Sensor position sensing method and device for intelligent clothing, clothing and product
By integrating IMU sensors in smart clothing cuffs and leveraging zero-speed detection and long-term memory models, the problems of sensor position offset and fabric motion artifacts in smart clothing are solved, improving measurement accuracy and natural interaction experience.
Patent Information
- Application Number
- CN202411471070.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2025-03-14
- Estimated Expiration
- 2044-10-21
AI Technical Summary
Sensor position shifts and fabric motion artifacts in smart clothing lead to a decrease in measurement accuracy and natural interaction experience, and existing IMU positioning methods accumulate errors in small-scale motion and are not applicable.
The IMU sensor is integrated in the cuffs of smart clothing, and the acceleration, angular velocity and rotational orientation data are obtained in real time, the motion state is judged through the zero-speed detection method, and the cuff height changes are predicted using a long and short-term memory model.
It improves the measurement accuracy of the sensor in small-scale motion, improves the measurement accuracy and natural interactive experience of smart clothing, and realizes accurate prediction of cuff operation and height changes.
Smart Images

Figure CN119618200A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart clothing, and in particular to a sensor position sensing method, device, clothing and product for smart clothing. Background Art
[0002] In recent years, smart wearable systems that incorporate wearable sensors such as pressure sensors, tension sensors, fiber optic sensors, and inertial sensors have been widely studied to achieve functions such as motion capture, health monitoring, and human-computer interaction. The advantages of these smart garments are that they are not blocked and have no restrictions on the range of motion, so users can use them freely and comfortably for a long time. However, in order to ensure the accuracy of sensor measurements in smart clothing, the sensors must be placed in the correct position. However, due to the characteristics of smart clothing itself, problems such as sensor position offset and motion artifacts of the fabric itself are still challenges facing smart clothing technology.
[0003] Traditional IMU positioning methods determine the position by converting the IMU's acceleration from the local coordinate system to the global coordinate system and performing double integration after removing the gravity acceleration, but this method causes the error to accumulate over time and quickly makes the result invalid. Therefore, it is usually necessary to impose additional constraints on the movement of the IMU itself to correct the error, such as through pedestrian gait analysis. Data-driven IMU positioning methods use deep learning technology to track the position of the IMU, which is usually used for large-scale positioning of pedestrians. Its error is measured in meters and is not suitable for the small-scale movement of sensors on smart clothing.
[0004] In addition, existing IMU position calculation methods often require the combination of multiple IMUs or IMUs with other sensors to reduce data drift. On smart clothing, the position detection of a single IMU is usually fixed on the sole to reduce the position tracking error through some characteristics of human walking motion. However, this solution is not suitable for the small-scale movement of sensors in smart clothing. Summary of the invention
[0005] The embodiments of the present invention provide a sensor position perception method, device, clothing and product for smart clothing to achieve accurate prediction of cuff operation and height changes, improve the measurement accuracy of the sensor in small-scale motion, and further enhance the measurement accuracy and natural interaction experience of smart clothing.
[0006] In order to achieve the above object, on the one hand, a sensor position sensing method for smart clothing is provided, wherein an IMU sensor is integrated in the cuff of the smart clothing, and the method comprises:
[0007] Acquire measurement data of the IMU sensor in real time, wherein the measurement data includes acceleration data, angular velocity data, and rotation orientation data;
[0008] Determine, by a zero-speed detection method, whether each frame of acceleration data in the measurement data is acceleration data when the IMU sensor is in a moving state or acceleration data when the IMU sensor is in a stationary state;
[0009] When there are acceleration data of a predetermined number of consecutive frames in the measurement data, which are acceleration data of the IMU sensor in a motion state, the measurement data of the predetermined number of consecutive frames are used as motion data;
[0010] The current number of cuff folding times is calculated according to the motion data, and the current number of cuff folding times is compared with the number of cuff folding times calculated last time to see if there is any change; if there is any change, the motion type of the motion data is cuff folding, and the first height change value of the IMU sensor relative to the reference point is estimated according to the current number of cuff folding times and the preset value of each cuff folding, wherein the reference point is the initial position of the IMU sensor; if there is no change, a first predetermined number of frames of data are taken forward from the end of the motion data as the first data, the first data is preprocessed according to a predetermined first processing rule, and the preprocessed first data is input into a pre-trained first long short-term memory model to obtain the motion type of the motion data; wherein the motion types of the motion data include: cuff pulling and cuff falling;
[0011] When the motion type of the motion data is cuff pulling, the motion data is divided to obtain a plurality of second data, wherein each second data includes a second predetermined number of frames of motion data, the plurality of second data are preprocessed according to a predetermined second processing rule, and the plurality of preprocessed second data are respectively input into a pre-trained second long short-term memory model to obtain a plurality of second height change values of the IMU sensor relative to the reference point;
[0012] The first height change value is added to the multiple second height change values to obtain a current height change value of the IMU sensor relative to the reference point.
