A method of detecting a fall of a person in a court based on ultrasonic waves and a related apparatus

Abstract

The application relates to the technical field of ultrasonic detection, and provides a method for detecting a user's fall in a court based on ultrasonic waves and related equipment, the method comprising the following steps: controlling multiple ultrasonic detection devices in the court to emit multiple ultrasonic waves to the user; after an ultrasonic wave receiving device in a wearable device worn by the user receives the ultrasonic waves, returning response information to each ultrasonic detection device respectively; determining whether the user falls based on all the response information; and after it is determined that the user falls, performing a preset rescue operation. The ultrasonic detection system is composed of the ultrasonic detection devices in the court and the wearable device worn by the user, whether the user falls in the court is detected through ultrasonic waves, and compared with a visual scheme, the method is not affected by illumination conditions and has high fall recognition accuracy.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic testing, specifically to a method and related equipment for detecting falls in a sports field using ultrasonic waves. Background Technology

[0002] With the popularization of mass sports, new ball sports such as pickleball have been rapidly promoted, and the number of participants continues to expand. During ball sports, athletes frequently run, stop abruptly, turn sharply, dive to save the ball, leap to tackle, and swing their rackets, resulting in drastic changes in their center of gravity. This makes them highly susceptible to slips, trips, and falls. If falls are not identified and warned of in a timely manner, they can easily lead to secondary injuries and delays in rescue efforts, posing significant safety hazards in sports.

[0003] Visual fall detection is currently the most widely used non-contact fall detection method. It mainly uses cameras to capture scene images and combines image recognition and human posture skeleton extraction algorithms to determine whether a person has fallen. However, this method has inherent limitations when applied to sports fields: visual detection is greatly affected by lighting conditions. Sports fields have complex lighting interferences such as strong light, backlighting, shadows, nighttime lighting changes, and reflections, which can easily lead to image overexposure, contrast imbalance, and feature loss. This makes it difficult to reliably identify changes in human posture and height, and it has poor all-weather adaptability.

[0004] Therefore, how to provide a more effective fall detection solution for sports fields has become an urgent technical problem to be solved. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application provides a method for detecting falls in sports fields using ultrasound, the technical solution of which is as follows: In a first aspect, embodiments of this application provide a method for detecting a person's fall using ultrasound in a sports field. The method includes: controlling multiple ultrasound detection devices in the sports field to emit multiple ultrasound waves to a user; after receiving the ultrasound waves, an ultrasound receiver in a wearable device worn by the user returns response information to each of the ultrasound detection devices; determining whether the user has fallen based on all the response information; and performing a preset rescue operation after determining that the user has fallen.

[0006] Optionally, determining whether the user has fallen based on all the response information includes: acquiring the emission time of the ultrasonic wave emitted by each ultrasonic detection device and the response time of receiving the response information; determining the distance between the user and each ultrasonic detection device based on the emission time and response time of each ultrasonic detection device; establishing coordinate equations for each ultrasonic detection device based on the distance between the user and each ultrasonic detection device, resulting in multiple coordinate equations; calculating the user's three-dimensional coordinates based on the multiple coordinate equations, and determining the user's height above the ground based on the three-dimensional coordinates; and determining whether the user has fallen based on the height above the ground.

[0007] Optionally, the wearable device is worn on the user's wrist. The step of calculating the user's three-dimensional coordinates based on the multiple coordinate equations and determining the user's height above the ground based on the three-dimensional coordinates includes: calculating the three-dimensional coordinates of the wearable device worn by the user based on the coordinate equations, and using the Z-axis height in the three-dimensional coordinates as the user's height above the ground; the step of determining whether the user has fallen based on the height above the ground includes: acquiring the specific force modulus value of the accelerometer inside the wearable device worn by the user; establishing a sliding window with a width of a first preset duration and a step size equal to the measurement cycle of the ultrasonic receiver; during the sliding of the sliding window, if the downward change rate of the height above the ground is detected to be greater than a preset change rate threshold, and the specific force modulus value is at least partially exceeded... If the magnitude of the force is less than a preset weightlessness threshold, the state of the sliding window is locked, and a first detection window with a width of a second preset duration is established adjacent to the sliding window within a preset time tolerance range. Within the first detection window, if it is detected that the specific force modulus is greater than N times the gravitational acceleration for at least some time, and the ground clearance is less than or equal to a preset fall height threshold, a second detection window with a width of a third preset duration is established adjacent to the first detection window within a preset time tolerance range; where N is a positive integer greater than 1. Within the second detection window, the user's three-dimensional coordinates are continuously acquired, and the user's movement speed is determined based on the three-dimensional coordinates. If the user's movement speed meets a preset condition, it is determined that the user has fallen.

[0008] Optionally, the width range of the sliding window is [0.3S, 0.4S]; the width range of the first detection window is [0.25S, 0.45S]; the width range of the second detection window is [1S, 2S]; the range of the preset weightlessness threshold is (0.2g, 0.7g]; and the value range of N is [3.5, 7].

