Fall detection system for fall detection of person, method for fall detection of person, and computer program product for fall detection of person

Abstract

A fall detection system for performing fall detection of a person (30) is provided and comprises at least one motion and / or presence detector (1) to detect motion or presence of the person (30). The at least one motion and / or presence detector (1) is operated at least in a first operating mode having a first operating parameter or in a second operating mode having a second operating parameter. A fall detector (200) is provided to detect the position or presence of a person (30) based on a sensing signal from at least one motion and / or presence detector (1). A fall detector (200) detects a residence time during which a person sits or lies down and / or determines a hypotension risk index of the person (30). The fall detector (200) activates a second mode of operation if the residence time exceeds a time threshold and / or if the hypotension risk index exceeds a risk index threshold.

Description

Technical Field

[0001] The invention relates to a fall detection system for fall detection of a person in a sensing area, a method for fall detection of a person in a sensing area, and a computer program product for fall detection of a person in a sensing area. Background Art

[0002] The leading cause of injury for older adults (people over 65 years old) is falls. Falls in older adults are particularly dangerous because they can result in broken bones and head injuries. Falls in older adults can be particularly dangerous if the person is living alone because the injuries can be so severe that the older person is no longer able to save themselves or call for help.

[0003] The importance of this problem will further increase in importance over the next decade, as many elderly people want to stay in their own homes as long as possible. However, even in a normal home environment, the risk of falls and injuries to the elderly is high. In order to prevent falls and avoid further increases in the severity of injuries caused by falls, it is important to monitor the activities of the elderly, and in particular to reliably and quickly detect whether a fall or injury has occurred.

[0004] The most important fall events for the elderly are trip and fall events (rapid falls to the ground from a walking position), falls when getting in and out of a chair (rapid falls to the ground from a sitting position), soft falls events (the person tries to grab a piece of furniture to slow down the fall to the floor), stroke falls events (first a slow fall from a standing position to one knee and then to the ground), and falls from the floor (very long falls that occur when the elderly try to pick something up from the floor and do not have the strength to get up again and fall slowly to the ground).

[0005] US2019 / 0175074 A1 discloses a fall detection method, device and system for detecting whether a target object falls in a detection area. The fall detection method comprises: receiving a WIFI signal transmitted by a transmitter in a detection area, and extracting CSI data from the WIFI signal; preprocessing the CSI data to obtain CSI data to be identified; and processing the CSI data to be identified to determine a CSI phase difference. Falls are detected based on the CSI phase difference. Summary of the invention

[0006] It is an object of the present invention to provide a more accurate fall detection of a person in a sensing area.

[0007] According to a first aspect of the present invention, a fall detection system for performing fall detection of at least one person in a sensing area is provided. The system comprises at least one motion and / or presence detector to detect the motion or presence of a person. The at least one motion and / or presence detector may be operated in at least a first operating mode having a first operating parameter and a second operating mode having a second operating parameter. The fall detector detects the position or presence of a person in the sensing area based on a sensing signal from the at least one motion and / or presence detector. The fall detector may be operated in the first operating mode or in the second operating mode. The fall detector determines the risk of falling by detecting a residence time of a person sitting or lying down and / or by determining a hypotension risk index of the person. The fall detector is configured to activate the second operating mode if an increased risk of falling is determined when the residence time exceeds a time threshold and / or when the hypotension risk index exceeds a risk index threshold.

[0008] The fall detector may first determine the fall risk based on the dwell time and / or based on a hypotension risk index. If the fall risk is low or below a threshold, the motion detector and the fall detector may operate in a first operating mode, which may be a normal operating mode. If the fall risk is high or above a threshold, the motion detector and the fall detector may operate in a second operating mode, which may be a fall detection operating mode with increased fall detection sensitivity. Thus, the second operating mode may be more suitable for fall detection. The second operating mode may focus on fall detection, with other considerations such as bandwidth usage, power consumption, etc. being less important.

[0009] The at least one motion and / or presence detector can be implemented as a network of network devices configured to perform RF-based sensing in a sensing area. The network devices are distributed in the sensing area and are configured to communicate with each other based on RF signals. At least one network device is configured to receive RF signals from other network devices, based on which motion detection or presence detection can be performed.

[0010] According to one example, the system includes a network of network devices and a fall detector. The network devices are distributed in a sensing area and an area configured to communicate with each other based on an RF signal. At least one network device is configured to receive an RF signal that has been transmitted by a network device and has propagated through the sensing area, and output a sensing signal based on the received RF signal. Motion detection can be performed based on a sensing signal from a received timing sensing signal. The fall detector is configured to detect the position and / or posture and / or movement of a person in the sensing area based on a sensing signal from at least one network device. The fall detector can analyze the sensing signal from the network device to determine whether the person in the sensing area is in a sitting position (e.g., sitting on a seat, chair, etc.), and determine the sitting time or stay time, that is, determine how long the person is in a sitting position. Similarly, for a person lying in bed. The fall detector can be configured to control the operation of the network device for motion detection. In particular, the system and the network device can have at least a first and a second detection mode. The first detection mode can correspond to a normal detection mode. The second detection mode can correspond to a detection mode with increased sensitivity. If the fall detector has determined that a person is in a sitting position (e.g. sitting in a chair) in the sensing area for a period of time exceeding a threshold, the second mode may be activated. In particular, if an elderly person is sitting in a seat or chair for a long time, the risk of falling when leaving the chair is greater. In this case, the sensitivity of the fall detection may be increased.

