CN116189383A - Fall and similar action early warning method based on inertial sensing - Google Patents
Fall and similar action early warning method based on inertial sensing Download PDFInfo
- Publication number
- CN116189383A CN116189383A CN202310197548.9A CN202310197548A CN116189383A CN 116189383 A CN116189383 A CN 116189383A CN 202310197548 A CN202310197548 A CN 202310197548A CN 116189383 A CN116189383 A CN 116189383A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- acceleration
- axis
- world coordinate
- triaxial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/0423—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting deviation from an expected pattern of behaviour or schedule
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Abstract
The invention discloses a fall and similar action early warning method based on inertial sensing. The method comprises the following steps: acquiring a triaxial acceleration signal and a triaxial angular velocity signal of a target under a machine body coordinate system, and calculating a combined acceleration; according to the mapping relation between the machine body coordinate system and the world coordinate system, a triaxial acceleration signal and a triaxial angular velocity signal of the world coordinate system are obtained; calculating triaxial motion acceleration under a world coordinate system; judging whether the target is in a weightlessness state or not by comparing the combined acceleration with a set threshold value; and under the condition that the target is in a weightlessness state, carrying out falling early warning according to the instantaneous displacement in the vertical direction and/or the variation of the inclination angle, wherein the instantaneous displacement is obtained based on the movement speed and the movement acceleration of the target in the vertical direction, and the variation of the inclination angle is obtained based on the angular speed signals of the X axis and the Y axis in the world coordinate system. The method and the device improve the accuracy of fall prediction.
Description
Technical Field
The invention relates to the technical field of human body fall detection, in particular to a fall and similar action early warning method based on inertial sensing.
Background
There are studies showing that falls are the most common form of the senior syndrome and are the leading cause of injury to the elderly over 65 years of age. Currently, the schemes for determining a fall mainly include video image-based fall detection, audio signal-based fall detection, and wearable device-based fall detection. In the scheme based on video images, real-time movement of an object is monitored by a camera, then action categories in the images are identified, current actions are matched with preset falling actions, and whether falling occurs or not is judged. The scheme cannot guarantee privacy safety of users, the detected falling behaviors are few, the use scene is limited, and the cost is high. In the case of an audio signal based solution, the fall event is determined by analysing the frequency part of the shock-induced vibrations, but such devices are relatively complex to install and relatively costly. For the scheme based on the wearable device, the sensing module of the conventional fall alarm generally adopts a single triaxial accelerometer, the measurement accuracy and the data mode are limited, or the adopted threshold algorithm is not good enough, and the biggest defect is that only fall alarm can be realized, namely, alarm and help seeking after falling can not be realized, and the user can not be reminded in advance after the fall is judged.
In the prior art, patent application CN202110819148.8 discloses a fall early warning system based on neural network signals, which comprises a detachable sole capable of being installed at the bottom of a flat sole and a pose adjusting device arranged in the sole; the detachable sole comprises a groove-shaped sole main body, wherein a transverse plate is arranged in the middle of the sole main body and divides the sole main body into a connecting cavity which is positioned at the upper part and used for supporting the flat shoes and a mounting cavity which is positioned at the lower part; the mounting cavity is internally provided with a transverse supporting plate, two strip-shaped mounting openings are symmetrically arranged on the left side and the right side of the front end and the rear end of the transverse supporting plate, and an action opening is formed in the bottom of the sole main body corresponding to each mounting opening. The scheme reduces the probability of falling through a mechanical mode and a physical method, but is ineffective for actions (such as falling down a bed) of non-daily walking in life, and cannot make falling early warning.
Patent application CN201910865163.9 discloses a medical treatment early warning device of preventing tumbleing, including tightening the circle, one side fixedly connected with connecting block of tightening the circle, one side fixedly connected with box body of connecting block, the inboard fixedly connected with buffering cushion of tightening the circle to tighten up and be provided with coupling assembling on the circle, tighten up and seted up a plurality of air vents, the top of box body inner wall is fixedly connected with battery and siren respectively. According to the scheme, whether falling occurs or not is judged by utilizing the magnitude of the human body inclination angle, but the inclination angle behavior actions with large amplitude such as normal bending, lying down and the like cannot be judged in a distinguishing mode, and the false alarm probability is high.