[0009] Optionally, the control of multiple ultrasonic detection devices within the sports field to emit multiple ultrasonic waves to the user includes: assigning a unique exclusive code to each ultrasonic detection device, embedding the exclusive code into the ultrasonic wave emitted by the corresponding ultrasonic detection device through pulse modulation; dividing an ultrasonic detection cycle into P emission time slots and at least one response time slot, wherein only one ultrasonic detection device emits ultrasonic waves in each emission time slot, and the ultrasonic detection devices corresponding to each emission time slot are different; in each emission time slot, the wearable device continuously acquires the ultrasonic waves emitted by the ultrasonic detection devices and records the arrival time of all ultrasonic waves; capturing the earliest arriving ultrasonic wave as the valid ultrasonic wave and recording the arrival time of the valid ultrasonic wave; parsing the exclusive code of the ultrasonic detection device in the valid ultrasonic wave and recording the correspondence between the arrival time and the exclusive code; after receiving the ultrasonic wave, the ultrasonic receiving device in the wearable device worn by the user returns response information to each ultrasonic detection device, including: in the response time slot, the wearable device sequentially returns response information containing the arrival time to each ultrasonic detection device corresponding to the exclusive code.

[0010] Optionally, capturing the earliest arriving ultrasonic wave as the valid ultrasonic wave and recording the arrival time of the valid ultrasonic wave includes: capturing the Mth received ultrasonic wave within the current time slice; where the initial value of M is 1; encoding and identifying the ultrasonic wave to determine the current encoding; matching the current encoding with the encoding set corresponding to all ultrasonic detection devices, and determining the most matching exclusive encoding of the current encoding in the encoding set; obtaining the order of the current time slice, and determining the ultrasonic detection device corresponding to the current time slice according to the order; determining whether the most matching exclusive encoding of the current encoding matches the ultrasonic detection device corresponding to the current time slice; if they match, then the Mth received ultrasonic wave is taken as the valid ultrasonic wave; if they do not match, then M = M + 1, and return to the step of capturing the Mth received ultrasonic wave within the current time slice.

[0011] Optionally, the preset rescue operation includes at least one of the following: sending a fall alarm message, user location information and the time of the fall to the stadium management terminal; and / or activating on-site audio-visual prompts; and / or sending an alarm notification to a preset contact person or rescue organization.

[0012] In a second aspect, this application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method for detecting human falls in a sports field based on ultrasound, as described in the first aspect.

[0013] Thirdly, this application provides a computer-readable storage medium storing an executable program, which is executed by a processor to implement the ultrasonic-based method for detecting human falls in a sports field as described in the first aspect.

[0014] Fourthly, this application provides a computer program product comprising a computer program that, when executed by a processor, implements the ultrasonic-based method for detecting human falls in a sports field as described in the first aspect.

[0015] One of the beneficial effects of this application is that an ultrasonic detection system is formed by using an ultrasonic detection device in the stadium and a wearable device worn by the user. The system uses ultrasonic waves to detect whether a user has fallen in the stadium. Compared with a visual solution, it is not affected by lighting conditions and has high accuracy in fall recognition. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a method for detecting falls in a sports field based on ultrasound, as provided in an embodiment of this application.

[0017] Figure 2 This is a schematic diagram illustrating the creation of the three windows provided in the embodiments of this application.

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0019] Figure 4 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0021] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0022] For ease of description of the first and second directions in the embodiments of this application, the first direction is the up-down direction in the figures, the second direction is the front-back direction in the figures, and the third direction is the left-right direction in the figures. The x-axis arrow direction is referred to as the "up" direction, the y-axis arrow direction as the "back" direction, and the z-axis arrow direction as the "right" direction, but these are not the sole limitations in the actual application of this application.

[0023] The courts mentioned in this application may include peak courts, basketball courts, badminton courts, etc., and this application makes no restrictions.

[0024] The sports field of this application is equipped with an intelligent management system. Through the intelligent management system, users can reserve venues and automatically enter and exit by scanning codes or facial recognition. The method of this application is applied to the aforementioned intelligent commercial sports field.

[0025] Please see Figure 1 , Figure 1 This is a schematic diagram of a process for detecting falls in a sports field based on ultrasound, provided in an embodiment of this application. Figure 1 As shown, the ultrasonic-based method 100 for detecting human falls in a sports field according to this application includes steps 110 to 140.

[0026] Step 110: Control multiple ultrasonic detection devices in the stadium to emit multiple ultrasonic waves to the user.

[0027] Optionally, multiple ultrasonic detection devices of this application may jointly form an ultrasonic base station array. The number and placement of the ultrasonic detection devices need to be standardized in accordance with the shape, size, distribution of sports areas, and obstruction conditions of the sports field, and this application does not impose any restrictions.

[0028] Optionally, it is necessary to ensure that when the user is located in any part of the court, the wearable device worn by the user can simultaneously receive signals from at least three or more ultrasonic detection devices, meeting the minimum data requirements for three-dimensional coordinate calculation.

[0029] The stadium contains numerous reflective surfaces such as hard surfaces, walls, roofs, and nets. In addition to propagating along a straight path between the ultrasonic detection device (hereinafter referred to as the base station), the ultrasonic detection sound waves emitted by the ultrasonic detection device (hereinafter referred to as the base station) will also be reflected, diffused, and refracted by various obstacles, forming multiple sound wave signals with different propagation paths and flight delays, which are then received by the wearable device in succession.