[0011] The fall detector may also be configured to determine a hypotension risk index. If the hypotension risk index exceeds a threshold, the fall detector may activate a second operating mode. As an example, if a person is standing up or sitting up suddenly, the hypotension risk increases. If an elderly person gets up slowly, the hypotension risk decreases compared to a situation where the elderly person is getting up immediately. The fall detector may be configured to detect recent behavior of the elderly person, which may lead to an indication that he may have a higher willingness to take risks, the hypotension risk index increases, because due to the higher willingness to take risks, the elderly person may stand up or sit up suddenly against the advice of the caregiver. For example, if the elderly person is excited about something, a higher willingness to take risks may be inferred. For example, the excitement level may be determined based on the elderly person's posture, heartbeat and / or breathing rate. For example, as referenced Figure 3 The described RF-based sensing of the network devices may be used to determine posture, heart rate, and / or breathing rate.

[0012] If the fall detector has detected that the elderly person has been gently active (such as moving the feet up and down and clenching and unclenching the hands) before getting up, the hypotension risk index is reduced. If the elderly person has been marking time after standing up, the hypotension risk index is also reduced. If the elderly person sleeps with their head raised (for example, by using an extra pillow), the hypotension risk index can be reduced. If the elderly person has eaten a large meal or drunk a lot of alcohol, or is sick, the hypotension risk index may increase. The hypotension risk index increases during exercise or when straining on the toilet. If the fall detector has detected that the elderly person is anxious or panic based on a sensing signal from a network device, the hypotension risk index can be increased. If the elderly person has taken a long hot bath or shower, the hypotension risk index can be increased. The hypotension risk index can increase in the morning because orthostatic hypotension occurs more in the morning when blood pressure is naturally lower.

[0013] The fall detector may be configured to compare the hypotension risk index with a threshold value and, if the threshold value has been exceeded, activate the second operating mode (fall from chair mode).

[0014] According to one example, in the second operating mode (chair fall mode), the fall detector can be configured to distinguish between four main phases of a sit-to-stand transition, namely the flexion phase (leaning forward), the momentum transfer phase (leaving the seat), the extension phase (returning to an upright position), and the stabilization phase. The fall detector is configured to compare the motion detected during these four phases. If the detected motion does not correspond to the four phases, the fall detector can indicate in an alert that there is a possibility of a near fall or fall from a seat or chair. Alternatively, when an elevated risk of falling is inferred from a sit-to-stand transition, the fall detector can enter a third fall detection mode that prioritizes the accuracy of fall detection over other considerations, such as wireless bandwidth and energy consumption of the radio, to the greatest extent possible.

[0015] According to one example, the fall detector is configured to analyze sensing signals from the network device during four phases during a sit-to-stand transition and detect a regular motion trajectory across the room after the person has stood up from the chair. If the motion that the elderly person has performed corresponds to a walking motion, no alarm is issued. However, if no walking motion is detected, an alarm may be issued. For example, this approach can even capture difficult-to-detect types of falls, such as an elderly person—after standing up—falling back into the chair again and sliding off the chair.

[0016] The fall detector is further configured to take into account a high potential risk index when selecting an operating mode of the fall detection system. The high potential risk index may be determined by the fall detector by analyzing the movement of the person before the person has sat on the chair, during a period of time when the person is sitting on the chair, and / or after the person has just stood up.

[0017] The fall detector is configured to at least partially control the network devices of the network. In particular, the network devices of the network can operate in at least a first and a second operating mode. The first operating mode may correspond to a normal operating mode. The second operating mode may correspond to an enhanced fall detection mode. In the fall detection mode, the network device transmitting the RF signal can operate with increased power. In addition, the transmitting network device can operate at different frequencies. In addition, in the second operating mode (i.e., the fall detection operating mode), some network devices arranged in the sensing area can be selected to perform motion detection. For example, the number of network devices participating in fall detection can be increased from two devices to all five network devices in the room. In addition, in the second operating mode (i.e., the fall detection operating mode), the network device can transmit the RF signal more frequently, for example, instead of 500Hz, the network device can transmit the RF signal for fall detection at 1500Hz.

[0018] If the transmit power is increased, this may result in an increase in the value of the signal quality matrix (RSSI, CSI) and / or the signal-to-noise ratio used as input to the fall detection algorithm. This may result in higher resolution and better inferences (e.g., fewer false positives or negatives) for the fall detection algorithm.