Patent application CN201810134106.9 discloses a fall early warning and positioning big data system for old people, which comprises a wearable signal acquisition device and a cloud data analysis system; the wearable signal acquisition device comprises a first pressure acquisition unit, a second pressure acquisition unit and a third pressure acquisition unit, wherein the first pressure acquisition unit, the second pressure acquisition unit and the third pressure acquisition unit are used for acquiring pressure signals at the second metatarsal, the phalanges and the first metatarsal and the phalanges when a user walks; the first pressure acquisition unit, the second pressure acquisition unit and the third pressure acquisition unit are all connected with the local storage module, the local storage module is connected with a mobile phone of a user through the short-distance wireless communication unit, and the mobile phone is connected with the cloud data analysis system in a remote communication mode. Although the personal safety of the old people can be effectively guaranteed to a certain extent, the risk of falling of the old people is reduced, but the falling early warning effect is poor. For example, when a human body performs a jumping up and down, lying down in place, or the like, a fall cannot be discriminated and predicted.
To sum up, the existing fall detection schemes have the following drawbacks:
1) The video signal acquisition equipment is utilized to acquire human behavior video information, and the scheme of realizing the inverse prediction through processing the human behavior video needs the assistance of the video acquisition equipment and can only work in a specific area covered by the video acquisition equipment. Moreover, the image processing mode can only have high recognition rate for typical human body falling behaviors, and recognition dead zones exist. Meanwhile, the scheme has the advantages of more required equipment, heavy hardware devices, complicated installation and use, higher cost and inconvenient use in common living scenes.
2) The old person fall early warning system based on biomechanics collects plantar physiological pressure signals through the pressure sensor so as to monitor and judge whether human gait is normal or not and further early warn falling behaviors. The scheme can better reflect information such as gait frequency, speed and the like, but has poor effect on predicting falling behaviors. Because plantar pressure only reflects certain falling behaviors on one side, the upper body of a human body can also show a plurality of falling symptom behaviors under the condition that plantar pressure is unchanged, such as a backseat falling, a sagging falling and the like. Because the sensor is on the sole of the foot, the wearing is inconvenient, and the comfort level of the foot in the walking process is easily affected by the electronic device, the sensor is not suitable for generalization.
3) The existing fall early warning system often adopts a remote transmission and calculation mode to feed back the result. And wearing a related sensor for fall early warning, transmitting the worn sensor original data to a PC end through a wireless transmission module, and finally processing through an algorithm of the PC end. The scheme has large equipment requirement and high algorithm complexity, and is unfavorable for edge node calculation.
4) The traditional fall early warning algorithm based on the acceleration signals and the attitude angles is high in false alarm rate, and fall judgment is often carried out by setting an acceleration signal threshold value and an attitude angle threshold value. Such schemes, although capable of filtering out some fall-like behaviors, have no ability to identify some actions in life and also have specific requirements on the direction of wear of the sensor.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a fall and similar action early warning method based on inertial sensing. The method comprises the following steps:
acquiring a triaxial acceleration signal and a triaxial angular velocity signal of a target under a machine body coordinate system, and calculating a combined acceleration;
according to the mapping relation between the machine body coordinate system and the world coordinate system, a triaxial acceleration signal and a triaxial angular velocity signal of the world coordinate system are obtained;
calculating triaxial motion acceleration under a world coordinate system;
judging whether the target is in a weightlessness state or not by comparing the combined acceleration with a set threshold value;
and under the condition that the target is in a weightlessness state, carrying out falling early warning according to the instantaneous displacement in the vertical direction and/or the variation of the inclination angle, wherein the instantaneous displacement is obtained based on the movement speed and the movement acceleration of the target in the vertical direction, and the variation of the inclination angle is obtained based on the angular speed signals of the X axis and the Y axis in the world coordinate system.
Compared with the prior art, the method has the advantages that in order to solve the problems of high fall early warning missing report rate and low accuracy rate, the typical characteristics of the fall behaviors are found and extracted by analyzing a large number of fall behaviors, and the fall early warning signals can be accurately predicted and sent out before falling through real-time analysis and processing, so that an execution mechanism is informed to timely protect and rescue the falling. The invention can filter out a large number of actions similar to the falling actions in life and early warn common falling actions and special falling actions.
