Detection method and detection module for falling-down movement of intelligent kneecap

Abstract

The invention provides a movement falling detection method and detection module for an intelligent kneecap, and the method comprises the following steps: data collection: collecting original movement data of the knee joint of a wearer through a collection mechanism worn on the kneecap of the knee joint, the controller calculates important parameters reflecting a three-dimensional space motion state through the original motion data; data processing: performing low-pass filtering on the data; performing falling detection judgment, performing threshold judgment on the important parameters reflecting the motion state of the three-dimensional space respectively, and when all the parameters exceed a set threshold, judging that a falling state is entered; and in early warning, after the system detects falling down, an early warning mechanism on the kneecap is triggered to start, and a user is prompted that the falling down event occurs. The intelligent kneecap can provide more accurate fall detection in the movement process, has higher accuracy and pertinence, and has better wearing comfort as an intelligent protector.

Description

Technical Field

[0001] The present invention relates to the technical field of kneepads, and in particular to a sports fall detection method for an intelligent kneepad. The present invention also relates to a sports fall detection module for an intelligent kneepad. Background Art

[0002] Knee pads are one of the most common sports injury protection products. They are mainly used as auxiliary equipment worn by sports enthusiasts or athletes to protect the knee joint from sports injuries. Current research has also confirmed that the reasonable use of knee pads can significantly reduce the occurrence of sports injuries.

[0003] With the aging of the population and the change of modern people's lifestyle, falls have become a common and serious health problem among sports people. Falls not only cause physical injuries such as fractures and head injuries, but untimely rescue after falls may also bring serious consequences. Therefore, how to effectively detect falls and issue alarms in time has become an important protective function in smart knee pads.

[0004] Currently, although smart watches and bracelets on the market can monitor activities and falls, the accuracy of fall detection is relatively low because they are worn far away from the knee joint. In addition, there are wearable sensors such as chest straps and waist belts that provide accurate data by monitoring body movement and posture, but their wearing position may affect exercise comfort and monitoring effect, and are not suitable for detection during exercise. Summary of the invention

[0005] The present invention aims to provide a sports fall detection method of an intelligent kneepad to overcome the deficiencies in the prior art.

[0006] In order to solve the above technical problems, the technical solution of the present invention is: a sports fall detection method of an intelligent kneepad, comprising the following steps:

[0007] S1. Collecting data. The collecting mechanism worn on the knee brace collects the original motion data of the wearer's knee joint: three-axis acceleration and three-axis angular velocity, which are recorded as {ax, ay, az} and {wx, wy, wz} respectively. The controller communicates with the collecting mechanism to obtain the original motion data, and calculates the important parameters reflecting the motion state of the three-dimensional space through the original motion data.

[0008] S2, data processing, low-pass filtering the data to reduce the high-frequency noise of the original data;

[0009] S3, fall detection and judgment, respectively, threshold judgment is performed on important parameters reflecting the three-dimensional space motion state, and when all exceed the set threshold, it is judged to enter the fall state;

[0010] S4, early warning: after the system detects a fall, it triggers the early warning mechanism on the knee pad to start and prompt the user that a fall has occurred.

[0011] Furthermore, in the above-mentioned sports fall detection method of the smart knee pad, the collection mechanism includes a three-axis accelerometer and a three-axis angular velocity meter, which collects raw motion data at a frequency of 100 Hz.

[0012] Furthermore, in the above-mentioned motion fall detection method of the smart knee brace, the important parameters reflecting the motion state in three-dimensional space are: total acceleration vector A, pitch angle θ, yaw angle φ, total angular velocity vector w;

[0013] Among them, the calculation formula of the total acceleration vector A is as follows:

[0014] A=(a,ay,α)

[0015]

[0016] |A| is the modulus of the total acceleration vector, indicating the magnitude of acceleration;

[0017] The pitch angle θ describes the change in the direction of the total acceleration vector A in the vertical plane and reflects the degree of inclination of the total acceleration vector in the yz plane. The calculation formula for the pitch angle θ is:

[0018]

[0019] The yaw angle φ describes the change in the direction of the acceleration vector in the horizontal plane, and usually reflects the rotation angle of the vector relative to the y-axis in the xy plane. The calculation formula for the yaw angle φ is:

[0020]

[0021] The total angular velocity vector is calculated as follows:

[0022] w=(w,Wy,w.)