[0019] In the fall detection mode of operation, the transmit beam of the transmitting network device may be changed.

[0020] The network of network devices (which may also be understood as a sensing network) comprises at least two network devices. Preferably, the network comprises more than three network devices, wherein the number of network devices in the network can be adapted based on the sensing area (fall detection area) in which sensing (fall detection) should be performed. For example, the larger the space, the more network devices can be provided in the network, and / or the more complex the shape of the space, the more network devices can be provided in the network.

[0021] In one example, the state and / or position and / or attitude is determined based on: i) the signal strength of multiple detected sensing signals and / or based on ii) channel state information derived from multiple detected sensing signals and a predetermined generated wireless sensing signal transmitted by a wireless transmitter. The state and / or position and / or attitude of at least one object in the sensing area can be based on the signal strength of multiple detected sensing signals. Since the signal strength of the sensing signal depends on the amplitude of the wireless signal that reaches the wireless receiver directly or indirectly (via reflection / diffraction), a single strength indicates different paths that the wireless signal can propagate from the wireless transmitter to the wireless receiver. Since these paths are highly dependent on the environment between the transmitting network device and the receiving network device, and therefore also on the location of the object in the environment, the signal strength indicates these locations. In addition, since the signal strength of multiple detected sensing signals is utilized, and since the sensing signals are detected by network devices arranged at different locations, more accurate information about the environment of the network device can be obtained as multiple different wireless multipaths in the sensing area.

[0022] In addition, the position of at least one object in the sensing area can be based on channel state information derived from multiple detected sensing signals and a predetermined generated wireless signal transmitted by the transmitting network device. The channel state information indicates the properties of the path that the wireless signal has taken from the wireless transmitter in the first network device to the wireless receiver in the second network device, and therefore describes how the wireless signal has propagated from the first network device (transmitter) to the second network device (receiver). Therefore, the channel state information also indicates the interaction of the wireless signal with the object along the propagation path. Therefore, the channel state information provides very accurate information about the network environment with which the wireless signal has interacted, for example, the wireless signal has been reflected, scattered or absorbed from the network environment. Since the predetermined generated wireless signal of the first network device is known and due to the network characteristics of the network, the channel state information can be derived from the sensing signal and the predetermined generated wireless signal.

[0023] According to one example, the network device can be implemented as a lamp (ceiling lamp, table lamp), a smart device (smart phone, smart watch, tablet computer, smart speaker), or a network-enabled electronic device (e.g., a laptop computer).

[0024] In one example, at least one of the network devices includes a lighting unit to implement lighting functionality. However, in other examples, the network device may also include other functionality, such as entertainment functionality, monitoring functionality, etc.

[0025] In one example, the motion and / or presence detector is implemented as a radar sensor (e.g., WiFi-based radar sensing, FMCW radar-based sensing, pulsed UWB radar-based sensing) or as a ToF (time of flight) based sensor. The radar sensor or the time of flight sensor can operate in at least a first and a second operating mode. The first operating mode can be a normal operating mode, and the second operating mode can be, for example, a fall detection operating mode with increased sensitivity. The fall detector detects the position or presence of a person in the sensing area based on a sensing signal from at least one motion and / or presence detector. The fall detector detects the residence time of a person sitting or lying down and / or determines a hypotension risk index of the person. The fall detector is configured to activate the second operating mode if the residence time exceeds a time threshold and / or if the hypotension risk index exceeds a risk index threshold.

[0026] The fall detector can be implemented as a dedicated device or can be integrated in a wireless hub or a central control unit. Alternatively, the fall detection can also be performed by one of the network devices. Alternatively, the fall detection can be performed by a remote device such as a server in the cloud. Furthermore, the fall detection can be performed by an IoT edge device. Therefore, it does not matter where the fall detection is performed as long as the function is performed based on a signal detected by a network device.

[0027] In another aspect of the present invention, a computer program product for performing fall detection of a person is proposed, wherein the computer program product comprises program code means for causing the system as described above to perform the method as described above.

[0028] It shall be understood that the system, the method, the computer program, and the network comprising the system have similar and / or identical preferred examples or embodiments, in particular as defined in the dependent claims.

[0029] It shall be understood that a preferred embodiment of the invention can also be any combination of the dependent claims or the above-described embodiments with the respective independent claim.

[0030] It shall be understood that the above aspects, and in particular the system of claim 1, the method of claim 11, and the computer program product of claim 13, have similar and / or identical preferred embodiments, in particular as defined in the dependent claims.

[0031] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In the following drawings:

[0033] Figure 1A block diagram of a fall detection system for performing fall detection on a person in a sensing area is shown,

[0034] Figure 2 shows a flow chart of fall detection,

[0035] Figure 3 A block diagram of a fall detection system is shown. DETAILED DESCRIPTION

[0036] Figure 1 A block diagram of a fall detection system for performing fall detection of a person in a sensing area is shown. The fall detection system 2 comprises a motion and / or presence detector 1 which can detect motion or presence of a person 30 in a sensing area 20. The fall detection system 2 also comprises a fall detector 200.

