thumb motion recognition method according to claim 7, characterized in that: The normalization expression is: Wherein, i represents the inertial sensor index, i=1, 2, i=1 corresponds to the first inertial sensor, i=2 corresponds to the second inertial sensor, represents the j+1th element component of the i-th normalized quaternion, j = 0, 1, 2, 3, q i，j represents the j+1th element component of the i-th quaternion, β i Represents the quaternion correction coefficient, q i，0 Represents the first element component of the i-th quaternion, q i，1 Represents the second component of the i-th quaternion, q i , 2 represents the third component of the i-th quaternion, q i , 3 represents the 4th component of the i-th quaternion; The bias calculation expression is: Among them, Q(t) represents the bias quaternion at time t, represents the first normalized quaternion at time t, Represents the second normalized quaternion at time t, express The inverse operation of The quaternion angle calculation model expression is: Among them, Angle hf (t) represents the quaternion angle at time t, π represents pi, Q0(t) represents the first component of the biased quaternion at time t, Q1(t) represents the second component of the biased quaternion at time t, Q2(t) represents the third component of the biased quaternion at time t, Q3(t) represents the fourth component of the biased quaternion at time t, arctan represents the calculation of the inverse tangent trigonometric function; The angular velocity difference calculation model expression is: Among them, ω_c(t) represents the angular velocity difference at time t, represents the second pre-processed angular velocity X-axis component at time t, represents the second pre-processed angular velocity Y-axis component at time t, represents the second pre-processed angular velocity Z-axis component at time t, represents the first preprocessed angular velocity X-axis component at time t, represents the first preprocessed angular velocity Y-axis component at time t, Represents the first pre-processed angular velocity Z-axis component at time t.

9. The thumb motion recognition method according to claim 8, characterized in that: The processing of the first preprocessed acceleration, the quaternion angle and the angular velocity difference to obtain the flexion and extension angle between the thumb and the back of the hand includes: Analyzing the first preprocessed acceleration to obtain a first preprocessed acceleration Z-axis component; Determine whether the Z-axis component of the first preprocessed acceleration is greater than or equal to a first threshold value, and obtain a tilt determination result; When the tilt determination result is yes, the quaternion angle is used as the flexion and extension angle between the thumb and the back of the hand; When the inclination judgment result is no, further judging whether the angular velocity difference is greater than or equal to a second threshold value, and obtaining a first relative motion judgment result; if the first relative motion judgment result is yes, processing the quaternion angle by using an angle increment calculation model, and obtaining a flexion and extension angle between the thumb and the back of the hand; The angle increment calculation model expression is: Angle(t)=Angle(t-1)+(Angle hf (t)-Angle hf (t-1)); Where Angle(t) represents the flexion and extension angle between the thumb and the back of the hand at time t, Angle(t-1) represents the flexion and extension angle between the thumb and the back of the hand at time t-1, and Angle hf (t) represents the quaternion angle at time t, Angle hf (t-1) represents the quaternion angle at time t-1.

10. The thumb motion recognition method according to claim 2 or 9, characterized in that: Determining the movement of the thumb according to the change of the flexion and extension angle between the thumb and the back of the hand includes: Determine whether the angular velocity difference between the second preprocessing angular velocity and the first preprocessing angular velocity is greater than or equal to a third threshold, and obtain a second relative motion situation determination result; When the result of the second relative motion situation judgment is yes, further judging whether the flexion and extension angle at the previous moment is greater than or equal to the flexion and extension angle at the current moment, and obtaining a flexion and extension angle change judgment result; If the result of the flexion and extension angle change judgment is yes, determining that the action of the thumb is a pressing action; If the flexion and extension angle change judgment result is no, then it is determined that the action of the thumb is a lifting action.

Images