Other features of the present invention and its advantages will become apparent from the following detailed description of exemplary embodiments of the invention, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a flow chart of a fall and similar motion warning method based on inertial sensing according to one embodiment of the invention;
fig. 2 is a process diagram of a fall and similar motion warning method based on inertial sensing according to an embodiment of the invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
In general, the fall and similar action early warning method based on inertial sensing provided firstly collects acceleration signals and angular velocity signals of human body motion through an inertial attitude sensor (such as the MPU 9250), and filters original acceleration and angular velocity signals of three axes (x-axis, y-axis and z-axis) of the sensor (assuming that a sensor worn by a human body is very close to the human body, the acceleration signals and the angular velocity signals output by the sensor can be understood as acceleration signals and angular velocity signals of human body motion).
And then, the filtered triaxial acceleration value is used for obtaining a combined acceleration value, and the combined acceleration can reflect the weightlessness condition of the human body and can be used for judging whether the human body falls down (the falling is accompanied by weightlessness).
Next, acceleration values and angular velocity values of three axes of the sensor are mapped to the world coordinate system, respectively. At this time, in the world coordinate system, there are six amounts, which are the three-axis acceleration value and the three-axis angular velocity value of the sensor map, respectively. The three-axis angular velocity values in the world coordinate system represent angular velocity values of the human body during tilting around the geographic middle east/west direction, the north/south direction, and the vertical direction. For example, if the X-axis of the world coordinate system indicates the east/west direction, when the human body falls in the south/north direction, the angular velocity of the X-axis is the angular velocity during the tilting of the human body around the east/west direction, and integrating the X-axis over a specific time interval results in a change in the tilting angle during the tilting of the human body around the east/west direction. The inclination angle variation of the human body in a certain time period is calculated by using the thought, so that whether falling is about to happen or not is judged in an auxiliary mode.
Further, considering that the inertial sensor is affected by gravity, the value of the triaxial acceleration in the body coordinate system will include the component of the gravitational acceleration (the magnitude and direction of the components of the gravitational acceleration in the three coordinate axes in the body coordinate system are determined by the self-posture of the sensor). Therefore, when the sensor tri-axial acceleration values in the body coordinate system are mapped into the world coordinate system, there will be a vertical downward gravitational acceleration value in the Z-axis direction in the world coordinate system. Then, the acceleration in the Z-axis direction in the world coordinate system is subtracted by the gravity acceleration to obtain the motion acceleration in the Z-axis direction. The accelerations in the rest of the X and Y axes in the world coordinate system are also motion acceleration measures, but the motion acceleration in the direction is vertical to the motion acceleration in the Z axis, and does not contain gravity acceleration, and the natural gravity acceleration is not required to be subtracted, because the natural gravity acceleration is always vertical downwards and only exists in the Z axis.
Then judging the value of the combined acceleration, filtering false falling actions and identifying true falling actions by utilizing the combined acceleration, and if the value is smaller than a normal threshold value, indicating that the human body is in a weightlessness state, and beginning falling (the weightlessness is an inherent attribute of falling behaviors); otherwise, it indicates that the human body has no falling tendency, and is in a falling interference action (e.g., daily behavior actions such as walking, jogging, etc.) or a stationary state (the threshold value used here is not a traditional threshold value method, the threshold value here is simply pre-determined, and the real falling early warning method is detailed in the following steps). Then, the human body can displace in the vertical direction under the world coordinate system, the acceleration of displacement is the acceleration in the Z-axis direction, and at the moment, the acceleration in the Z-axis direction is vertically downward. Simultaneously, the calculation of the instantaneous vertical displacement of the human body and the calculation of the instantaneous inclination angle variation of the human body are triggered. The key point is to monitor whether the gravity center of the human body or a certain body part except limbs continuously moves downwards and continuously changes with a large inclination amount, so that the displacement of the human body in the vertical direction and the inclination angle change amount of the human body are calculated.
For example, if the vertical displacement of the human body is greater than a certain threshold value and the amount of change in the inclination angle of the human body is greater than a certain threshold value in the world coordinate system, fall warning is started. The vertical displacement can be calculated by speed and time; the tilt angle variation can be calculated by integrating the resultant angular velocity of the X-axis and the Y-axis in the world coordinate system. In the calculation process of the displacement and the inclination angle variation, once the change of the inclination angle of the human body and the vertical downward displacement are monitored to be no longer continuously positive/negative, the calculation of the displacement and the inclination angle is stopped immediately, and the calculated results are cleared, so that the preparation is made for the next falling.