[0037] The fall detector 200 comprises a controller 210, an optional memory 220 and a motion analyzer 230. The motion analyzer 230 may be implemented as a gesture detector or a presence detector. The sensing signals from the motion and / or presence detectors may be used by the motion analyzer to detect the presence of a stationary person (who is not moving), since the presence of a human body mass will change the wireless multipath of the signals detected by the motion and / or presence detectors.

[0038] The controller 210 may control the operation of the motion and / or presence detector 1. The motion and / or presence detector 1 may operate in at least a first and a second operating mode. The controller 210 may activate at least the first and the second operating mode. The first operating mode is a normal operating mode. The second operating mode is a fall detection operating mode with increased sensitivity in particular. The controller 210 of the fall detector 200 may change the operation of the motion and / or presence detector 1 as compared to the first operating mode. The controller 210 may be able to change parameters of the motion and / or presence detector 1, such as the transmission power, the transmission frequency and the wireless messages sent per second.

[0039] The fall position detector 200 may further include an alarm unit 250 for activating an alarm in the event that a fall is detected.

[0040] The memory 220 of the fall detector 200 can be used to store historical data, which can be used for further analysis. Optionally, the memory 220 can also be used to store user-specific settings or parameters. Such user-specific parameters may relate to the user's age, the user's health status, etc.

[0041] The motion analyzer 230 receives the sensing signals from the motion and / or presence detector 1 and performs motion / presence analysis on the person 30 in the sensing area 20, in particular the person 30 in a sitting position (e.g., sitting on a seat like a chair 40 or the like). The motion analyzer 230 can specifically determine the sitting time or the dwell time of the person 30 on the seat 40. The motion analyzer 230 can also determine the dwell time of the person 30 lying on a bed or lying on a sofa, etc. In other words, the motion analyzer 230 can determine the time period of inactivity of the user. Then, the fall detector 200 (e.g., the controller 210 or the motion analyzer 230) can use this parameter to select one of at least two operating modes. For example, if the time period of inactivity (such as the dwell time of the person 30 on the seat 40 or lying down) exceeds a threshold, the second operating mode is activated. Similarly, the motion analyzer 230 can also additionally perform vital sign detection (heart rate, breathing rate) to further improve its decision when to activate the second operating mode. For example, if the period of inactivity is accompanied by a very low heart rate, the risk of falling is further increased.

[0042] In the second operating mode, the operating parameters of the motion and / or presence detector 1 are changed as compared to the first operating mode. These changes are performed in order to improve the sensitivity of fall detection. In particular, the second operating mode is adjusted to achieve improved fall detection in situations when the person 30 is getting up from a seat 40 or getting up after having been lying down. While it is relatively easy for the fall detector to detect a stumble type fall, because the person first walks and then falls heavily to the ground and the walking trajectory stops, a getting up from a chair type fall generates a less obvious time series RSSI / CSI characteristic. Therefore, since the second operating mode utilizes more advanced motion sensing, for example, chair fall detection is achieved. The second operating mode may also be referred to as a chair fall mode.

[0043] The fall detector 200 may optionally include a risk analyzer 240. The risk analyzer 240 is used to detect and analyze a high risk potential index. If the high risk potential index HRI is high, this information may be used by the controller 210 to select a second operating mode. The second operating mode may correspond to a special high performance sensing mode to best capture falls from a chair / falls after taking a few steps from a chair (e.g. due to dizziness).

[0044] The motion and / or presence detector may be implemented as in reference Figure 3The described network of network devices, radar sensors (e.g., FMCW radar, pulsed UWB radar-based sensing), thermal sensors, time-of-flight sensors, or sound sensors. These can be used to detect the movement and / or presence of a person in a sensing area. They can be used to determine the residence time of a person in a seat or when lying down. In other words, they are used to determine periods of inactivity, which may affect the risk of falling when the period of inactivity has ended and the person starts to move (i.e., get up or stand up).

[0045] Figure 2 FIG. 1 shows a flow chart of fall detection. Fall detection can be performed as shown in FIG. Figure 1 The fall detector 200 is implemented by the fall detection system 2 described above. In step S1, motion and / or presence detection is performed. In step S2, risk analysis is performed. In step S3, the fall detector 200 analyzes the motion and / or presence detection results. In addition, the fall detector may optionally analyze the results of the risk analysis. In step S4, if the residence time exceeds a time threshold and / or the risk index exceeds a risk threshold, the fall detector 200 activates the second operation mode.