[0023]

[0024] Furthermore, in the above-mentioned sports fall detection method of the intelligent knee brace, when making a fall detection judgment, threshold judgments are made on |A|, θ, φ, and |w|, respectively, including the following steps:

[0025] S31, monitoring the total angular velocity vector w of the human body, when the total angular velocity vector exceeds a set threshold, it indicates that the human body enters dynamic motion from a static state;

[0026] S32, judging the movement direction of the human body, when the pitch angle θ exceeds the set threshold, and the absolute value of the yaw angle φ is greater than the set threshold, it means that the human body is moving sideways to the ground and may fall;

[0027] S33, real-time monitoring of the total acceleration vector. When a sudden change in the total acceleration is detected, it indicates that the human body has violently impacted the ground. Within 10 seconds after the impact on the ground occurs, the total acceleration continues to be lower than the set threshold.

[0028] S34. If the above three conditions are met, it is comprehensively judged that the human body has fallen and entered a static state after the fall.

[0029] Furthermore, in the above-mentioned sports fall detection method of the smart knee pad, the setting range of the angular acceleration threshold wth is 2-7 rad / s.

[0030] Furthermore, in the above-mentioned sports fall detection method of the intelligent knee pad, the setting threshold of the pitch angle θ is 120°, and the setting range of the threshold of the yaw angle φ is |φ|>80°.

[0031] Furthermore, in the above-mentioned sports fall detection method of the smart knee pad, the setting range of the total acceleration threshold Ath is 0.6g-3g, where g is the acceleration of gravity.

[0032] Furthermore, in the above-mentioned sports fall detection method of the smart knee pad, after a period of warning, if the user does not confirm or cancel the prompt information, the system enters the alarm process; the alarm process is:

[0033] First, the controller activates the buzzer and emits a high-frequency alarm sound to attract the attention of people around; at the same time, the human-computer interaction mobile application will obtain the user's real-time GPS location and generate detailed alarm information, which includes the user's current location and fall time, and send the alarm information to the preset emergency contact via SMS, email or a dedicated emergency service platform.

[0034] The present invention also provides a sports fall detection module for an intelligent kneepad, comprising a controller and a collection mechanism, an early warning mechanism, and a communication mechanism electrically connected to the controller, wherein the collection mechanism comprises a three-axis accelerometer and a three-axis angular velocity meter for collecting three-dimensional original motion data of the human body; the early warning mechanism is used for human-computer interaction to display body information, including an RGB light, which is a visual alarm and will start high-frequency flashing of the light when triggered; the communication mechanism wirelessly sends the early warning information processed by the controller to a mobile phone app, and the controller is used to process the data collected by the collection mechanism and execute a fall detection algorithm.

[0035] Furthermore, the sports fall detection module of the above-mentioned smart knee pad also includes an alarm mechanism, which includes a buzzer, which emits a high-frequency alarm sound to prompt the outside world when triggered, and sends the alarm information to an emergency contact through a communication mechanism.

[0036] Compared with the prior art, the beneficial effects of the present invention are: the intelligent knee pad of the present invention can provide more accurate fall detection during exercise by fitting the knee joint design, and has higher accuracy and specificity than the prior art; in addition, the exercise fall detection method of the present invention solves the problems of false alarm, missed alarm and comfort existing in the prior art through precise detection position, sensitive motion characteristic analysis, real-time warning, intelligent algorithm and multi-function integration, and greatly improves the accuracy of fall detection and wearing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 It is a flow chart of the sports fall detection method of the smart knee brace of the present invention;

[0039] Figure 2 This is a schematic diagram of the sports fall detection module of the smart kneepad of the present invention;

[0040] Figure 3 The installation position and three-axis direction diagram of the smart kneepad of the present invention;