For clarity, the parameters involved are first described as follows: inertial sensor (IMU) triaxial acceleration and angular velocity are a respectively x 、a y 、a z And omega x 、ω y 、ω z The method comprises the steps of carrying out a first treatment on the surface of the The three-axis Euler angles (attitude angles) are gamma, psi and theta respectively; the combined acceleration is a Closing device The method comprises the steps of carrying out a first treatment on the surface of the Combined acceleration threshold a Threshold value Is constant; the three-axis acceleration and the gravity acceleration in the world coordinate system and the angular velocity are a respectively X 、a Y 、a Z And g and ω X 、ω Y 、ω Z Where g is the local actual gravitational acceleration; the human body movement speed in the vertical direction is v Dynamic movement The method comprises the steps of carrying out a first treatment on the surface of the Of the human body in the vertical directionThe motion acceleration is Acc Z The method comprises the steps of carrying out a first treatment on the surface of the The change amount of the human body inclination angle is delta phi, and the threshold value of the change amount of the human body inclination angle is delta phi Threshold value The method comprises the steps of carrying out a first treatment on the surface of the The sign bit of the human body weightlessness is G Loss of function The method comprises the steps of carrying out a first treatment on the surface of the IMU sampling period d t =1/(sampling frequency); the displacement of the weightlessness of the human body in the vertical direction is s z The method comprises the steps of carrying out a first treatment on the surface of the The fall early warning signal Sign is Sign.
Specifically, as shown in fig. 1 and 2, the provided fall and similar action early warning method based on inertial sensing includes the following steps:
step S110, acquiring acceleration signals, angular velocity signals and attitude angles of human body movement by using an inertial attitude sensor.
First, the three-axis acceleration and attitude angle of the inertial attitude sensor are read. Not only is the following: a, a x X-axis acceleration input of IMU; a, a y Y-axis acceleration input of IMU; a, a z Z-axis acceleration input of IMU; omega x X-axis angular velocity input, ω of IMU y Y-axis angular velocity input, ω of IMU z Z-axis angular velocity input of IMU; γ=y-axis attitude angle; ψ = z-axis attitude angle; θ=x-axis attitude angle.
It should be appreciated that the attitude angle may be calculated in a variety of ways, such as a quaternion attitude solution algorithm based on extended kalman filtering, a complementary filtering method, or a gradient descent method, etc.
And step S120, filtering the acquired original signals to obtain triaxial acceleration signals and triaxial angular velocity signals under the machine body coordinate system.
For example, the raw tri-axial acceleration signal and tri-axial angular velocity signal acquired are filtered using a moving average filter to remove noise spurs. The general formula for a moving average filter is:
wherein window size is the set window size. The moving average filter moves windows of window size along the data and calculates the average of the data contained in each window.
Specifically, the collected triaxial acceleration signals and triaxial angular velocity signals are subjected to filtering processing, namely:
wherein, the liquid crystal display device comprises a liquid crystal display device,
and->
Is an intermediate variable generated in the filtering process, has no practical meaning, and t represents the time of signal acquisition.
Through the processing, the three-axis acceleration signal and the three-axis angular velocity signal under the filtered body coordinate system can be obtained. Besides sliding window filtering, other filtering methods may be used.
In step S130, a triaxial acceleration signal and a triaxial angular velocity signal in the world coordinate system, and a motion acceleration in the vertical direction are calculated.
The attitude angle of the human body obtained by using the inertial sensor comprises a pitch angle gamma, a roll angle theta and a course angle phi, and the rotation matrix from the body coordinate system to the world coordinate system is recorded as
Then->
Equal to:
three-axis acceleration value of object in world coordinate system is a X 、a Y 、a Z Three-axis angular velocity value omega X 、ω Y 、ω Z 。
Wherein, the liquid crystal display device comprises a liquid crystal display device,a X 、a Y 、a Z and a x 、a y 、a z The following conversion relations are provided:
wherein omega X 、ω Y 、ω Z And omega x 、ω y 、ω z The following conversion relations are provided:
where γ is the rotation angle on the y-axis in the body coordinate system, i.e., pitch angle, ψ is the rotation angle on the z-axis in the body coordinate system, i.e., yaw angle, θ is the rotation angle on the x-axis in the body coordinate system, i.e., roll angle.