[0046] Figure 3 A block diagram of a fall detection system for performing fall detection of a person in a sensing area is shown. The fall detection system 2 comprises a motion and / or presence detector 1. The motion and / or presence detector 1 comprises a network 10 of preferably several network devices 100. In other words, the motion and / or presence detector 1 may be implemented as a network 10 of several network devices 100. The fall detection system 2 comprises at least one fall detector 200 for detecting a fall of a person 30 in a sensing area 20. The network devices 100 are capable of communicating with each other based on RF signals. The network device 100 comprises an RF transceiver or RF transmitter 110 and an RF receiver for RF communication. The network device 100 may optionally comprise a lighting unit 120. Furthermore, the network device may comprise a controller 130.

[0047] According to one example, the network device 100 may include a sound generator 140 and / or a sound sensor 150. The network device may optionally include the sound generator 140, the sound sensor 150, or both. If at least part of the motion sensing is to be performed based on sound signals, only the sound generator 140 and the sound sensor 150 will be provided. Otherwise, the sound generator 140 and the sound sensor 140 may be omitted.

[0048] The network device 100 may be arranged at different locations in the sensing area 20. In the sensing area, a person 30 may sit on a seat like a chair 40, for example.

[0049] The fall detector 200 includes a controller 210, an optional memory 220, and a motion analyzer 230 and / or a posture detector and / or a real presence detector. The motion analyzer 230 can be implemented as a posture detector or a presence detector. Since the presence of human mass changes the wireless multipath in the sensing area, the presence detector can use RF sensing to detect the presence of a stationary person (who is not moving).

[0050] The controller 210 can control the operation of at least one of the network devices 100. The controller 210 can start at least a first and a second operation mode. The first operation mode is a normal operation mode. The second operation mode is a mode for detecting a fall from a chair, i.e., in the second operation mode, the controller 210 of the fall detector 200 can change the operation of at least one network device 100 as compared to the first operation mode. The controller 210 may be able to change parameters of the network device 100, such as transmission power, RF transmission frequency, wireless messages sent per second. In addition, the controller 210 may be able to select some of the plurality of network devices. Therefore, only the selected network devices 100 of the network devices 100 are used to detect the RF signal that has been transmitted by at least one network device 100.

[0051] The fall position detector 200 may further include an alarm unit 250 for activating an alarm in the event that a fall is detected.

[0052] The memory 220 of the fall detector 200 can be used to store historical data, which can be used for further analysis. Optionally, the memory can also be used to store user-specific settings or parameters. Such user-specific parameters may relate to the user's age, the user's health status, etc.

[0053] The motion analyzer 230 receives the sensing signal from the network device 100 and performs motion analysis of the person 30 in the sensing area 20, in particular, the person 30 in a sitting position (e.g., sitting on a chair 40 or the like). The motion analyzer 230 can specifically determine the sitting time or the stay time of the person 30 in a sitting position (e.g., on the chair 40). Then, the fall detector 200 (e.g., the controller 210 or the motion analyzer 230) can use the parameter to select one of at least two operation modes. For example, if the stay time or the sitting time of the person 30 in a sitting position (e.g., sitting on a seat or chair 40) exceeds a threshold, the second operation mode is activated.

[0054] In the second operating mode, operating parameters of the transmitting and / or receiving network devices are changed as compared to the first operating mode. These changes are performed to improve the sensitivity of fall detection. In particular, the second operating mode is adjusted to achieve improved fall detection in the case when the person 30 is getting up from the chair 40. Although it is relatively easy for the fall detector to detect a stumble type fall because the person first walks and then falls heavily to the ground and the walking trajectory stops, a getting up from a chair type fall generates a less obvious time series RSSI / CSI characteristic. Therefore, since the second operating mode utilizes more advanced RF sensing, chair fall detection is achieved. The second operating mode may also be referred to as a chair fall mode.

[0055] The fall detector 200 may optionally include a risk analyzer 240. The risk analyzer 240 is used to detect and analyze a high risk potential index. If the high risk potential index HRI is high, this information can be used by the controller 210 to select a second operating mode. The second operating mode may correspond to a special high-performance sensing mode to optimally capture falls from a chair / falls after taking a few steps from a chair (e.g., due to dizziness). The second operating mode may have a different RF sensing mode (i.e., RF network device) assignment. In addition, the transmit power may be different, the transmit / receive beam angles may be different, or the signal processing of the CSI signal may be different.

[0056] In the second mode of operation, the activated or active network devices 100 may be different from those in the first mode of operation. Optionally, during configuration of the fall detection system, the location of the chair 40 in the room may be predetermined and may be stored, for example, in the memory 220. Thus, in the second mode of operation, the location of the chair 40 may be taken into account when selecting from among the plurality of network devices 100 those network devices 100 that should be used during fall detection.

[0057] If the elderly person's sitting time or stay time on the chair has exceeded a threshold and / or if the high risk potential index HRI is high, the controller 210 can activate the second operation mode (chair fall mode). The controller 210 can also use a combination of these two parameters to activate the second operation mode.