[0013] Preferably, according to the sensor position sensing method, determining whether each frame of acceleration data in the measurement data is acceleration data when the IMU sensor is in motion or acceleration data when the IMU sensor is in a stationary state by a zero speed detection method includes:
[0014] Calculate the acceleration variance of a predetermined number of windows. When the acceleration variance is greater than or equal to a predetermined threshold, the acceleration data of the current frame is in motion; when the acceleration variance is less than the predetermined threshold, the acceleration data of the current frame is in a stationary state. The window length of the window is preset, and the unit of the acceleration data is preset.
[0015] Preferably, according to the sensor position sensing method, calculating the current cuff folding times according to the motion data comprises:
[0016] Constructing a three-dimensional coordinate system according to the initial frame data in the motion data, wherein the three-dimensional coordinate system includes x, y, and z axes, the x axis and the y axis are two axes in the horizontal direction, and the z axis is an axis in the vertical direction; and projecting the orientation of the IMU sensor onto the xz plane of the three-dimensional coordinate system;
[0017] Calculate the rotation angle of each frame of motion data in the motion data relative to the y-axis, and then accumulate the rotation angles to obtain the total rotation angle of the motion data, where:
[0018]
[0019] Δθ k represents the rotation angle of the kth frame data in the motion data, θ k Represents the total rotation angle, V k Represents the rotation vector of the k-th frame data in the motion data, V′ k V represents the rotation vector of the k-th frame data in the motion data projected on the xz plane; k-1 Represents the rotation vector of the k-1th frame data in the motion data, V′ k-1 represents a rotation vector of the k-1th frame data in the motion data projected on the xz plane; wherein the k-1th frame data is the previous frame data of the kth frame data in the motion data;
[0020] The number of cuff folding times is calculated by the total rotation angle, where:
[0021]
[0022] T k Indicates the number of times the cuff is folded.
[0023] Preferably, according to the sensor position sensing method, preprocessing the first data or the second data includes:
[0024] When the coordinate system of the first data or the second data is the IMU sensor coordinate system:
[0025] When the unit of the acceleration data is m / s 2 , scaling the acceleration data according to a first predetermined ratio;
[0026] When the unit of the angular velocity data is rad / s, scaling the angular velocity data according to a second predetermined ratio;
[0027] When the cuff folding times is an odd number, the x-axis and z-axis data of the acceleration data and the angular velocity data are inverted;
[0028] When the IMU sensor is integrated into the cuff of the left hand, the y-axis data of the acceleration data is inverted, and the x-axis and z-axis data of the angular velocity data are inverted.
[0029] Preferably, according to the sensor position sensing method, the preprocessing of the first data also includes: when the number of frames of the motion data is less than the first predetermined number of frames, the data after the end of the motion data and in a static state is used to splice after the motion data to complete the process.
[0030] Preferably, according to the sensor position sensing method, the preprocessing of the second data also includes: when the frame number of the motion data is less than the second predetermined frame number, evenly supplementing the data in a static state before and after the motion data until the frame number of the motion state is equal to the second predetermined frame number.