Further, filtering the disturbance of the gravitational acceleration under the world coordinate system to obtain the motion acceleration in the Z-axis direction, and then obtaining the triaxial motion acceleration Acc under the world coordinate system X 、Acc Y 、Acc Z Is calculated as follows:
wherein Acc Z The motion acceleration in the Z-axis direction in the world coordinate system is the local actual gravity acceleration. Acc Y Is the motion acceleration in the Y-axis direction under the world coordinate system, acc X Is the motion acceleration in the X-axis direction under the world coordinate system.
In the step, according to the mapping relation between the machine body coordinate system and the world coordinate system, the three-axis attitude angle is utilized to solve a mapping matrix, and the three-axis acceleration signal and the angular velocity signal are mapped under the world coordinate system by the mapping matrix. Further, the three-axis acceleration signal in the world coordinate system is subtracted by the gravity acceleration g in the vertical direction Z-axis to obtain the three-axis motion acceleration in the world coordinate system.
It should be noted that, in calculating the net motion acceleration in the world coordinate system, the above embodiment maps the three-axis acceleration values in the body coordinate system into the world coordinate system, and then subtracts the gravitational acceleration. The process may also be replaced by the following steps: and mapping the gravitational acceleration under the world coordinate system into the machine body coordinate system, subtracting the gravitational acceleration under the machine body coordinate system from the triaxial acceleration in the machine body coordinate system, and mapping the triaxial acceleration value subtracted with the gravitational acceleration into the world coordinate system, wherein the triaxial value under the world coordinate system is also net motion acceleration.
In step S140, the combined acceleration under the body coordinate system is calculated.
For example, the combined acceleration in the body coordinate system is expressed as:
wherein the three-axis acceleration value after filtering is a x 、a y 、a z . The filtered triaxial angular velocity value is omega x 、ω y 、ω z . The total acceleration can reflect whether the human body loses weight or not and the degree of losing weight.
And step S150, judging whether the target is in a weightlessness state or not based on the combined acceleration, and performing fall early warning according to the instantaneous displacement in the vertical direction and the change amount of the inclination angle.
First, the weight loss of the human body is judged. If the combined acceleration a Closing device ＜a Threshold value It indicates that the object is beginning to be in a weightless condition. At the same time, calculation of the movement velocity v of the human body in the vertical direction is started Dynamic movement And the motion acceleration Acc Z And integrates the triaxial angular velocity in the world coordinate system. Further solving the displacement s of the human body in the vertical direction z And a change amount ΔΦ of the inclination angle with respect to the vertical direction. For example, if the human body loses weight and shifts s z ＞s Threshold value And Δφ > Δφ Threshold value Judging that the human body is about to fall downA fall early warning signal is sent.
Specifically, if the combined acceleration is less than the normal threshold, both: a, a Closing device ＜a Threshold value Indicating that the human body is weightless, indicating that the weightless mark is at position 1, namely G Loss of function =1; otherwise, the weightlessness flag bit is set at 0, namely G Loss of function ＝0；
If G Loss of function When=1, the calculation of the instantaneous displacement in the vertical direction is started, and there are:
where T represents the end time of calculating the displacement S (i.e., the time of giving a fall warning, hereinafter sign=1), T represents the time index of calculating the displacement, and t=1 represents the start time of calculating the displacement S (i.e., G) Loss of function Time of =1), d t Representing the sampling period.
At the same time, calculation of the amount of change in the tilt angle is also started, and there are:
it should be noted that: the body's own rotation about the Z-axis is independent of the fall process and therefore does not participate in the calculation.
When the instantaneous displacement in the vertical direction is greater than the threshold (i.e.) z ＞s Threshold value ) The gravity center or key part of the human body is described as moving downwards in a large extent; when the change amount of the human body inclination angle is larger than the threshold value (delta phi > delta phi) Threshold value ) It indicates that the center of gravity or key parts of the human body have been greatly inclined. In one embodiment, when the two variables are both greater than the corresponding thresholds, then judging that the human body is about to fall, and then setting a fall early warning Sign to 1, namely sign=1; does not satisfy the judgment conditionIf so, the fall early warning Sign is still set to 0, namely sign=0.
If the combined acceleration is greater than the normal threshold, both: s is(s) Closing device ＞s Threshold value Record s Z And Δφ
And->
The values of>
And delta phi T And +.>
And->
And (3) representing.