[0058] The high potential risk index HRI can be considered high when a person is standing up or sitting up suddenly, when a person is getting up suddenly from the bed, or when a person's recent behavior indicates that he has a higher willingness to take risks. If the person has eaten a big meal or drank a lot of alcohol, or is sick, the high potential risk index may increase. In addition, the high potential index may also increase during exercise or when exerting force on the toilet. In addition, if the system has detected that the person is anxious or may panic, the high potential risk index increases. In addition, if the person has taken a long hot bath or shower, the high potential index also increases. During the morning period, the high potential risk index also increases.

[0059] The high risk potential index HRI may decrease or be reduced when a person is slowly getting out of bed, when a person is gently moving before getting up, when a person is marking time after standing up, or when a person is sleeping with the head raised (e.g., with an extra pillow).

[0060] A threshold value may be associated with the high potential risk index. If the high potential risk index exceeds the threshold value, the controller may activate the second operating mode. On the other hand, if the high potential risk index is below or far below the threshold value, the controller may not activate the second operating mode.

[0061] The motion analyzer 230 can analyze the motion of the person when the person stands up. In particular, the motion analyzer can analyze four motion phases during the sit-to-stand transition, namely the flexion phase (leaning forward), the momentum transfer phase (leaving the seat), the extension phase (returning to the upward position), and the stabilization phase. The motion analyzer 230 and / or the risk analyzer 240 can analyze the user's motion during the sit-to-stand transition. If the user does not follow these four motion phases, the motion analyzer 230 or the risk analyzer 240 can indicate this fact to the controller 210 so that the controller 210 can activate the second operating mode.

[0062] In a second operating mode, the transmission power of the transmitting network device may be increased to increase the sensitivity of the system. Alternatively or in combination, the transmission beam may be adapted. Here, the beam may be narrowed, or the main direction of the transmission may be changed. Combinations of these are also possible. The adaptation of the transmission beam may allow limiting the sensing volume. This is advantageous because it may be less susceptible to interference from other objects. An example may be a pedal fan mounted on the ceiling or an additional person or pet in the room. The motion or movement of the pedal fan or a second person or pet may affect the detection of the motion of a person getting up from a chair.

[0063] Additionally or alternatively, the number of network devices that transmit and / or receive the transmitted signal can be increased to increase the coverage of the system. Therefore, as the number of network devices increases, the density of the transmitted RF signal can increase, which in turn increases the sensitivity of the signal and increases the signal-to-noise ratio.

[0064] Additionally or alternatively, at least one or more network devices for transmitting the RF signal may be selected from a plurality of network devices.Thus, the sensing topology may be changed, for example, depending on the position of the chair and thus expected future fall events.

[0065] According to one example, the operation of the receiving network device may also be changed. In particular, the receiving volume may be modified. The receiving volume may indicate an area or space where a signal with a desired signal quality (RSSI, CSI) may be received. Additionally or alternatively, beamforming may be performed at the receiving network device.

[0066] The fall detector 200 may also be capable of storing user parameters or settings. Such settings may be a person's dehydration, vitamin B12 deficiency, alcohol consumption, medications and drug treatments, lower body weakness.

[0067] Preferably, at least two network devices 100 are used for fall detection.

[0068] According to one embodiment, the network device 100 may be implemented as a ceiling lamp.

[0069] A network device according to an example may be considered as any device suitable for forming a network with other network devices. In particular, the network device comprises a network device communicator suitable for receiving and transmitting wired or wireless signals, such as radio frequency signals, infrared signals, transmitting and receiving audio signals for audio sensing purposes, electrical signals, etc.

[0070] The network between the network devices can then be formed by communication between the network devices, which follows known network communication protocols such as WiFi, ZigBee, Thread, Bluetooth, etc. Preferably, the network device refers to an intelligent device, that is, a device that includes a communication unit for receiving and transmitting network communication signals but implements the functions of the corresponding traditional device in other ways. In particular, such an intelligent device may be a smart home or office device, in which case the corresponding traditional function will be the function of a traditional home or office device. Preferably, the traditional function refers to a lighting function, and the network device refers to a network lighting device that is further adapted to include a wireless transmitter and / or a wireless receiver. Optionally, the network device may also include a sound generator and / or a sound detector for audio sensing. However, the network device may also refer to, for example, a smart plug, a smart switch, etc.

[0071] The system may be part of a network, for example, may be part of one or more network devices. In particular, the system may be provided as hardware and / or software, as part of one of the network devices, or distributed over a plurality of network devices that communicate with each other to form the system. However, the system may also be provided as a standalone system, for example, in a device that is not part of a network of network devices but that communicates directly or indirectly with at least one of the network devices, for example, to control the network devices. For example, the system may be provided as part of a handheld computing device such as a smartphone, a tablet computer, a laptop computer, etc. However, the system may also be located in a cloud formed by one or more servers, wherein in this case, the system may communicate with the network (in particular the network devices) via one or more devices (such as routers) connected to the cloud.