[0030] The core principle of ultrasonic ranging is the Time-of-Flight (TOF) method, and the ranging accuracy depends entirely on the flight time corresponding to the actual propagation path of the sound wave. According to the physical laws of sound wave propagation, in the same spatial environment, the straight-line distance between two points is the shortest, and the corresponding sound wave flight time is also the shortest. Therefore, the first arriving sound wave signal received by the wearable terminal is the direct signal that has propagated along the straight line between the base station and the terminal, and its flight time can truly reflect the actual spatial distance between the two.

[0031] The signals that arrive later are mostly clutter signals formed by reflection, diffusion, and refraction. These signals have long propagation paths and large flight delays. If such signals are used as a reference for calculation, the actual spatial distance between the base station and the terminal will be overestimated, which will lead to problems such as offset in three-dimensional coordinate calculation and distortion in the determination of ground clearance.

[0032] Based on the above principle, this application determines the earliest arriving ultrasonic signal as the valid trigger signal, and uses it as the benchmark for response initiation and time delay calculation, actively discarding all subsequent late-arriving clutter to ensure the accuracy of the flight time involved in the actual spatial distance calculation.

[0033] Even though each ultrasonic detection device in this application emits a unique and exclusive code (identity code) for its detection sound waves, and the wearable device can identify the source of the signal by decoding, if all ultrasonic detection devices emit ultrasonic signals at the same time, the multiple sound waves will overlap and the amplitude will mix within the stadium space.

[0034] The encoded information of ultrasonic signals relies on specific pulse waveforms and timing characteristics for modulation and transmission. When multiple sound waves propagate and superimpose simultaneously, the ultrasonic pulse waveform is disrupted. On one hand, the distorted pulse waveform can cause decoding errors, missing codes, or incorrect codes in the encoding and parsing module inside the wearable device, making it impossible to restore the encoded information of the proprietary code. On the other hand, the superimposed mixed sound waves will change timing characteristic points such as the signal's starting edge and peak point, making it impossible to accurately determine the true arrival time of the ultrasonic wave, resulting in errors in the calculation of flight duration.

[0035] Flight duration is the core input of the TOF ranging algorithm. The measurement error of flight duration will be propagated step by step, eventually causing the distance calculation results between the wearable device and each base station to deviate from the true value, further leading to errors in the three-dimensional coordinate solution and inaccurate determination of the ground altitude.

[0036] To this end, this application employs a Time Division Multiple Access (TDMA) mechanism, dividing a single global detection cycle into several independent and non-overlapping transmission time slots, with each ultrasonic detection device occupying its own dedicated transmission time slot. Within any given transmission time slot, only a single device is allowed to transmit ultrasonic detection signals, while the other devices remain silent. This ensures the integrity and clarity of the single-channel acoustic waveform, allowing for the proper parsing of the encoded modulation information, thus guaranteeing the accuracy of measurement data such as flight duration, distance, and three-dimensional coordinates from the source.

[0037] Based on the above description, step 110 may optionally include steps 111 to 115, and step 120 may include step 121.

[0038] Step 111: Assign a unique code to each ultrasonic testing device, and embed the unique code into the ultrasonic waves emitted by the corresponding ultrasonic testing device through pulse modulation.

[0039] In one embodiment, pulse modulation represents digital information by controlling the presence or polarity of ultrasonic pulses: a bit "1" in the encoding maps to an ultrasonic pulse of a preset width, and a bit "0" maps to silence of a corresponding duration. Thus, the ultrasonic detection device transmits a frame of modulated ultrasonic signal consisting of a pulse sequence within an allocated time slot, the envelope of which fully carries its unique encoding. In this way, the physical identity of different ultrasonic detection devices is embedded in their sound wave signals.

[0040] Step 112: Divide an ultrasonic detection cycle into P emission time slots and at least one response time slot. In each emission time slot, only one ultrasonic detection device emits ultrasonic waves, and the ultrasonic detection devices corresponding to each emission time slot are different from each other.

[0041] Each transmission time slot must be long enough to accommodate at least one complete ultrasonic transmission and channel protection interval. Within each transmission time slot, only one ultrasonic detection device is allowed to transmit ultrasonic waves through a scheduling mechanism, and the ultrasonic detection devices corresponding to any two transmission time slots must be different.

[0042] A typical scheduling method involves allocating time slices sequentially according to a uniquely coded index, allowing each node to transmit periodically in turn. A response time slice is set after the transmission time slice, used by the receiving node to send data back to the ultrasonic testing device, thus forming a complete bidirectional measurement frame structure.

[0043] Optionally, the number of response time slices can be one, so that all wearable devices transmit response information in the same response time slice; or the number of response time slices can be multiple, so that a separate response time slice is set for each wearable device. The specific choice can be made as needed, and this application does not impose any restrictions.

[0044] Step 113: In each of the emission time slices, the wearable device continuously acquires the ultrasonic waves emitted by the ultrasonic detection device and records the arrival time of all ultrasonic waves.

[0045] Step 114: Capture the earliest arriving ultrasound wave as the valid ultrasound wave and record the arrival time of the valid ultrasound wave.