In one embodiment, when s Z And Δφ satisfies the following conditions one and two simultaneously or ω x =0 or ω y When=0, then s Z And resetting the delta phi value, ending the early warning process of the falling, and returning to the step S110 to prepare for the early warning of the falling next time; otherwise, jumping to judge whether the combined acceleration is smaller than the normal threshold value to continuously calculate the instantaneous displacement s in the vertical direction Z And a variation delta phi of the human body inclination angle.
Condition one:
condition II:
in this step S150, considering that the normal behavior of the human body involves a short slight weight loss, a threshold is set to distinguish whether it is a false weight loss of the normal behavior or a true weight loss where a fall is likely to occur. When the real weightlessness status is in, the process of calculating the real weightlessness status is startedThe human body is displaced in the vertical direction, and the change amount of the inclination angle of the human body under the world coordinate system in the true weightlessness state process is calculated. Furthermore, during one sampling period d of the inertial sensor t In the method, the displacement of the human body in the vertical direction is calculated by adopting a uniform acceleration motion mode, and the inclination angle of the human body is calculated by adopting a uniform inclination mode. And when the human body is in a true weightlessness state, the rotational speed around the Z axis is irrelevant to the inclination of the human body in the human body deviation process under the world coordinate system, so that the human body is not involved in calculation. In a true weightlessness state, when the displacement in the vertical direction is greater than a set displacement threshold and the change amount of the inclination angle in the world coordinate system is greater than the set threshold, the falling is considered to be about to happen, and a falling early warning signal is triggered. By means of the designs, a large number of actions similar to falling actions (such as sitting, walking, standing, bending, lying down, squatting, jumping and the like) in life can be filtered out, and common falling actions (such as left/right falling, front/back falling, side direction falling and the like) and special falling actions (such as falling type falling, falling down a bed, claudication falling, hip/knee falling first, wall-supporting slowly sliding and the like) can be early warned.
To further verify the effect of the invention, a similar action to the fall behavior was verified, and the experimental results are shown in table 1, so that the average false alarm rate is only 1.40%.
Table 1 experimental results
| ADL action type | Number of experiments | Number of false alarm | False alarm feedback mode | False alarm rate |
| Walking by walking | 150 | 1 | Language prompt | 0.7％ |
| Jogging | 150 | 1 | Language prompt | 0.7％ |
| Sit down and stand up | 150 | 0 | Language prompt | 0.0％ |
| Lying down | 150 | 2 | Language prompt | 1.3％ |
| Squat and stand up | 150 | 3 | Language prompt | 2.0％ |
| Jumping | 150 | 2 | Language prompt | 1.3％ |
| Stair climbing | 150 | 3 | Language prompt | 2.0％ |
| Downstairs | 150 | 2 | Language prompt | 1.3％ |
| Intermittent falling motion | 150 | 5 | Language prompt | 3.3％ |
It is to be noted that the above-described embodiments may be modified or adapted by a person skilled in the art without departing from the spirit of the invention. For example, the change of the vertical displacement of the human body or the deviation angle of the human body relative to the vertical direction under the true weightlessness is used as a falling judgment feature to carry out falling early warning; mapping the machine body coordinate system under the world coordinate system and filtering the gravitational acceleration to obtain the motion acceleration. For another example, in other different scenes, the combined acceleration is used as an important marker for judging the weight loss of the human body to calculate the vertical position distance, or the combined acceleration is used as an important marker for judging the weight loss of the human body to calculate the offset angle relative to the vertical direction. Or, the X-axis angular velocity and the Y-axis angular velocity in the world coordinate system are utilized to square and sum, and finally the calculated relation of the evolution is utilized to obtain the combined angular velocity for the falling early warning or the detection algorithm, so that the method and the idea for obtaining the combined angular velocity are within the protection range. In addition, the method for judging whether the falling monitoring is ended or not by utilizing the vertical displacement of the combined acceleration and the vertical direction or the variation of the combined acceleration and the deviation angle or the vertical displacement and the deviation angle of the combined acceleration and the vertical direction is within the protection scope of the invention.