[0041] Figure 4 It is a schematic diagram of the pitch angle and yaw angle of the sports fall detection method of the smart knee pad of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] like Figure 1 As shown, a method for detecting a fall in sports using a smart knee brace comprises the following steps:

[0045] S1. Collecting data. The collecting mechanism worn on the knee pad collects the original motion data of the wearer's knee joint: three-axis acceleration and three-axis angular velocity, which are respectively recorded as {ax, ay, az} and {wx, wy, wz}. The controller communicates with the collecting mechanism to obtain the original motion data, and calculates important parameters reflecting the three-dimensional space motion state through the original motion data; wherein, the collecting mechanism includes a three-axis accelerometer and a three-axis angular velocity meter, which collect the original motion data at a frequency of 100 Hz.

[0046] The important parameters reflecting the motion state of three-dimensional space are: total acceleration vector A, pitch angle θ, yaw angle φ, total angular velocity vector w; Figure 3 As shown, the wearing position and three-axis direction of the knee pad are marked;

[0047] Among them, the calculation formula of the total acceleration vector A is as follows:

[0048] A=(a,ay,α)

[0049]

[0050] |A| is the modulus of the total acceleration vector, indicating the magnitude of acceleration;

[0051] like Figure 4 As shown, the pitch angle θ describes the change in the direction of the total acceleration vector A in the vertical plane and reflects the degree of inclination of the total acceleration vector in the yz plane. The calculation formula for the pitch angle θ is:

[0052]

[0053] like Figure 4 As shown, the yaw angle φ describes the change in the direction of the acceleration vector in the horizontal plane, and usually reflects the rotation angle of the vector relative to the y-axis in the xy plane. The calculation formula for the yaw angle φ is:

[0054]

[0055] The total angular velocity vector is calculated as follows:

[0056] w=(w,wy,w.)

[0057]

[0058] S2, data processing, low-pass filtering the data to reduce the high-frequency noise of the original data, facilitating the subsequent feature value extraction;

[0059] S3, fall detection and judgment, respectively, threshold judgment is performed on important parameters reflecting the three-dimensional space motion state, and when all exceed the set threshold, it is judged to enter the fall state;

[0060] Specifically, when performing fall detection and determination, threshold determinations are respectively made for ∣A∣, θ, φ, and ∣w∣, including the following steps:

[0061] S31. First, monitor the total angular velocity vector w of the human body. When the total angular velocity vector exceeds the set threshold, it represents that the human body enters dynamic motion from a stationary state;

[0062] S32. Next, judge the movement direction of the human body. When the pitch angle θ exceeds 120° and the absolute value of the yaw angle φ is greater than 80°, it represents that the human body is moving towards the lateral ground and is likely to fall;

[0063] S33. Subsequently, monitor the total acceleration vector in real time. When a sudden change in the total acceleration is detected, it indicates that the human body has suffered a severe impact on the ground. Monitor the total acceleration. Within 10 seconds after the impact on the ground, the total acceleration continuously remains below the set threshold;

[0064] S34. If the above 3 conditions are met, it is comprehensively judged that the human body has fallen and entered a stationary state after the fall.

[0065] The specific process of fall detection and determination is as follows:

[0066] Angular velocity monitoring:

[0067] w > wth → Dynamic state

[0068] Movement direction judgment:

[0069] θ > 120° ∧ ∣φ∣ > 80° → Lateral movement trend

[0070] Acceleration sudden change monitoring:

[0071] ΔA > ΔAth → Impact on the ground

[0072] Stationary state detection:

[0073] A < Ath for t ≥ 10s → Stationary after fall

[0074] Comprehensive determination and alarm:

[0075] Dynamic state ∧ Lateral movement trend ∧ Impact on the ground ∧ Stationary after fall → Trigger alarm

[0076] Among them, wth is the angular acceleration threshold, and the set range is 2 - 7 rad / s. ΔA and ΔAth are respectively the total acceleration change amount and the total acceleration change amount threshold. Ath is the stationary total acceleration threshold, and the set range is 0.6g - 3g. g is the gravitational acceleration, and t is the stationary time after the impact on the ground.

[0077] S4, early warning: after the system detects a fall, it triggers the early warning mechanism on the knee pad to start and prompt the user that a fall has occurred.