[0046] Based on the fundamental principle that direct waves arrive before reflected waves, from multiple arrival times recorded within a time slice, the effective ultrasonic wave that truly corresponds to the current ultrasonic detection device and has the shortest propagation path is selected through dual constraints of timing and encoding. Its arrival time is then used as the basis for subsequent ranging or time difference calculations.

[0047] Optionally, in order to prevent the ultrasound waves from the previous transmission time slot from being delayed into the next transmission time slot, step 114 includes steps 1141 to 1147.

[0048] Step 1141: Capture the Mth received ultrasonic wave within the current time slice; where the initial value of M is 1.

[0049] Step 1142: Encode and identify the ultrasonic wave to determine the current code.

[0050] Step 1143: Perform code matching between the current code and the code set corresponding to all the ultrasonic testing devices, and determine the exclusive code that best matches the current code in the code set.

[0051] Specifically, the current code obtained in step 1142 is correlated one by one with the pre-stored code set within the receiving node. The code set contains the unique codes of all ultrasonic detection devices. By calculating the correlation coefficient, Hamming distance, or other similarity metrics between the current code and each unique code, the unique code with the highest similarity is selected as the "best-matching unique code," and this matching degree value is recorded. If the similarity is lower than a preset reliability threshold, the signal can be determined to be noise or severely distorted interference, and no further matching is performed.

[0052] Step 1144: Obtain the order of the current time slices, and determine the ultrasonic detection device corresponding to the current time slice based on the order.

[0053] Step 1145: Determine whether the most matching exclusive code of the current code matches the ultrasonic detection device corresponding to the current time slice.

[0054] Step 1146: If a match is found, the Mth received ultrasonic wave is taken as the valid ultrasonic wave.

[0055] Therefore, the earliest arriving ultrasonic wave is specifically encoded and verified in the above steps to prevent the ultrasonic wave from being transmitted across the transmission time slice.

[0056] Furthermore, in complex acoustic environments like sports fields, which are semi-enclosed and have multiple reflective surfaces, the ultrasonic signals emitted by the ultrasonic detection device will form multiple propagation paths after being reflected by walls, the ground, sports facilities, and even other people's bodies. Although using successful code matching and earliest arrival time as criteria for selecting valid ultrasonic waves can filter out most unexpected situations, it is still possible that the first arrived coded matching ultrasonic wave is a non-line-of-sight path signal that has undergone one or more reflections. That is, it may be a high-energy but non-direct reflection path signal. The distance value calculated based on the arrival time of this signal will be equal to the total distance of the reflection path, rather than the actual straight-line distance between the transmitter and the receiver.

[0057] Therefore, in step 1146, if a match is found, the Mth received ultrasonic wave is taken as a valid ultrasonic wave, which specifically includes the following steps: (1) Extract the received signal envelope of the Mth received ultrasonic wave.

[0058] (1.1) The Mth received ultrasonic wave is converted into a digital ultrasonic signal, denoted as the original signal r(t). The digital ultrasonic signal refers to the discrete digital sequence obtained by converting the received ultrasonic wave into an analog electrical signal and then sampling and quantizing it through an analog-to-digital converter.

[0059] (1.2) Perform bandpass filtering on r(t), the center frequency of the filter passband is equal to the carrier frequency of the ultrasonic wave emitted by the ultrasonic detection device, and the width of the filter passband covers the main spectral components generated by pulse modulation, to obtain the filtered signal rf(t).

[0060] The purpose of bandpass filtering is to suppress out-of-band noise and interference.

[0061] (1.3) The processor performs quadrature downconversion and low-pass filtering on rf(t), extracts the in-phase component I(t) and the quadrature component Q(t), and calculates the received signal envelope E(t) of the ultrasonic signal using the following formula:

[0062] Where t is a time variable, and the unit is seconds (s); the dimension of E(t) is the same as that of the original signal amplitude.

[0063] Wherein, E(t) is the curve of the instantaneous amplitude of the ultrasonic signal changing with time, providing basic waveform data for subsequent calculation of the received signal strength indication and the steepness of the envelope rising edge.

[0064] (2) Calculate the received signal strength indicator (RSSI) of the Mth ultrasonic wave.

[0065] Specifically, a preset noise threshold Eth is invoked, and E(t) is scanned starting from the beginning of the signal. The moment when E(t) first exceeds Eth is recorded as the pulse start moment. The moment when E(t) first falls below Eth is recorded as the pulse end time. Interval [ , This refers to the effective duration of the ultrasonic pulse.

[0066] During the effective duration, the Received Signal Strength Indication (RSSI) of the Mth ultrasonic wave is calculated using the following formula:

[0067] In the formula, K is the gain-power conversion constant of the ultrasonic receiver, which is obtained from the factory calibration and is in dBm.

[0068] RSSI represents the average power level of the ultrasonic pulse at the receiver.

[0069] (3) Calculate the steepness of the rising edge of the envelope of the Mth ultrasound.

[0070] The effective duration segment determined in step S2 [ , Within the range, scan the received signal envelope E(t) and find the maximum value, which is recorded as the envelope peak value. .

[0071] Then, from Start searching backwards at time t, and record the first time E(t) reaches 0.1* Time And reached 0.9* for the first time. Time The steepness of the rising edge of the envelope is calculated using the following formula. .