[0031] Preferably, according to the sensor position perception method, wherein the loss function of the first long short-term memory model is a cross entropy function, and the activation function is a ReLU function;
[0032] The loss function of the second long short-term memory model is a mean square error loss function, and the activation function is a ReLU function.
[0033] On the other hand, the present invention provides a sensor position sensing device for smart clothing, which includes a memory and a processor, the memory stores at least one program, and the at least one program is executed by the processor to implement any of the sensor position sensing methods described above.
[0034] On the other hand, the present invention provides a smart clothing, comprising: an IMU sensor integrated in the cuff; and a sensor position sensing device for smart clothing as described above.
[0035] In yet another aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the sensor position sensing method as described above is implemented.
[0036] The above technical solution has the following technical effects:
[0037] The technical solution of the embodiment of the present invention integrates an IMU sensor in the cuff of the smart clothing to obtain multi-axis measurement data including acceleration, angular velocity and rotation direction in real time, and uses the zero velocity detection method (AMVD: Acceleration-Moving Variance A motion detector is used to determine the motion state of each frame of acceleration data; when it is detected that the acceleration data of a predetermined number of consecutive frames are in a motion state, the data of this segment is extracted as motion data; and the current cuff folding times are calculated, and the type of motion data is determined to be cuff folding by comparing the change of the current cuff folding times with the cuff folding times calculated last time. If the folding times are changed, the type is determined to be cuff folding, and the first height change value of the IMU sensor relative to the reference point is estimated according to the pre-stored cuff height data, wherein the reference point is the initial position of the IMU sensor; otherwise, the data of the first predetermined number of frames are extracted from the end of the motion data as the first data, and the first data are pre-processed and input into a trained first long short-term memory (LSTM) model according to a predetermined first processing rule to determine the type of the cuff; when the type is identified as cuff pulling, the motion data is divided to obtain a plurality of second data, wherein each second data includes the motion data of the second predetermined number of frames, and the plurality of second data are pre-processed and input into a second long short-term memory (LSTM) model according to a predetermined second processing rule to obtain a plurality of second height change values of the IMU sensor relative to the reference point. Finally, the first height change value and the multiple second height change values are added to obtain the height change value of the current IMU sensor relative to the reference point. This achieves accurate prediction of the cuff height change and improves the user experience and accuracy of smart clothing in natural interaction.
[0038] In a further embodiment, by preprocessing the acceleration data and angular velocity data in the motion data, including scaling the data proportionally and adjusting the data direction according to the placement of the sensor, it is ensured that no matter how the cuff is folded or on which arm it is worn, the operation of the cuff can be accurately reflected, allowing the smart clothing to maintain good measurement accuracy without strictly limiting the placement of the sensor, thereby making the smart clothing closer to ordinary clothing worn daily.
[0039] In a further embodiment, by supplementing the static state data when the data is insufficient, all data segments can meet the model input requirements, thereby improving the model's prediction accuracy of the cuff operation type (such as folding or pulling) and its height changes, and ultimately achieving highly accurate tracking of smart clothing sleeve operations, enhancing the practicality and user experience of smart clothing. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A schematic diagram of a flow chart of a sensor position sensing method for smart clothing according to an embodiment of the present invention;
[0041] Figure 2 This is a schematic diagram of the result of using AMVD to perform motion state detection on each frame of acceleration data in the measurement data in a sensor position sensing method for smart clothing according to an embodiment of the present invention;
[0042] Figure 3 A schematic diagram of cuff operation classification and cuff pulling distance prediction in a sensor position sensing method for smart clothing according to an embodiment of the present invention;
[0043] Figure 4 A flow chart of cuff height change when the motion type is cuff pulling in a sensor position sensing method for smart clothing according to an embodiment of the present invention;
[0044] Figure 5 A diagram of a sensor position sensing device for smart clothing according to an embodiment of the present invention. DETAILED DESCRIPTION
[0045] To further illustrate the various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, a person of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.
[0046] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.