[0072] According to an example, a network 10 having a plurality of network devices 100 implemented as lighting or luminous devices may be provided. The network device 100 includes a microphone (sound sensor 130) and / or a speaker (sound generator 120). Therefore, the sound generator 120 and the sound sensor 130 may be distributed in the sensing area 20.

[0073] The fall detector 200 may be implemented as a dedicated device, or may be integrated in a wireless hub or a central control unit. Alternatively, the fall detection 200 may also be performed by one of the network devices 100. Alternatively, the fall detection may be performed by a remote device such as a server in the cloud. Furthermore, the fall detection may be performed by an IoT edge device. Therefore, the location where the fall location detection is performed does not matter as long as the function is performed based on a signal detected by a network device.

[0074] In addition, fall detection can also be performed by a smart device that can be located in the sensing area and can communicate with the network 10 and the network device 100. As an example, an application can be run on such a smart device that is performing fall location detection. Alternatively, fall detection can be performed by a smart speaker or smart watch that can be arranged in the sensing area 20.

[0075] According to one example, several network devices 100 are arranged in the sensing area 20. The first plurality of network devices 100 may be arranged near the person 30. The second plurality of network devices 100 may be arranged away from the first plurality of network devices 100. In order to improve the accuracy of fall detection, the fall location detector 200 may select some of the first plurality of network devices 100.

[0076] According to further examples, information from fall detection can be used during RF position or motion sensing. According to one example, if based on fall detection, it is detected that a person has fallen from a chair, the sensing arrangement can be reconfigured and those network devices 100 that have a direct line of sight to the chest area of ​​the person who may have fallen from the chair are selected to more accurately measure the person's vital signs. Vital sign measurements can be performed based on audio sensing or RF sensing.

[0077] In one example, the network device 100 may be placed on a table and may be implemented as a table lamp (the network device may also include a light unit 140). In addition, the network device 100 may be implemented as a ceiling network device 100. The network device 100 may be arranged in or at a ceiling.

[0078] According to one example, the fall detector 200 controls several network devices 100 arranged in the sensing area 20 (eg, at the ceiling) to perform fall detection.

[0079] According to an example, it is proposed to preferably use a lighting system as a detection unit distributed across a room to monitor object status and / or position.According to an example, the network devices may be part of a lighting system and each network device may comprise at least one light unit.

[0080] According to an example, several network devices (sensing nodes) may be provided.

[0081] According to an example, the network device 100 may include a sound generator 140 and / or a sound sensor 150. The network device may optionally include a sound generator 140, a sound sensor 150, or both.

[0082] Thus, the motion and / or presence detector may be implemented by a sound generator and a sound sensor. In other words, the motion and / or presence detection is performed using sound signals. Optionally, the sound generator and the sound sensor may be as described in reference Figure 3A part of the network device described. Therefore, the state and / or position and / or posture can be determined based on the signal strength of multiple detected sensing signals (audio signals) and / or based on channel state information derived from multiple detected sensing signals (audio signals). The state and / or position and / or posture of at least one object in the sensing area can be based on the signal strength of multiple detected sensing signals. Since the signal strength of the sensing signal depends on the amplitude of the sound that reaches the sound detector directly or indirectly (via reflection / diffraction), a single intensity indicates different paths that the sound can propagate from the sound generator to the sound sensor. Since these paths are highly dependent on the environment between the sound generator and the sound detector, and therefore also on the position of the object in the environment, the signal strength indicates these positions. In addition, since the signal strength of multiple detected sensing signals is utilized, wherein the sensing signal is generated by the detection of the sound detectors arranged at different positions, the sensing signal provides information about the environment of the network device from multiple different sound paths.

[0083] In addition, the position of at least one object in the sensing area can be based on channel state information derived from multiple detected sensing signals and the predetermined generated sound. The channel state information indicates the properties of the path that the sound has taken from the sound generator to the sound detector, and therefore describes how the sound has propagated from the sound generator to the sound detector. Therefore, the channel state information also indicates the interaction of the sound with the object along the propagation path. Therefore, the channel state information provides very accurate information about the network environment with which the sound has interacted, for example, the sound has been reflected, scattered or absorbed from the network environment. Since the predetermined generated wireless signal of the first network device is known and due to the network characteristics of the network, the channel state information can be derived from the sensing signal and the predetermined generated sound.

[0084] Other variations to the disclosed examples or embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0085] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0086] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0087] The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, provided together with or as a part of other hardware; but may also be distributed in other forms, such as via the Internet, or other wired or wireless telecommunication systems.