[0072]

[0073] in, The unit is , The larger the value, the steeper the pulse leading edge.

[0074] (4) Obtain the preset effective range of received signal strength and the preset steepness threshold.

[0075] The preset effective range of received signal strength can be obtained by the following method: the tester wears a wearable device and walks to various typical positions on the court, records the RSSI values ​​of the direct line-of-sight signals of all ultrasonic testing devices, and takes the minimum and maximum values ​​to determine the preset effective range of received signal strength.

[0076] The preset steepness threshold can be obtained by: collecting a large number of envelope rising edge steepness samples of direct-view path signals and typical reflected path signals under empty stadium conditions, and performing characteristic curve analysis to determine the optimal preset steepness threshold.

[0077] (5) Based on the received signal strength of the Mth ultrasound, the RSSI and the steepness of the envelope rising edge are indicated. Determine whether the Mth ultrasound wave is a valid ultrasound wave.

[0078] Optionally, if the Received Signal Strength Indicator (RSSI) of the Mth ultrasonic wave is within a preset valid range of received signal strength, and the rising edge steepness of the envelope of the Mth ultrasonic wave is greater than a preset steepness threshold, then the Mth ultrasonic wave is determined to be a valid ultrasonic wave; otherwise, M = M + 1, and return to the step of capturing the Mth received ultrasonic wave in the current time slice.

[0079] Specifically, the steepness of the rising edge of the envelope reflects the time-domain characteristics of the signal waveform. In a direct-view path, the signal travels in a straight line, resulting in a clean waveform with a steep rising edge. In a reflected path, because multiple paths arrive at different times, the waveform superimposed will have a gentler rising edge, thus resulting in a lower steepness.

[0080] Specifically, Received Signal Strength Indication (RSSI) reflects the energy attenuation of the signal. The strength of the line-of-sight path conforms to the free-space propagation model, and within a fixed-location stadium, the strength will fall within a calibrable and reasonable range. The strength of the reflected path, due to additional reflection losses and a longer path, is usually lower than this range.

[0081] Therefore, steps (1) to (5) above effectively improve the accuracy of subsequent coordinate measurements by filtering direct-view signals and reflected / diffuse signals through envelope rising edge steepness and received signal strength indication.

[0082] Step 1147: If there is no match, set M=M+1 and return to the step of capturing the Mth received ultrasound in the current time slice.

[0083] If the result is a mismatch, it indicates that the Mth signal being tested may be a malfunction caused by multipath interference, a delayed copy of a signal from another transmission time slice, or environmental noise. In this case, the signal is discarded, the count value M is incremented by 1 to point to the next ultrasonic signal with the second earliest arrival time in the receiver list, and the process jumps back to step 1141 for a new round of encoding identification and matching verification. This process is repeated until a matching valid signal is found.

[0084] Step 115: parse the unique code of the ultrasonic detection device in the valid ultrasonic waves, and record the correspondence between the arrival time and the unique code.

[0085] Based on steps 111 to 115 above, step 120 includes step 121.

[0086] Step 121: During the response time slice, the wearable device sequentially returns response information containing the arrival time to the ultrasonic detection device corresponding to each of the unique codes.

[0087] Step 120: After receiving the ultrasonic waves, the ultrasonic receiver in the wearable device worn by the user returns response information to each of the ultrasonic detection devices.

[0088] Optionally, each user can be provided with a small wearable wristband upon entry. The wristband is equipped with sensors such as an ultrasonic receiver and an IMU to detect falls without affecting the user's playing.

[0089] Based on the usage of each court, when a user is using a court, the corresponding ultrasonic detection device is activated to send ultrasonic waves to the court at a preset frequency. The ultrasonic receiver in the wearable wristband worn by the user receives the ultrasonic waves and returns response information. Thus, the distance between the user (specifically, the wristband worn by the user) and each ultrasonic detection device can be determined based on the transmission and reception times.

[0090] Specifically, the determination of whether a golf course is in use can be made based on the reservation information of each course in the course management system. For example, if a course is reserved and paid for during the time slot of 9:00-10:00, the ultrasonic detection device will be activated during the time slot of 9:00-10:00.

[0091] Step 130: Based on all the response information, determine whether the user has fallen.

[0092] Optionally, to determine whether a user has fallen, it is necessary to determine the user's height above the ground, which can be calculated from the distance of the user from each ultrasonic detection device. In this case, step 130 includes steps 131 to 135.

[0093] Step 131: Obtain the emission time of the ultrasonic wave emitted by each ultrasonic testing device and the response time of receiving the response information.

[0094] Step 132: Determine the distance between the user and each ultrasonic detection device based on the transmission time and response time of each ultrasonic detection device.

[0095] Specifically, distance = ultrasonic speed v * (response time - transmission time).

[0096] Step 133: Establish the coordinate equations for each ultrasonic testing device based on the distance between the user and each ultrasonic testing device, resulting in multiple coordinate equations.

[0097] Specifically, let Q ultrasonic detection devices be deployed within the stadium (Q≥3, three-dimensional positioning requires at least 3 sets of independent distances), and let the coordinates of the i-th ultrasonic detection device be... The three-dimensional coordinates of the wearable device to be determined are: P(x, y, z), and the distance from the i-th ultrasonic detection device to the wearable device is... .