[0078] After a period of warning, the time can be set according to the actual situation. In the embodiment, it is set to 3 minutes. If the user does not confirm or cancel the prompt information, the system enters the alarm process; the alarm process is:

[0079] First, the controller activates the buzzer and emits a high-frequency alarm sound to attract the attention of people around; at the same time, the mobile phone application of human-computer interaction obtains the user's real-time GPS location, generates detailed alarm information, and sends the alarm information to the preset emergency contacts, such as family members or medical institutions, via SMS, email or a dedicated emergency service platform. If the user returns to normal during this period, the alarm can be manually terminated, and the system will record the entire process for subsequent analysis and optimization.

[0080] The alarm information includes the user's current location and the time of the fall so that emergency contacts can locate and respond quickly.

[0081] The motion fall detection method of the present invention solves the problems of false alarm, missed alarm and comfort existing in the prior art through precise detection position, sensitive motion characteristic analysis, real-time warning, intelligent algorithm and multi-function integration, and greatly improves the accuracy of fall detection and wearing experience.

[0082] Example 2

[0083] like Figure 2 As shown, the present invention also provides a sports fall detection module of an intelligent kneepad, which is fitted and worn at the human knee joint. The sports fall detection module includes a controller and a collection mechanism, an early warning mechanism, and a communication mechanism electrically connected to the controller. The collection mechanism includes a three-axis accelerometer and a three-axis angular velocity meter, which are used to collect three-dimensional original motion data of the human body; the early warning mechanism is used for human-computer interaction to display body information, including RGB lights, which are visual alarms and will start high-frequency flashing of the lights when triggered; the communication mechanism wirelessly sends the early warning information processed by the controller to the mobile phone app, and the controller is used to process the data collected by the collection mechanism and execute the fall detection algorithm.

[0084] The sports fall detection module of the above-mentioned smart kneepad also includes an alarm mechanism, which includes a buzzer. When triggered, it emits a high-frequency alarm sound to prompt the outside world and sends the alarm information to an emergency contact through a communication mechanism.

[0085] When the controller receives the data collected by the collection mechanism and executes the fall detection algorithm to identify the user who has fallen, it triggers the RGB light, which starts flashing at a high frequency. At the same time, an emergency alarm pop-up window will pop up on the mobile phone application to remind the user that a fall may have occurred.

[0086] If the user does not confirm or cancel the alarm within three minutes, the system will automatically enter the alarm process, trigger the alarm mechanism, and the controller will activate the buzzer to emit a high-frequency alarm sound to attract the attention of people around; at the same time, the mobile phone application will obtain the user's real-time GPS positioning and generate detailed alarm information. The alarm information includes the user's current location and fall time so that the emergency contact can quickly locate and respond. The alarm information is sent to the preset emergency contacts, such as family members or medical institutions, through the communication mechanism, which sends it by SMS, email or a dedicated emergency service platform.

[0087] If the user returns to normal during this period, the alarm can be manually terminated and the system will record the entire process for subsequent analysis and optimization.

[0088] The intelligent kneepad of the present invention can provide more accurate fall detection during exercise by being designed to fit the knee joint. Compared with the existing technology, it has higher accuracy and specificity, and as an intelligent sports protective gear, it can provide better wearing comfort.

[0089] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0090] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A sports fall detection method using an intelligent kneepad, characterized in that: The following steps are involved: S1. Collecting data. The collecting mechanism worn on the knee brace collects the original motion data of the wearer's knee joint: three-axis acceleration and three-axis angular velocity, which are recorded as {ax, ay, az} and {wx, wy, wz} respectively. The controller communicates with the collecting mechanism to obtain the original motion data, and calculates the important parameters reflecting the motion state of the three-dimensional space through the original motion data. S2, data processing, low-pass filtering the data to reduce the high-frequency noise of the original data; S3, fall detection and judgment, respectively, threshold judgment is performed on important parameters reflecting the three-dimensional space motion state, and when all exceed the set threshold, it is judged to enter the fall state; S4, early warning: after the system detects a fall, it triggers the early warning mechanism on the knee pad to start and prompt the user that a fall has occurred.