[0047] Embodiment 1:
[0048] In order to achieve accurate prediction of cuff operation and height change, improve the measurement accuracy of sensors in small-scale motion, and thereby enhance the measurement accuracy and natural interaction experience of smart clothing, an embodiment of the present invention provides a sensor position perception method for smart clothing. Figure 1 FIG. 1 is a flow chart of a sensor position sensing method for smart clothing according to an embodiment of the present invention. Figure 1 As shown, the IMU sensor is integrated into the cuff of the smart clothing, including:
[0049] Acquire the measurement data of the IMU sensor in real time, wherein the measurement data includes acceleration data, angular velocity data and rotation direction data;
[0050] The zero-speed detection method is used to determine whether each frame of acceleration data in the measurement data is acceleration data when the IMU sensor is in a moving state or acceleration data when the IMU sensor is in a stationary state;
[0051] When there are acceleration data of a predetermined number of consecutive frames in the measurement data, which are acceleration data of the IMU sensor in motion, the measurement data of the predetermined number of consecutive frames are used as motion data;
[0052] Calculate the current number of cuff folding times according to the motion data, and compare the current number of cuff folding times with the number of cuff folding times calculated last time to see if there is any change; if there is any change, the motion type of the motion data is cuff folding, and estimate the first height change value of the IMU sensor relative to the reference point according to the current number of cuff folding times and the preset value of each cuff folding, wherein the reference point is the initial position of the IMU sensor; if there is no change, take out the data of the first predetermined number of frames from the end of the motion data as the first data, pre-process the first data according to the predetermined first processing rule, and input the pre-processed first data into the pre-trained first long short-term memory model to obtain the motion type of the motion data; wherein the motion types of the motion data include: cuff pulling and cuff falling;
[0053] When the motion type of the motion data is cuff pulling, the motion data is divided to obtain a plurality of second data, wherein each second data includes a second predetermined number of frames of motion data, the plurality of second data are preprocessed according to a predetermined second processing rule, and the plurality of preprocessed second data are respectively input into a pre-trained second long short-term memory model to obtain a plurality of second height change values of the IMU sensor relative to the reference point;
[0054] The first height change value is added to the plurality of second height change values to obtain a height change value of the current IMU sensor relative to the reference point.
[0055] Embodiment 2:
[0056] Existing IMU position calculations usually require the combination of multiple IMUs or fusion with other sensors to reduce data drift problems. In the application scenario of a single IMU, a common practice is to fix it on the sole and use the characteristics of human walking motion to reduce the error of human position tracking. However, this gait-based method is not suitable for the position detection needs of sensors on smart clothing in small-scale motion.
[0057] Therefore, an embodiment of the present invention provides a sensor position perception method for smart clothing, which uses supervised learning and trains an LSTM model to predict the height change of the IMU sensor relative to the initial position of the IMU sensor in a moving state. The method includes:
[0058] 1. Obtain measurement data from the IMU sensor in real time.
[0059] Preferably, the measurement data includes acceleration data, angular velocity data and rotation orientation data, a total of 9-axis data.
[0060] Preferably, the IMU sensor is fixed on the cuff of the smart garment by sewing a small pocket on the cuff.
[0061] In a specific implementation, the IMU sensor collects and transmits data at a sampling rate of 60 Hz.
[0062] 2. Use the zero velocity detection (AMVD) method to determine whether each frame of acceleration data in the measurement data is the acceleration data when the IMU sensor is in a moving state or the acceleration data when the IMU sensor is in a stationary state.
[0063] Preferably, Figure 2 This is a schematic diagram of the result of using AMVD to detect the motion state of each frame of acceleration data in the measurement data in the sensor position sensing method for smart clothing according to an embodiment of the present invention. Figure 2 As shown, the acceleration variance of a predetermined number of windows is calculated. When the acceleration variance is greater than or equal to a predetermined threshold, the acceleration data of the current frame is in motion; when the acceleration variance is less than the predetermined threshold, the acceleration data of the current frame is in a stationary state; wherein the window length of the window is preset, and the unit of the acceleration data is preset.