[0098] The equation for solving a single coordinate is:

[0099] By establishing three or more coordinate solution equations, the desired three-dimensional coordinates of the wearable device, P(x, y, z), can be calculated.

[0100] Step 134: Solve the user's three-dimensional coordinates according to the multiple coordinate solution equations, and determine the user's ground clearance based on the three-dimensional coordinates.

[0101] Specifically, the user's three-dimensional coordinates are P(x, y, z) in step 133, and the user's height above the ground is determined by the Z-axis coordinate.

[0102] Furthermore, the calculated three-dimensional coordinates of the user are actually the three-dimensional coordinates of the wearable device. In this application, the three-dimensional coordinates of the wearable device are used to reflect the three-dimensional coordinates of the user.

[0103] Step 135: Determine whether the user has fallen based on the height above the ground.

[0104] Specifically, there are also ultrasonic fall detection technologies in other fields, but existing traditional ultrasonic fall detection technologies usually use ultrasonic ranging to achieve fall detection. For example, the published patents CN109345771A, a method and system for detecting human falls, and CN103424747A, fall prevention device and fall protection device, all use ultrasonic ranging to achieve fall detection or fall prevention.

[0105] However, ultrasonic ranging solutions are not well applied in sports fields because athletes frequently pick up balls and bend over, causing the distance between the body and the ground to vary widely, resulting in a high rate of misjudgment.

[0106] In particular, since the ultrasonic receiver of this application is built into the wristband, when the user picks up the ball or lowers his body to catch the ball, the measured Z-axis height will exceed the conventional fall threshold, thus being misidentified as a fall. Furthermore, users may also sit on the ground in the court. Conventional solutions that rely solely on distance thresholds to determine whether a fall has occurred are not suitable for the detection scenarios in the court.

[0107] Therefore, optionally, this application adopts a triple detection window, namely a weightlessness and fall window, a ground impact window, and a fall and stillness window, to perform three-stage continuous time-series detection, thereby distinguishing between active motion and passive imbalance.

[0108] At this point, step 135 specifically includes steps 1351 to 1355. Please refer to [further details]. Figure 2 , Figure 2 This is a schematic diagram illustrating the creation of three windows provided in an embodiment of this application. The following describes steps 1351 to 1355 and... Figure 2 Let me introduce it.

[0109] Step 1351: Obtain the specific force modulus value of the accelerometer in the wearable device worn by the user.

[0110] Specifically, conventional fall detection typically uses the magnitude of acceleration in the Z-axis (vertical) direction for fall detection. However, since the accelerometer in this application is worn on the user's wrist, the wrist will violently roll and rotate during a fall, making the wristband's posture completely uncontrollable.

[0111] If the Z-axis component is used, when a person falls, their wrist turns, and the original gravity or impact force will shift to the X or Y axis. The Z-axis reading will be very small, and the system will mistakenly think that no impact or weightlessness has occurred, thus leading to a false alarm.

[0112] Therefore, in step S1351, the specific force modulus is used for detection. No matter how the bracelet rotates, as long as a violent impact occurs (e.g., greater than 3g) or it enters a state of weightlessness in free fall (close to 0g), the specific force modulus will definitely undergo a corresponding violent change.

[0113] For ease of understanding, in the context of this scheme, this specific force modulus can be intuitively equated to the triaxial composite acceleration modulus directly output by the accelerometer, which reflects the interaction forces other than gravity. When a person is standing still, its value is approximately 1g; in a state of complete weightlessness, its value approaches 0g, where g is the acceleration due to gravity.

[0114] Step 1352: Establish a sliding window with a width of a first preset duration and a step size of the measurement cycle of the ultrasonic receiving device.

[0115] Optionally, the width range of the sliding window, i.e. the range of the first preset duration, is [0.3S, 0.4S].

[0116] Step 1353: During the sliding process of the sliding window, if the downward change rate of the height above the ground is detected to be greater than a preset change rate threshold, and the specific force modulus is less than a preset weightlessness threshold at least for a portion of the time, then the state of the sliding window is locked, and a first detection window with a width of a second preset duration is established adjacent to the sliding window within a preset time tolerance range.

[0117] Optionally, the preset change rate threshold is greater than 0.5 m / s.

[0118] Optionally, the preset weightlessness threshold range is (0.2g, 0.7g).

[0119] Among them, sliding window A is used for weightlessness fall detection. When a person falls, there will be a moment of weightlessness. In the weightless state, the specific force modulus of the human body is close to zero, and the height off the ground drops rapidly. However, the accelerometer of this application is on the human wrist. When falling, the wrist is often accompanied by struggle, reaching out to support itself, and other protective actions. This will make the wrist not completely weightless. Therefore, the preset weightlessness threshold of this application is not set to zero or close to zero.

[0120] Using only the rate of change of height from the ground can misclassify scenarios such as picking up a ball or bending the wrist to catch a ball as falls. Using only the acceleration modulus can misidentify scenarios that cause the wrist to experience a brief period of weightlessness as falls, such as a sudden drop in the specific force modulus at the turning point of rapid wrist movement (the transition between downward and upward movement), which can be misidentified as a fall. Therefore, using both the specific force modulus and the rate of change of height from the ground in sliding window A can effectively improve the initial screening accuracy of falls.