2. The sports fall detection method of the smart kneepad according to claim 1, characterized in that: The acquisition mechanism includes a three-axis accelerometer and a three-axis angular velocity meter, which acquires original motion data at a frequency of 100 Hz.

3. The sports fall detection method of the smart kneepad according to claim 1, characterized in that: The important parameters reflecting the motion state of the three-dimensional space are: total acceleration vector A, pitch angle θ, yaw angle φ, total angular velocity vector w; Among them, the calculation formula of the total acceleration vector A is as follows: A=(a x ,a y ,a z ), |A| is the modulus of the total acceleration vector, indicating the magnitude of acceleration; The pitch angle θ describes the change in the direction of the total acceleration vector A in the vertical plane and reflects the degree of inclination of the total acceleration vector in the yz plane. The calculation formula for the pitch angle θ is: The yaw angle φ describes the change in the direction of the acceleration vector in the horizontal plane, and usually reflects the rotation angle of the vector relative to the y-axis in the xy plane. The calculation formula for the yaw angle φ is: The total angular velocity vector is calculated as follows: in=(in x ,In y ,In z ), 4. The sports fall detection method of the smart knee brace according to claim 3 is characterized in that: When fall detection is performed, threshold determination is performed on |A|, θ, φ, and |w|, respectively, including the following steps: S31, monitoring the total angular velocity vector w of the human body, when the total angular velocity vector exceeds a set threshold, it indicates that the human body enters dynamic motion from a static state; S32, judging the movement direction of the human body, when the pitch angle θ exceeds the set threshold, and the absolute value of the yaw angle φ is greater than the set threshold, it means that the human body is moving sideways to the ground and may fall; S33, real-time monitoring of the total acceleration vector. When a sudden change in the total acceleration is detected, it indicates that the human body has violently impacted the ground. Within 10 seconds after the impact on the ground occurs, the total acceleration continues to be lower than the set threshold. S34. If the above three conditions are met, it is comprehensively judged that the human body has fallen and entered a static state after the fall.

5. The sports fall detection method of the smart knee brace according to claim 4, characterized in that: The setting range of the angular acceleration threshold is 2-7 rad / s.

6. The sports fall detection method of the smart knee brace according to claim 4, characterized in that: The setting threshold of the pitch angle θ is 120°, and the setting range of the threshold of the yaw angle φ is |φ|>80°.

7. The sports fall detection method of the smart knee brace according to claim 4, characterized in that: The setting range of the total acceleration threshold Ath is 0.6g-3g, where g is the gravitational acceleration.

8. The sports fall detection method of the smart knee brace according to claim 1, characterized in that: After a period of warning, if the user does not confirm or cancel the prompt information, the system enters the alarm process; the alarm process is: First, the controller activates the buzzer and emits a high-frequency alarm sound to attract the attention of people around; at the same time, the human-computer interaction mobile application will obtain the user's real-time GPS location and generate detailed alarm information, which includes the user's current location and fall time, and send the alarm information to the preset emergency contact via SMS, email or a dedicated emergency service platform.

9. A sports fall detection module for an intelligent kneepad, characterized in that: The motion fall detection module is applied to the motion fall detection method of the smart knee pad described in any one of claims 1 to 8, including a controller and a collection mechanism, an early warning mechanism, and a communication mechanism electrically connected to the controller, wherein the collection mechanism includes a three-axis accelerometer and a three-axis angular velocity meter for collecting three-dimensional original motion data of the human body; the early warning mechanism is used for human-computer interaction to display body information, including RGB lights, which are visual alarms and will start high-frequency flashing of the lights when triggered; the communication mechanism wirelessly sends the early warning information processed by the controller to the mobile phone app, and the controller is used to process the data collected by the collection mechanism and execute the fall detection algorithm.

10. The sports fall detection module of the smart knee brace according to claim 9, characterized in that: It also includes an alarm mechanism, which includes a buzzer. When triggered, it emits a high-frequency alarm sound to prompt the outside world and sends the alarm information to an emergency contact through a communication mechanism.

Images