[0064] In a specific implementation, the window length of AMVD is set to 30 frames and the acceleration unit is set to m / s 2 , the threshold is set to 0.08, where each frame of acceleration data in the measurement data will be included in 30 different windows. If any of the windows is considered to be stationary by AMVD, the acceleration data of this frame is considered to be stationary.
[0065] In a specific implementation, the measurement data containing m frames of data is used as X m , where the tth frame data is x t , use AMVD to determine whether the IMU sensor is currently moving.
[0066] 3. When there are acceleration data of a predetermined number of consecutive frames in the measurement data, which are acceleration data of the IMU sensor in motion, the measurement data of the predetermined number of consecutive frames are used as motion data.
[0067] Preferably, the continuous predetermined number of frames is 30 frames.
[0068] 4. Calculate the current cuff folding times according to the motion data, and compare the current cuff folding times with the last calculated cuff folding times to see if they have changed;
[0069] If there is a change, the motion type of the motion data is cuff folding, and the first height change value of the IMU sensor relative to the reference point is estimated according to the current number of cuff folding times and the preset value of each cuff folding, wherein the reference point is the initial position of the IMU sensor;
[0070] If there is no change, take out a first predetermined number of frames of data from the end of the motion data as the first data, preprocess the first data according to a predetermined first processing rule, and input the preprocessed first data into a pre-trained first long short-term memory model to obtain the motion type of the motion data; preferably, the first predetermined number of frames is 60 frames; preferably, the motion types of the motion data include: cuff pulling and cuff falling.
[0071] Figure 3 The present invention is a schematic diagram of the operation classification of cuffs and the prediction of the cuff pulling distance in the sensor position sensing method for smart clothing in one embodiment of the present invention. The operation classification of the cuffs corresponds to the motion type of the motion data; the cuff pulling distance corresponds to the height change value of the IMU sensor set in the cuff relative to the selected reference point. Preferably, the reference point is the initial position of the IMU sensor. Specifically, as Figure 3 As shown, the operation classification of the sleeve includes: pulling the cuff to fold the cuff and letting the cuff fall naturally under the action of gravity; the pulling distance of the cuff is the distance between the position of the cuff provided with the IMU sensor after the corresponding operation and the initial position of the cuff after the clothes are put on. In a specific implementation, the cuff pulling distance is used to represent the height change value of the IMU sensor relative to the selected reference point.
[0072] In a specific implementation, calculating the current cuff folding times according to the motion data includes: constructing a three-dimensional coordinate system according to the initial frame data in the motion data, and projecting the orientation of the IMU sensor on the xz plane of the three-dimensional coordinate system; preferably, the three-dimensional coordinate system includes x, y, and z axes, the x axis and the y axis are two axes in the horizontal direction, and the z axis is an axis in the vertical direction;
[0073] The rotation angle of each frame of motion data relative to the y-axis is calculated, and the obtained rotation angles are accumulated to obtain the total rotation angle of the motion data, and then the number of cuff folding times is calculated by the total rotation angle; preferably, the total rotation angle and the number of cuff folding times are calculated by the following formula:
[0074]
[0075] Δθ kRepresents the rotation angle of the kth frame data in the motion data, θ k Represents the total rotation angle, V k Represents the rotation vector of the kth frame of motion data, V′ k V represents the rotation vector of the k-th frame of motion data projected on the xz plane; k-1 Represents the rotation vector of the k-1th frame of motion data, V′ k-1 represents the rotation vector of the k-1 frame data in the motion data projected on the xz plane; wherein the k-1 frame data is the previous frame data of the k-1 frame data in the motion data;
[0076] The number of cuff folds is calculated from the total rotation angle, where:
[0077]
[0078] T k Indicates the number of times the cuffs are folded.
[0079] Preferably, the number of folding times of the cuff at the final k-th frame is represented by the result of dividing the rotation angle by π and rounding off.