[0121] Step 1354: In the first detection window, if it is detected that the specific force modulus is greater than N times the gravitational acceleration at least for a portion of the time, and the ground clearance is less than or equal to a preset fall height threshold, then within a preset time tolerance range, a second detection window with a width of a third preset duration is established adjacent to the first detection window; where N is a positive integer greater than 1.

[0122] Among them, the first detection window B is the impact detection window, which is used to capture the instantaneous impact characteristics generated by the collision between the human body and the ground.

[0123] Optionally, the width range of the first detection window, i.e. the range of the second preset duration, is [0.25S, 0.45S].

[0124] Optionally, the value of N is in the range of [3.5, 7].

[0125] When a person falls, they collide with the ground. The impact force causes the force modulus to rise rapidly, usually exceeding 3.5g. However, in scenarios where the user actively lowers their height, the user will spontaneously apply a buffering force, preventing a direct and strong collision with the ground. Therefore, the first detection window can distinguish between the user actively lowering their height and lowering their height due to a fall.

[0126] Step 1355: In the second detection window, continuously acquire the user's three-dimensional coordinates, determine the user's movement speed based on the three-dimensional coordinates, and if the user's movement speed meets a preset condition, determine that the user has fallen.

[0127] Specifically, the third detection window is used to determine whether the user is stationary, thereby distinguishing between actively diving for the ball, standing up immediately after squatting, and being unable to get up quickly after falling.

[0128] Furthermore, the third detection window can distinguish between severe falls and minor, harmless falls. If a person gets up and moves quickly after a fall, there is no need to trigger an alarm.

[0129] Optionally, the width range of the second detection window, i.e. the range of the third preset duration, is [1S, 2S].

[0130] Based on the above physical mechanism, this invention abandons the traditional single judgment logic and sets up a triple continuous detection window. It obtains the user's accurate coordinates through ultrasonic measurement, thereby calculating the height off the ground and the movement speed. Then, it combines the specific force modulus value of the accelerometer and adopts a time-series progressive, feature binding and step-by-step verification method to achieve accurate differentiation between real and false falls.

[0131] If only a single-window detection is used, it can only capture any single feature such as height change or acceleration change, and cannot distinguish between active motion and passive imbalance, resulting in serious misjudgment. This application sets up a three-segment temporal window, strictly limiting the complete temporal link of weightlessness, impact, and finally stillness. Conventional sports field movements cannot simultaneously, completely, and temporally match these three sets of features.

[0132] Step 140: After confirming that the user has fallen, execute the preset rescue operation.

[0133] Optionally, the preset rescue operations include at least one of the following: sending a fall alarm message, user location information, and the time of the fall to the stadium management terminal; and / or activating on-site audio-visual prompts; and / or sending an alarm notification to a preset contact person or rescue organization.

[0134] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 200 includes: one or more processors 210 and a memory 220. Figure 3 Take a processor 210 as an example.

[0135] In some implementations, the processor 210 and the memory 220 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0136] In some implementations, processor 210 is configured to control multiple ultrasonic detection devices within the stadium to emit multiple ultrasonic waves to the user; after receiving the ultrasonic waves, the ultrasonic receiver in the wearable device worn by the user returns response information to each of the ultrasonic detection devices; based on all the response information, it is determined whether the user has fallen; and after determining that the user has fallen, a preset rescue operation is executed.

[0137] In some implementations, memory 220 serves as a non-volatile computer-readable storage medium, used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules for the ultrasonic-based method for detecting falls in a sports field as described in this application embodiment. Processor 210 executes various functional applications and data processing of the electronic device by running the non-volatile software programs, instructions, and modules stored in memory 220, thereby implementing the ultrasonic-based method for detecting falls in a sports field as described in the above method embodiment.

[0138] In some embodiments, memory 220 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created based on the use of the electronic device. Furthermore, memory 220 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 220 may optionally include memory remotely located relative to processor 210, and these remote memories may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0139] In some implementations, one or more modules are stored in memory 220 and, when executed by one or more processors 210, perform the ultrasonic-based method for detecting falls in a sports field as described in any of the above method embodiments, for example, performing the above-described method. Figure 1 Steps 110 to 140 of the method.

[0140] Please refer to Figure 4 , Figure 4 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable storage medium 300 stores program code 310, which can be called by a processor to execute the method for detecting falls in a sports field based on ultrasound, as described in the above method embodiments.

[0141] The computer-readable storage medium 300 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-volatile computer-readable medium. The computer-readable storage medium 300 has storage space for program code that performs any of the method steps of the control method described above. This program code can be read from or written to one or more computer program products. The program code may, for example, be compressed in a suitable form.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting falls in a sports field based on ultrasound, characterized in that, The method includes: Control multiple ultrasonic detection devices within the stadium to emit multiple ultrasonic waves to the user; After receiving the ultrasonic waves, the ultrasonic receiver in the wearable device worn by the user returns response information to each of the ultrasonic detection devices. Based on all the response information, determine whether the user has fallen; Once it is confirmed that the user has fallen, a preset rescue operation is performed.

2. The method according to claim 1, characterized in that, Based on all the aforementioned response information, determining whether the user has fallen includes: The emission time of the ultrasonic wave emitted by each ultrasonic testing device and the response time of receiving the response information are obtained. Based on the emission time and response time of each ultrasonic detection device, the distance of the user from each ultrasonic detection device is determined; Based on the distance between the user and each ultrasonic detection device, a coordinate solution equation for each ultrasonic detection device is established, resulting in multiple coordinate solution equations. The user's three-dimensional coordinates are calculated based on the multiple coordinate calculation equations, and the user's height above the ground is determined based on the three-dimensional coordinates. Whether a user has fallen is determined based on the height above the ground.

3. The method according to claim 2, characterized in that, The wearable device is worn on the user's wrist. The process of calculating the user's three-dimensional coordinates based on the multiple coordinate equations and determining the user's height above the ground based on the three-dimensional coordinates includes: The three-dimensional coordinates of the wearable device worn by the user are calculated according to the coordinate calculation equation, and the height of the Z-axis in the three-dimensional coordinates is taken as the user's height above the ground. The step of determining whether a user has fallen based on the ground clearance includes: Acquire the specific force modulus value of the accelerometer inside the wearable device worn by the user; Establish a sliding window with a width of a first preset duration and a step size equal to the measurement cycle of the ultrasonic receiving device; If, during the sliding process of the sliding window, the downward change rate of the ground height is detected to be greater than a preset change rate threshold, and the specific force modulus is less than a preset weightlessness threshold at least for a portion of the time, then the state of the sliding window is locked, and a first detection window with a width of a second preset duration is established adjacent to the sliding window within a preset time tolerance range. In the first detection window, if it is detected that the specific force modulus is greater than N times the gravitational acceleration at least for some time, and the ground clearance is less than or equal to a preset fall height threshold, then a second detection window with a width of a third preset duration is established adjacent to the first detection window within a preset time tolerance range; where N is a positive integer greater than 1. In the second detection window, the user's three-dimensional coordinates are continuously acquired, and the user's movement speed is determined based on the three-dimensional coordinates. If the user's movement speed meets a preset condition, it is determined that the user has fallen.

4. The method according to claim 3, characterized in that, The width range of the sliding window is [0.3S, 0.4S]; the width range of the first detection window is [0.25S, 0.45S]; the width range of the second detection window is [1S, 2S]; the range of the preset weightlessness threshold is (0.2g, 0.7g]; the value range of N is [3.5, 7].

5. The method according to claim 1, characterized in that, The control system controls multiple ultrasonic detection devices within the stadium to emit multiple ultrasonic waves to the user, including: Each ultrasonic testing device is assigned a unique code, which is then embedded into the ultrasonic waves emitted by the corresponding ultrasonic testing device using pulse modulation. An ultrasonic detection cycle is divided into P emission time slots and at least one response time slot. In each emission time slot, only one ultrasonic detection device emits ultrasonic waves, and the ultrasonic detection devices corresponding to each emission time slot are different from each other. In each of the emission time slices, the wearable device continuously acquires the ultrasonic waves emitted by the ultrasonic detection device and records the arrival times of all ultrasonic waves. The earliest arriving ultrasonic wave is captured as the valid ultrasonic wave, and the arrival time of the valid ultrasonic wave is recorded. The unique code of the ultrasonic detection device in the effective ultrasonic waves is parsed, and the correspondence between the arrival time and the unique code is recorded; After receiving ultrasonic waves, the ultrasonic receiver in the wearable device worn by the user returns response information to each ultrasonic detection device, including: During the response time slice, the wearable device sequentially returns response information containing the arrival time to the ultrasonic detection device corresponding to each of the unique codes.

6. The method according to claim 5, characterized in that, The process of capturing the earliest arriving ultrasonic wave as the valid ultrasonic wave and recording the arrival time of the valid ultrasonic wave includes: Capture the Mth received ultrasonic wave within the current time slice; where the initial value of M is 1; The ultrasonic waves are encoded and identified to determine the current encoding; The current code is matched with the code set corresponding to all the ultrasonic testing devices, and the exclusive code that best matches the current code is determined in the code set. Obtain the order of the current time slices, and determine the ultrasonic detection device corresponding to the current time slice based on the order; Determine whether the most matching exclusive code of the current code matches the ultrasonic detection device corresponding to the current time slice; If a match is found, the Mth received ultrasonic wave is taken as the valid ultrasonic wave. If there is no match, then M = M + 1, and return to the step of capturing the Mth received ultrasound wave in the current time slice.

7. The method according to claim 1, characterized in that, The preset rescue operation includes at least one of the following: Send a fall alarm message, user location information, and the time of the fall to the stadium management terminal; and / or, Activate on-site audio-visual prompts; and / or, Send an alarm notification to the preset contact person or rescue organization.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the ultrasonic-based method for detecting human falls in a sports field as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an executable program, which is executed by a processor to implement the ultrasonic-based method for detecting human falls in a sports field as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for detecting human falls in a sports field based on ultrasound as described in any one of claims 1 to 7.

Images