In summary, the method filters the original signal to remove interference and signal noise, so as to ensure that the subsequent calculation is accurate and is not interfered by measurement noise; the whole fall early warning process does not depend on the attitude angle, and crosstalk of daily behaviors similar to falling in life can be prevented. More importantly, the invention utilizes the common characteristics of a plurality of falling behaviors, namely: the displacement amount of the human body in the vertical direction under the world coordinate system and the variation amount of the offset angle with respect to the vertical direction in the weightless state are greatly varied. And the falling behavior prediction is carried out by monitoring the instantaneous displacement in the vertical direction of the human body and the variation of the deviation angle under the weightlessness state, so that the prediction accuracy is improved. In the intermittent action (such as slow sliding of the buttress, etc.) of the falling action, the falling action can be effectively identified by monitoring the change of the combined acceleration, the change of the vertical displacement and the direction of the change of the angular velocity, so that the differentiation of the falling action and the non-falling action is higher. In addition, through experimental verification, the invention has the advantages of low complexity, high execution efficiency, small calculation power, real-time response processing at the edge terminal and wider application.
The present invention may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++, python, and the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.
The foregoing description of embodiments of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (10)
1. A fall and similar action early warning method based on inertial sensing comprises the following steps:
acquiring a triaxial acceleration signal and a triaxial angular velocity signal of a target under a machine body coordinate system, and calculating a combined acceleration;
according to the mapping relation between the machine body coordinate system and the world coordinate system, a triaxial acceleration signal and a triaxial angular velocity signal of the world coordinate system are obtained;
calculating triaxial motion acceleration under a world coordinate system;
judging whether the target is in a weightlessness state or not by comparing the combined acceleration with a set threshold value;
and under the condition that the target is in a weightlessness state, carrying out falling early warning according to the instantaneous displacement in the vertical direction and/or the variation of the inclination angle, wherein the instantaneous displacement is obtained based on the movement speed and the movement acceleration of the target in the vertical direction, and the variation of the inclination angle is obtained based on the angular speed signals of the X axis and the Y axis in the world coordinate system.
2. The method according to claim 1, wherein fall warning is performed when the following conditions are met:
when the instantaneous displacement in the vertical direction is greater than a first threshold; or alternatively
When the change amount of the human body inclination angle is larger than a second threshold value; or alternatively
When the instantaneous displacement in the vertical direction is greater than the first threshold and when the amount of change in the human body inclination angle is greater than the second threshold.
3. The method as recited in claim 1, further comprising:
when the target is judged to be in a non-weightless state, performing:
record s Z 、Δφ、
And->
The values of>
Δφ T 、/>
And->
A representation;
when (when)
And->
And->
Or when omega x =0 or ω y When=0, s will be Z And clearing the delta phi value, and ending the early warning process of falling;
wherein omega x 、ω y 、ω z Is the triaxial angular velocity value under the machine body coordinate system, delta phi is the change quantity of the inclination angle, s Z Is the instantaneous displacement in the vertical direction, T represents the end time of the calculated displacement.
4. The method of claim 1, wherein the mapping relationship between the body coordinate system and the world coordinate system is expressed as:
wherein, the triaxial acceleration signal under the machine body coordinate system is a x 、a y 、a z The triaxial angular velocity signal is omega x 、ω y 、ω z Gamma is the rotation angle on the y-axis in the body coordinate system, ψ is the rotation angle on the z-axis in the body coordinate system, θ is the rotation angle on the x-axis in the body coordinate system,
is a rotation matrix from the body coordinate system to the world coordinate system.
5. The method of claim 1, wherein the three-axis motion acceleration in the world coordinate system is expressed as:
wherein Acc Z Is the motion acceleration in the Z-axis direction under the world coordinate system, acc Y Is the motion acceleration in the Y-axis direction under the world coordinate system, acc X Is the motion acceleration in the X-axis direction in the world coordinate system, and g is the gravity acceleration.
6. The method according to claim 1, characterized in that the instantaneous displacement in the vertical direction is expressed as:
the amount of change in the tilt angle is expressed as:
wherein the movement speed in the vertical direction is v Dynamic movement The method comprises the steps of carrying out a first treatment on the surface of the The motion acceleration in the vertical direction is Acc Z The method comprises the steps of carrying out a first treatment on the surface of the The change amount of the tilt angle is Deltaphi, and the threshold value of the change amount of the tilt angle is Deltaphi Threshold value ；d t Is the sampling period; the instantaneous displacement in the vertical direction is s Z T represents the time index for calculating the displacement, t=1 represents the start time of calculating the displacement, and T represents the end time of calculating the displacement.
7. The method of claim 1, wherein the three-axis acceleration signal and the three-axis angular velocity signal in the body coordinate system are obtained by filtering raw data with a moving average filter.