[0088] Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A fall detection system (2) for performing fall detection of at least one person (30) in a sensing area (20), comprising at least one motion and / or presence detector (1) configured to detect the motion or presence of a person (30), wherein the at least one motion and / or presence detector (1) is operable in at least a first operating mode with first operating parameters and in a second operating mode with second operating parameters, and A fall detector (200) configured to detect the position or presence of a person (30) in a sensing area (20) based on a sensing signal from at least one motion and / or presence detector (1) in a first operating mode or a second operating mode, The fall detector (200) is configured to determine the risk of falling by detecting the length of time a person sits or lies down and / or is configured to determine a hypotension risk index of the person (30), wherein the fall detector (200) is configured to activate a second operating mode if the fall detector (200) determines a high risk of falling, wherein The motion and / or presence detector comprises a network (10) of network devices (100) configured to perform RF-based sensing in a sensing area (20), wherein the network devices (100) are distributed in the sensing area (20) and are configured to communicate with each other based on RF signals, and are further configured to: generating an RF signal by at least one network device (100), detecting an RF signal from a network device (100) after propagating through at least a portion of a sensing area (20), generating a sense signal indicative of the RF signal, and The fall detector (200) is further configured to The fall detector (200) detects the duration of a person sitting on the seat (40) or lying down, If the dwell time exceeds a time threshold, activating a second operating mode, and A fall of a person (30) is detected in a second operation mode based on an RF sensing signal from a network device (100).

2. The system according to claim 1, wherein The at least one motion and / or presence detector (1) comprises a network (10) of network devices (100) configured to perform RF-based sensing in a sensing area (20), wherein the network devices (100) are distributed in the sensing area (20) and are configured to communicate with each other based on RF signals, At least one of the network devices (100) is configured to receive RF signals from other network devices (100), based on which motion detection and / or presence detection and / or vital sign detection can be performed.

3. The system according to claim 2, wherein The fall detector (200) includes a controller (210) configured to control the operation of at least one of the network devices (100) to perform RF-based sensing in a sensing area (20).

4. The system according to any one of claims 2 to 3, wherein The fall detector (200) is configured to detect movement of a person (30) when the person is standing up from a sitting position or getting up from a lying position, wherein the fall detector (200) is configured to compare the detected motion with a standard sit-to-stand transition motion or a lie-to-stand transition motion, The fall detector (200) is configured to sound an alarm if the detected motion does not correspond to a standard sit-to-stand or lie-to-stand transition motion.

5. The system according to any one of claims 1 to 4, wherein A second operating parameter of the second operating mode is an increased transmission power, a change in transmission frequency, a greater number of activated network devices (100), and / or a modification of the reception volume.

6. The system according to any one of claims 2 to 5, wherein At least one of the network devices (100) includes lighting functionality.

7. A system according to any one of claims 2 to 6, wherein At least one network device (100) is implemented as a light unit, in particular a ceiling light, a light wall switch, a user interface device or a table lamp.

8. The system according to any one of claims 2 to 7, wherein At least one network device (100) comprises a sound generator (140) and another network device comprises a sound sensor (150), The sensing signal from the sound sensor (150) can be used for motion and / or presence detection and / or vital sign detection.

9. The system according to any one of claims 1 to 8, wherein The hypotension risk index depends on the health status of the person (30), the behavior of the person (30), and / or the risk tolerance of the person (30) determined by the agitation level of the person (30).

10. The system according to any one of claims 1 to 9, wherein The motion and / or presence detector (1) is implemented as a radar sensor or as a time-of-flight based sensor.

11. A method for performing fall detection of at least one person (30) in a sensing area (20), comprising the following steps detecting the movement and / or presence of a person (30) by means of at least one movement and / or presence detector (1), wherein the at least one motion and / or presence detector (1) is operable in at least a first operating mode with first operating parameters and in a second operating mode with second operating parameters, In the first operating mode or the second operating mode, the position or presence of a person (30) in the sensing area (20) is detected by the fall detector (200) based on the sensing signal from the at least one motion and / or presence detector (1), determining the risk of falling by detecting the duration of a person sitting or lying down by a fall detector (200) and / or by determining a hypotension risk index of the person (30), If the fall detector (200) determines a high risk of falling, a second operating mode is activated by the fall detector (200), wherein A motion and / or presence detector comprises a network (10) of network devices (100) configured to perform RF-based sensing in a sensing area (20), wherein the network devices (100) are distributed in the sensing area (20) and are configured to communicate with each other based on RF signals, comprising the following steps: generating an RF signal by at least one network device (100), detecting an RF signal from a network device (100) after propagating through at least a portion of a sensing area (20), generating, by the network device (100), a sensing signal indicative of the RF signal, The fall detector (200) detects the duration of a person sitting on the seat (40) or lying down, If the dwell time exceeds a time threshold, activating a second operating mode, and A fall of a person (30) is detected in a second operation mode based on an RF sensing signal from a network device (100).

12. A computer program product for performing fall detection of a person (30) in a sensing area (20), wherein the computer program product comprises program code means for causing a fall detection system according to any one of claims 1 to 10 to perform the method according to claim 11.

Images