[0080] In a specific implementation, the first processing rule includes: when the coordinate system of the first data is an IMU sensor coordinate system; and / or,
[0081] When the unit of acceleration data is m / s 2 When the unit of the angular velocity data is rad / s, the angular velocity data is scaled according to a second predetermined ratio, so as to perform preliminary standardization on the data; preferably, the first predetermined ratio is 1 / 30; preferably, the second predetermined ratio is 1 / 10;
[0082] When the IMU sensor is placed 180° in the opposite direction around the y-axis, that is, when the cuff is folded an odd number of times, the x-axis and z-axis data of the acceleration data and angular velocity data are inverted to compensate for the data difference before and after the folding;
[0083] When the IMU sensor is integrated into the cuff of the left hand, the y-axis data of the acceleration data is inverted, and the x-axis and z-axis data of the angular velocity data are inverted to compensate for the data difference between the left and right hands;
[0084] When the frame number of the motion data is less than the first predetermined frame number, the data after the end of the motion data and in a static state is spliced and filled after the motion data to make up for the length of all data to maintain the first predetermined frame number.
[0085] Preferably, the first long short-term memory model is used as a model for classifying motion types, the loss function is a cross entropy function, and the activation function is a ReLU function; wherein, the loss function is used to measure the difference between the model prediction value and the true value, and optimize the model parameters by minimizing this difference; the activation function introduces nonlinear characteristics, so that the neural network can learn and represent complex function mappings; the loss function of the first long short-term memory model is the cross entropy function, which measures the difference between two probability distributions and is widely used in classification problems; the ReLU function used is a common activation function, which has a fast calculation speed, can alleviate the problem of gradient disappearance, and helps to improve the sparsity of the model.
[0086] In a specific implementation, the input data of the first long short-term memory model includes acceleration data and angular velocity data of the motion data within the last 60 frames after being processed by a predetermined first processing rule. Only the last 60 frames of data are used because the main difference between the motion data of the cuff pulling type and the cuff falling type lies in the data regularity at the end of the motion.
[0087] 5. When the motion type of the motion data is cuff pulling, the motion data is divided to obtain a plurality of second data, wherein each second data includes motion data of a second predetermined number of frames, the plurality of second data are preprocessed according to a predetermined second processing rule, and the plurality of preprocessed second data are respectively input into a pre-trained second long short-term memory model to obtain a plurality of second height change values of the IMU sensor relative to the reference point. Preferably, the second predetermined number of frames is 60 frames.
[0088] In a specific implementation, the second processing rule includes: when the coordinate system of the second data is an IMU sensor coordinate system; and / or,
[0089] When the unit of acceleration data is m / s 2 When the unit of the angular velocity data is rad / s, the angular velocity data is scaled according to a second predetermined ratio, so as to perform preliminary standardization on the data; preferably, the first predetermined ratio is 1 / 30; preferably, the second predetermined ratio is 1 / 10;
[0090] When the IMU sensor is placed 180° in the opposite direction around the y-axis, that is, when the cuff is folded an odd number of times, the x-axis and z-axis data of the acceleration data and angular velocity data are inverted to compensate for the data difference before and after the folding;
[0091] When the IMU sensor is integrated into the cuff of the left hand, the y-axis data of the acceleration data is inverted, and the x-axis and z-axis data of the angular velocity data are inverted to compensate for the data difference between the left and right hands;
[0092] When the number of frames of the motion data is less than the second predetermined number of frames, the static data are evenly supplemented before and after the motion data until the number of frames of the motion state is equal to the second predetermined number of frames. Preferably, when the motion data cannot be divided into multiple complete 60-frame windows, that is, when the window length is not a multiple of 60, static data are additionally supplemented before and after the motion data; for example, if a certain segment of motion data has 201 frames and it is divided into 4 windows with 39 frames less, 20 frames of static data are supplemented before the start of the motion data, and 19 frames of static data are supplemented at the end of the motion data, so as to ensure that a segment of data can be divided into several complete 60-frame windows.
[0093] Preferably, the loss function of the second long short-term memory model is a mean square error loss function, and the activation function is a ReLU function; the mean square error loss function used is used to calculate the mean of the square error, which is more suitable for regression problems, especially when the output is a continuous value.
[0094] In a specific implementation, Figure 4 This is a flow chart of the change in cuff height when the motion type is cuff pulling in a sensor position sensing method for smart clothing according to an embodiment of the present invention. Figure 4 As shown, the motion data segment is divided into multiple windows of 60 frames in length, the input data includes acceleration data and angular velocity data of the motion data within 60 frames after being processed by a predetermined second processing rule, and the output prediction result is the height change value of the IMU sensor relative to the reference point in 60 frames, in centimeters.
[0095] 6. Add the first height change value to the multiple second height change values to obtain the height change value of the current IMU sensor relative to the reference point.
[0096] In a specific implementation, for a continuous IMU data stream, the IMU data stream is divided into a static state and a motion state, the IMU data that is continuously in motion is used as motion data, and a predetermined algorithm is used to distinguish the motion data into three types: the user folds (such as rolls up) the cuffs, the cuffs naturally fall under the action of gravity, and the user pulls the cuffs. Among them, if the motion data is detected as a motion type in which the user pulls the cuffs, a deep learning method is used to predict the distance change of the IMU sensor relative to the initial position of the IMU sensor.
[0097] The above method in the embodiment of the present invention uses a deep learning method to achieve end-to-end IMU sensor height change prediction based on the rules of the user's sleeve operation when wearing smart clothing, thereby solving the problem that the existing IMU positioning solution cannot be used for small-scale movement of sensors on smart clothing, and realizing high-precision sensor position adaptive perception for natural interaction with smart clothing.
[0098] Embodiment three:
[0099] The present invention also provides a sensor position sensing device for smart clothing, such as Figure 5 As shown, the device includes a processor 501, a memory 502, a bus 503, and a computer program stored in the memory 502 and executable on the processor 501. The processor 501 includes one or more processing cores. The memory 502 is connected to the processor 501 via the bus 503. The memory 502 is used to store program instructions. When the processor executes the computer program, the steps in the above method embodiment of the first embodiment of the present invention are implemented.
[0100] Further, as an executable solution, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, and various interfaces and lines are used to connect the various parts of the entire computer unit.
[0101] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the computer unit by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0102] Embodiment 4:
[0103] The present invention also provides a smart clothing, comprising: an IMU sensor integrated in a cuff; and a sensor position sensing device for smart clothing as described above.
[0104] Embodiment five:
[0105] The present invention also provides a computer program product, comprising a computer program, and when the computer program is executed by a processor, the method described above is implemented.
[0106] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.
Claims
1. A sensor position sensing method for smart clothing, characterized in that: The IMU sensor is integrated into the cuff of the smart clothing, including: Acquire measurement data of the IMU sensor in real time, wherein the measurement data includes acceleration data, angular velocity data, and rotation orientation data; Determine, by a zero-speed detection method, whether each frame of acceleration data in the measurement data is acceleration data when the IMU sensor is in a moving state or acceleration data when the IMU sensor is in a stationary state; When there are acceleration data of a predetermined number of consecutive frames in the measurement data, which are acceleration data of the IMU sensor in a motion state, the measurement data of the predetermined number of consecutive frames are used as motion data; The current number of cuff folding times is calculated according to the motion data, and the current number of cuff folding times is compared with the number of cuff folding times calculated last time to see if there is any change; if there is any change, the motion type of the motion data is cuff folding, and the first height change value of the IMU sensor relative to the reference point is estimated according to the current number of cuff folding times and the preset value of each cuff folding, wherein the reference point is the initial position of the IMU sensor; if there is no change, a first predetermined number of frames of data are taken forward from the end of the motion data as the first data, the first data is preprocessed according to a predetermined first processing rule, and the preprocessed first data is input into a pre-trained first long short-term memory model to obtain the motion type of the motion data; wherein the motion types of the motion data include: cuff pulling and cuff falling; When the motion type of the motion data is cuff pulling, the motion data is divided to obtain a plurality of second data, wherein each second data includes a second predetermined number of frames of motion data, the plurality of second data are preprocessed according to a predetermined second processing rule, and the plurality of preprocessed second data are respectively input into a pre-trained second long short-term memory model to obtain a plurality of second height change values of the IMU sensor relative to the reference point; The first height change value is added to the multiple second height change values to obtain a current height change value of the IMU sensor relative to the reference point.
2. The sensor position sensing method according to claim 1, characterized in that: Determining whether each frame of acceleration data in the measurement data is acceleration data when the IMU sensor is in motion or acceleration data when the IMU sensor is in a stationary state by a zero speed detection method includes: Calculate the acceleration variance of a predetermined number of windows. When the acceleration variance is greater than or equal to a predetermined threshold, the acceleration data of the current frame is in motion; when the acceleration variance is less than the predetermined threshold, the acceleration data of the current frame is in a stationary state. The window length of the window is preset, and the unit of the acceleration data is preset.
3. The sensor position sensing method according to claim 1, characterized in that: Calculating the current cuff folding times according to the motion data includes: Constructing a three-dimensional coordinate system according to the initial frame data in the motion data, wherein the three-dimensional coordinate system includes x, y, and z axes, the x axis and the y axis are two axes in the horizontal direction, and the z axis is an axis in the vertical direction; and projecting the orientation of the IMU sensor onto the xz plane of the three-dimensional coordinate system; Calculate the rotation angle of each frame of motion data in the motion data relative to the y-axis, and then accumulate the rotation angles to obtain the total rotation angle of the motion data, where: Δθ k represents the rotation angle of the kth frame data in the motion data, θ k Represents the total rotation angle, V k Represents the rotation vector of the k-th frame data in the motion data, V′ k V represents the rotation vector of the k-th frame data in the motion data projected on the xz plane; k-1 Represents the rotation vector of the k-1th frame data in the motion data, V′ k-1 represents a rotation vector of the k-1th frame data in the motion data projected on the xz plane; wherein the k-1th frame data is the previous frame data of the kth frame data in the motion data; The number of cuff folding times is calculated by the total rotation angle, where: T k Indicates the number of times the cuff is folded.
4. The sensor position sensing method according to claim 1, characterized in that: Preprocessing the first data or the second data includes: When the coordinate system of the first data or the second data is the IMU sensor coordinate system: When the unit of the acceleration data is m / s 2 , scaling the acceleration data according to a first predetermined ratio; When the unit of the angular velocity data is rad / s, scaling the angular velocity data according to a second predetermined ratio; When the cuff folding times is an odd number, the x-axis and z-axis data of the acceleration data and the angular velocity data are inverted; When the IMU sensor is integrated into the cuff of the left hand, the y-axis data of the acceleration data is inverted, and the x-axis and z-axis data of the angular velocity data are inverted.
5. The sensor position sensing method according to claim 1, characterized in that: Preprocessing the first data also includes: when the number of frames of the motion data is less than the first predetermined number of frames, using data after the end of the motion data and in a static state to splice after the motion data to complete the process.
6. The sensor position sensing method according to claim 1, characterized in that: Preprocessing the second data also includes: when the frame number of the motion data is less than the second predetermined frame number, evenly supplementing the static state data before and after the motion data until the frame number of the motion state is equal to the second predetermined frame number.
7. The sensor position sensing method according to claim 1, characterized in that: The loss function of the first long short-term memory model is a cross entropy function, and the activation function is a ReLU function; The loss function of the second long short-term memory model is a mean square error loss function, and the activation function is a ReLU function.
8. A sensor position sensing device for smart clothing, characterized in that: The method comprises a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement the sensor position sensing method according to any one of claims 1 to 7.
9. A smart garment, characterized in that: include: IMU sensor integrated in the cuff; And, a sensor position sensing device for smart clothing as described in claim 8.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the sensor position sensing method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
User movement detection for verifying trust between computing devices
CN112673373A
User movement detection for verifying trust between computing devices
WO2021034299A1