8. The method of claim 1, wherein the combined acceleration is expressed as:
wherein a is x 、a y 、a z Is a triaxial acceleration signal under a machine body coordinate system, a x Corresponding to the x-axis, a y Corresponding to the y axis, a z Corresponding to the z-axis.
9. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor realizes the steps of the method according to any of claims 1 to 8.
10. A computer device comprising a memory and a processor, on which memory a computer program is stored which can be run on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 8 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310197548.9A CN116189383A (en) | 2023-02-22 | 2023-02-22 | Fall and similar action early warning method based on inertial sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310197548.9A CN116189383A (en) | 2023-02-22 | 2023-02-22 | Fall and similar action early warning method based on inertial sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116189383A true CN116189383A (en) | 2023-05-30 |
Family
ID=86434421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310197548.9A Pending CN116189383A (en) | 2023-02-22 | 2023-02-22 | Fall and similar action early warning method based on inertial sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116189383A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117257283A (en) * | 2023-11-22 | 2023-12-22 | 浙江强脑科技有限公司 | Fall protection method and device, intelligent artificial limb, terminal and storage medium |
| CN117462314A (en) * | 2023-11-09 | 2024-01-30 | 浙江强脑科技有限公司 | Damping adjustment method, damping adjustment device, intelligent artificial limb, intelligent artificial terminal and storage medium |
-
2023
- 2023-02-22 CN CN202310197548.9A patent/CN116189383A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117462314A (en) * | 2023-11-09 | 2024-01-30 | 浙江强脑科技有限公司 | Damping adjustment method, damping adjustment device, intelligent artificial limb, intelligent artificial terminal and storage medium |
| CN117462314B (en) * | 2023-11-09 | 2024-04-09 | 浙江强脑科技有限公司 | Damping adjustment method, damping adjustment device, intelligent artificial limb, intelligent artificial terminal and storage medium |
| CN117257283A (en) * | 2023-11-22 | 2023-12-22 | 浙江强脑科技有限公司 | Fall protection method and device, intelligent artificial limb, terminal and storage medium |
| CN117257283B (en) * | 2023-11-22 | 2024-04-09 | 浙江强脑科技有限公司 | Fall protection method and device, intelligent artificial limb, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116189383A (en) | Fall and similar action early warning method based on inertial sensing | |
| CN111132603B (en) | Detecting falls using a mobile device | |
| EP2451351B1 (en) | Fall prevention | |
| US8930163B2 (en) | Method for step detection and gait direction estimation | |
| Kepski et al. | Fall detection using ceiling-mounted 3d depth camera | |
| JP6567658B2 (en) | Device and method for classifying user activity and / or counting user steps | |
| Majumder et al. | iPrevention: Towards a novel real-time smartphone-based fall prevention system | |
| US20170241797A1 (en) | Pedometer with Accelerometer and Foot Motion Distinguishing Method | |
| Shi et al. | Fall Detection Algorithm Based on Triaxial Accelerometer and Magnetometer. | |
| US20180085045A1 (en) | Method and system for determining postural balance of a person | |
| Sabatini et al. | Fourier-based integration of quasi-periodic gait accelerations for drift-free displacement estimation using inertial sensors | |
| KR20140110484A (en) | Risk behavior detection method using image information | |
| CN114469074A (en) | Fall early warning method, system, equipment and computer storage medium | |
| CN107016411B (en) | Data processing method and device | |
| KR101270004B1 (en) | System and method for measuring physical activity, method for guiding physical activity and abnormal pattern using the same | |
| US20240032820A1 (en) | System and method for self-learning and reference tuning activity monitor | |
| Amiroh et al. | Intelligent System for Fall Prediction Based on Accelerometer and Gyroscope of Fatal Injury in Geriatric | |
| US20230389880A1 (en) | Non-obtrusive gait monitoring methods and systems for reducing risk of falling | |
| Weng et al. | Fall detection based on tilt angle and acceleration variations | |
| Shipkovenski et al. | Accelerometer based fall detection and location tracking system of elderly | |
| KR101553236B1 (en) | The Classifying and Counting Algorithm for Real-time Walk/Run Exercise based on An Acceleration Sensor | |
| Ong et al. | BrainSmart: Ambient Assisted Living System Smartphone App Prototype for Parkinson's Disease Patients | |
| Biswas et al. | On fall detection using smartphone sensors | |
| CN113936420B (en) | Detecting falls using a mobile device | |
| Purwar et al. | A systematic review on fall detection systems for elderly healthcare |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |