WO2020097875A1 - 摔倒检测方法、装置、设备以及存储介质 - Google Patents

摔倒检测方法、装置、设备以及存储介质 Download PDF

Info

Publication number
WO2020097875A1
WO2020097875A1 PCT/CN2018/115718 CN2018115718W WO2020097875A1 WO 2020097875 A1 WO2020097875 A1 WO 2020097875A1 CN 2018115718 W CN2018115718 W CN 2018115718W WO 2020097875 A1 WO2020097875 A1 WO 2020097875A1
Authority
WO
WIPO (PCT)
Prior art keywords
riding
user
impact
emergency help
state
Prior art date
Application number
PCT/CN2018/115718
Other languages
English (en)
French (fr)
Inventor
左海亮
王晓虎
牛浩田
汤彧
Original Assignee
高驰运动科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 高驰运动科技(深圳)有限公司 filed Critical 高驰运动科技(深圳)有限公司
Priority to PCT/CN2018/115718 priority Critical patent/WO2020097875A1/zh
Priority to CN201880098049.1A priority patent/CN112805760B/zh
Publication of WO2020097875A1 publication Critical patent/WO2020097875A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons

Definitions

  • the embodiments of the present application relate to the technical field of sports protection, for example, to a fall detection method, device, equipment, and storage medium.
  • cycling is becoming an outdoor sport that people love more and more.
  • a fall is mainly detected based on a pressure sensor or image recognition.
  • the fall detection system based on the pressure sensor realizes the real-time detection of fall events by detecting and analyzing the changes of the sole pressure under normal walking and falling states.
  • a video monitor is installed in a specific area, the environment and furnishings in the area are identified, and the human body in the area is tracked and detected. When the human body is found lying down at a certain position It can be judged as falling over a long time. Or according to the abnormal movement of the human body to judge the fall.
  • the method of detecting falls based on the pressure sensor is mainly aimed at the signs of the standing state, which is judged by analyzing the changes in the sole pressure. This method will bring many false detections, such as sitting on the sofa or actively lying down. It is detected as a fall, because this method cannot determine whether the pressure change on the sole is the active or passive behavior of the subject, plus the pressure on the sole of the subject has many possibilities of change under normal life conditions. Therefore, this method has low reliability in detecting fall behavior. In the riding scene, the pressure of the sole of the foot is always in a state of change on the pedal, and it is more difficult to determine whether the ride actually fell.
  • the method of detecting falls based on image recognition is restricted by the space.
  • the embodiments of the present application provide a fall detection method, device, equipment, and storage medium, which can improve the accuracy of fall detection.
  • an embodiment of the present application provides a fall detection method, including: acquiring a triaxial acceleration of a riding user and calculating a vector sum of the triaxial acceleration; and judging whether the vector sum satisfies a weightlessness condition Whether the riding user enters a weightless state; if the riding user enters a weightless state, then within the duration of the weightless state, according to whether the vector sum meets the impact condition, determine whether the riding user has an impact; if If the riding user has an impact, the riding stop time of the riding user is determined after the impact; according to whether the first displacement speed before the preset time interval of the riding stop time satisfies the riding conditions, determine Whether the riding user is in an effective riding state before the preset time interval of the riding stop time; if the riding user is in the effective riding state before the preset time interval of the riding stop time, then It is determined that the riding user has fallen.
  • an embodiment of the present application further provides a fall detection device.
  • the device includes: an acceleration acquisition module configured to acquire a triaxial acceleration of a riding user and calculate a vector sum of the triaxial acceleration; weightlessness status judgment The module is set to determine whether the riding user enters the weightless state according to whether the vector sum meets the weightlessness condition; the impact occurrence judgment module is set to be in the weightlessness state if the riding user enters the weightless state.
  • the riding stop determination module is set to determine the riding user's Riding stop time; riding state judgment module, set to judge whether the riding user is at the riding stop time according to whether the first displacement speed before the preset time interval of the riding stop time satisfies the riding condition Whether it is in an effective riding state before the preset time interval; the fall state determination module is set to determine if the riding user is in an effective riding state before the preset time interval at the stop time of the riding The rider is falling.
  • an embodiment of the present application further provides an apparatus, the apparatus including: at least one processor; a storage device configured to store at least one program; when the at least one program is executed by the at least one processor, Causing the at least one processor to implement the fall detection method as described above.
  • an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the fall detection method as described above is implemented.
  • FIG. 3 is a schematic structural diagram of a fall detection device in an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a device in an embodiment of this application.
  • FIG. 5 is a schematic structural diagram of a device in another embodiment of this application.
  • FIG. 1 is a flowchart of a fall detection method in an embodiment of the present application. This embodiment can be applied to a situation where fall detection is implemented.
  • the method can be executed by a fall detection device, which can use at least software and hardware.
  • the device can be configured in a device.
  • the device can be a device such as a helmet that can be worn or carried by a user.
  • the method includes steps S110 to S160.
  • step S110 the triaxial acceleration of the riding user is acquired and the vector sum of the triaxial acceleration is calculated.
  • riding user is a user currently performing riding sports
  • specific type of riding sports is not limited in this embodiment, for example, riding sports include bicycle sports and motorcycle sports.
  • Acceleration is a physical quantity that describes how fast an object's speed changes. It is a space vector.
  • the three-axis acceleration represents the component of the object's acceleration on three coordinate axes. In this embodiment, without knowing the movement direction of the riding user in advance, the current three-axis acceleration of the riding user can be obtained through a three-axis acceleration sensor.
  • the current three-axis acceleration a x , a y and a z of the riding user are obtained through a three-axis acceleration sensor, and according to the formula Calculate the vector sum of the three-axis acceleration, where vector_sum a is the vector sum , a x , a y and a z are all vectors.
  • step S120 based on whether the vector sum meets the weightlessness condition, it is determined whether the riding user has entered a weightlessness state.
  • the weightlessness condition may be that the vector sum lasts less than or equal to the first threshold and the duration exceeds the first duration.
  • the sum of the first threshold and the first duration may be set according to the characteristics of the riding motion and riding state of the riding user.
  • the value range of the first threshold can be set to 0.2m / s 2 to 0.3m / s 2 according to the height range of the riding user during riding, for example, 0.25m / s 2
  • the first The value range of the duration is set to 250ms-350ms, for example, 300ms.
  • the cycling user if the vector sum continues to be less than or equal to the first threshold and the duration exceeds the first duration, it is determined that the riding user enters a weightless state. Otherwise, the cycling user has not entered the weightless state, and continues to obtain the triaxial acceleration of the cycling user.
  • step S130 if the riding user enters the weightless state, it is determined whether the riding user has an impact based on whether the vector sum meets the impact condition during the duration of the weightless state.
  • the impact condition is that the vector sum is greater than or equal to the second threshold, and the second threshold and the duration of the weightless state can be set according to the riding motion of the riding user and the characteristics of the riding state.
  • the value range of the second threshold can be set from 3m / s 2 to 4m / s 2 according to the speed range of the riding user during riding, for example, it can be 3.5m / s 2
  • the weightless state duration time The value range of is set to 1s-2s, for example it can be 2s.
  • the rider after the rider enters the weightless state, if the vector sum is greater than or equal to the second threshold during the weightless state, it is determined that the rider has collided, otherwise the rider has not collided. If the duration of the weightless state of the riding user is greater than or equal to 2s, the falling height of the riding user has exceeded the actual height of the riding tool. This data is the abnormal data of the fall during the riding and will not be processed.
  • step S140 if the riding user has an impact, the riding user's riding stop time is determined after the impact.
  • a possible way to determine the riding stop time of the riding user after the impact is: after the impact, if the real-time displacement speed at a time is less than the second displacement speed threshold, then the time Determine the moment when the ride stops.
  • the value range of the second displacement speed threshold is set to 0 m / s to 0.3 m / s, for example, it can be 0.2 m / s.
  • the real-time displacement speed can be obtained by the positioning module, and the positioning module can also obtain the current position of the riding user.
  • the riding user's riding stop time is determined according to the real-time displacement speed of the riding user after the impact.
  • step S150 according to whether the first displacement speed before the preset time interval of the riding stop time satisfies the riding condition, it is determined whether the riding user is in an effective riding state before the preset time interval of the riding stop time.
  • the riding condition is that the first displacement speed is greater than or equal to the first displacement speed threshold.
  • the first displacement speed threshold can also be set according to the riding motion of the riding user and the characteristics of the riding state.
  • the value range of the first displacement velocity threshold is 0.5 m / s to 2 m / s, for example, 0.8 m / s.
  • the first displacement speed is the real-time displacement speed before the preset time interval at the moment when the riding stops, and the preset time interval may be set according to need, and may be 10s in this embodiment.
  • the first displacement speed of the riding user before the preset time interval at the stopping time of the riding is greater than or equal to the first displacement speed threshold, it is determined that the riding user is before the preset time interval of the stopping time Effective riding state, otherwise the riding user is not in an effective riding state.
  • the rider during the fall during the ride is a process of sudden drop from a horizontal displacement speed to a horizontal displacement speed to stop. Therefore, the addition of the judgment of the effective riding state in this embodiment can effectively avoid the misjudgment when the device such as a helmet is thrown on the sofa or falls from the desktop, and the accuracy of fall detection can be improved, so that the scene requiring assistance Medium, will not disturb cycling users and emergency contacts.
  • step S160 if the riding user is in a valid riding state before the preset time interval at the moment when the riding stops, it is determined that the riding user has fallen.
  • the specific alarm method can be set as needed, and is not limited in this embodiment.
  • the vector sum is used to determine whether the riding user enters a weightless state and whether there is an impact. If the riding user experiences weightlessness and impact, the The first displacement speed of the riding user before the preset time interval at the moment when the riding stops determines whether it is in the effective riding state, and if the riding user is in the effective riding state, it is determined that the riding user has fallen.
  • This embodiment increases the judgment of the effective riding state, avoids the misjudgment during human operation, and improves the accuracy of fall detection.
  • FIG. 2 is a flowchart of a fall detection method in another embodiment of this application. The method includes steps S210 to S290.
  • step S210 the triaxial acceleration of the riding user is acquired and the vector sum of the triaxial acceleration is calculated.
  • step S220 based on whether the vector sum meets the weightlessness condition, it is determined whether the riding user has entered a weightlessness state.
  • the cycling user if the vector sum continues to be less than or equal to the first threshold and the duration exceeds the first duration, it is determined that the riding user enters a weightless state. Otherwise, the cycling user has not entered the weightless state, and continues to obtain the triaxial acceleration of the cycling user.
  • step S230 if the riding user enters the weightless state, it is determined whether the riding user has an impact based on whether the vector sum meets the impact condition during the duration of the weightless state.
  • the rider after the rider enters the weightless state, if the vector sum is greater than or equal to the second threshold during the weightless state, it is determined that the rider has collided, otherwise the rider has not collided.
  • step S240 if the riding user has an impact, the riding user's riding stop time is determined after the impact.
  • the moment is determined to be the moment when the ride stops.
  • step S250 according to whether the first displacement speed before the preset time interval of the riding stop time satisfies the riding condition, it is determined whether the riding user is in an effective riding state before the preset time interval of the riding stop time.
  • the preset time interval of the riding user at the riding stop time is determined Previously it was in an active riding state, otherwise the riding user was not in an effective riding state.
  • step S260 if the riding user is in a valid riding state before the preset time interval at the moment when the riding stops, it is determined that the riding user has fallen.
  • step S270 an emergency help countdown signal is issued and the emergency help mode is entered.
  • an emergency help device which can be a device that can send a signal, such as a light or a voice player.
  • step S280 if the operation signal for canceling the emergency help mode of the riding user is not received within the preset countdown duration, emergency help information is issued to the outside.
  • the preset countdown duration can be set as required, and in this embodiment, the preset countdown duration can be 30s.
  • the wireless module can be a Bluetooth module.
  • the fall detection device controls the rider's mobile phone to make an emergency call to the outside through the Bluetooth module; the fall detection device can send an emergency call to the server containing the current position information and help when falling through the Bluetooth application Signal, the server sends an emergency help message containing information about the current location of the fall.
  • step S290 if the preset emergency contact's phone is accessed, the preset recording is automatically answered and played.
  • preset emergency contacts and preset recordings can be set as needed.
  • the emergency help information is sent out externally, if there is a telephone access for the preset emergency contact, the answer is automatically answered and the preset recording is played. While playing the preset recording, the rider can also communicate with the preset emergency contact by phone.
  • the effective time can be set as the preset recording time, or can be set as needed, for example, 30s.
  • the vector sum is used to determine whether the riding user enters a weightless state and whether there is an impact. If the riding user experiences weightlessness and impact, then according to The first displacement speed of the riding user before the preset time interval at the moment when the riding stops determines whether it is in the effective riding state, and if the riding user is in the effective riding state, it is determined that the riding user has fallen.
  • This embodiment increases the judgment of the effective riding state, avoids the misjudgment during human operation, and improves the accuracy of fall detection; and after the rider falls, the emergency help countdown is added to provide the rider with sufficient Response time, while ensuring the timeliness of rescue, ensures that the rider will not be disturbed and inconvenient in life, and improves the real-time and reliability of emergency assistance.
  • FIG. 3 is a schematic structural diagram of a fall detection device in an embodiment provided by the present application. This embodiment can be applied to a situation in which fall detection is implemented.
  • the fall detection device provided by the embodiment of the present application can execute the fall detection method provided by any embodiment of the present application, and has a function module corresponding to the execution method.
  • the device includes an acceleration acquisition module 310, a weightlessness state determination module 320, an impact occurrence determination module 330, a riding stop determination module 340, a riding state determination module 350, and a fall state determination module 360.
  • the acceleration acquisition module 310 is configured to acquire the triaxial acceleration of the riding user and calculate the vector sum of the triaxial acceleration.
  • the weightlessness state determination module 320 is configured to determine whether the riding user enters the weightlessness state based on whether the vector sum meets the weightlessness condition.
  • the impact occurrence judging module 330 is configured to determine whether the rider has a collision according to whether the vector sum meets the impact condition during the duration of the weightless state if the rider enters the weightless state.
  • the riding stop determination module 340 is configured to determine the riding stop time of the riding user after the collision if the riding user has an impact.
  • the riding state determination module 350 is set to determine whether the riding user is in an effective riding before the preset time interval of the riding stop according to whether the first displacement speed before the preset time interval of the riding stop meets the riding conditions Row status.
  • the falling state determination module 360 is configured to determine that the riding user is in a falling state if the riding user is in an effective riding state before a preset time interval at the moment when the riding stops.
  • the riding stop determination module 340 is set to: after the impact, if the real-time displacement speed at a moment is less than the second displacement speed threshold, determine the moment as the riding stop moment.
  • the weightlessness condition is that the vector sum continues to be less than or equal to the first threshold and the duration exceeds the first duration
  • the impact condition is that the vector sum is greater than or equal to the second threshold
  • the riding condition is that the first displacement speed is greater than or equal to the first A displacement speed threshold.
  • the first threshold is 0.25m / s 2
  • the first duration is 300ms
  • the second threshold is 3.5m / s 2
  • the first displacement velocity threshold is 0.8m / s
  • the second displacement velocity threshold is 0.2 m / s.
  • the device further includes an emergency help module.
  • the emergency help module includes: an emergency help countdown unit configured to send an emergency help countdown signal and enter the emergency help mode; an emergency help sending unit is set to If the operation signal of the rider canceling the emergency help mode is not received within the countdown time, an emergency help message is sent out.
  • the emergency help sending module unit is configured to dial an emergency help call to the outside or send an emergency help short message containing the current location information when falling.
  • the device further includes: an automatic answering module, configured to automatically answer and play the preset recording if the preset emergency contact's phone is accessed.
  • the fall detection device provided by the embodiment of the present application can execute the fall detection method provided by any embodiment of the present application, and has a function module corresponding to the execution method.
  • FIG. 4 is a schematic structural diagram of a device in an embodiment of this application.
  • FIG. 4 shows a block diagram of an exemplary device 412 suitable for implementing embodiments of the present application.
  • the device 412 shown in FIG. 4 is only an example, and should not bring any limitation to the functions and usage scope of the embodiments of the present application.
  • the device 412 is represented in the form of a general-purpose device.
  • the components of the device 412 may include, but are not limited to: acceleration sensors, positioning modules, emergency assistance devices, voice input devices, wireless modules, at least one processor 416, storage device 428, and components for connecting different systems (including storage device 428 and processor 416) ) Bus 418, acceleration sensor, positioning module, emergency help device, voice input device, and wireless module are connected to the processor 416 (not shown in FIG. 4).
  • the bus 418 represents at least one of several types of bus structures, including a storage device bus or storage device controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to industry standard architecture (Industry Subversive Alliance, ISA) bus, micro channel architecture (Micro Channel Architecture, MAC) bus, enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards) Association, VESA) local bus and peripheral component interconnect (PCI) bus.
  • Device 412 typically includes a variety of computer system readable media. These media may be any available media that can be accessed by device 412, including volatile and nonvolatile media, removable and non-removable media.
  • the storage device 428 may include a computer system readable medium in the form of volatile memory, such as at least one of a random access memory (Random Access Memory, RAM) 430 and a cache memory 432.
  • Device 412 may include other removable / non-removable, volatile / nonvolatile computer system storage media.
  • the storage system 434 can be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 4 and is commonly referred to as a "hard disk drive").
  • each drive may be connected to the bus 418 through at least one data medium interface.
  • the storage device 428 may include at least one program product having a set of (eg, at least one) program modules configured to perform the functions of each embodiment of the present application.
  • a program / utility tool 440 having a set of (at least one) program modules 442 may be stored in, for example, a storage device 428.
  • Such program modules 442 include but are not limited to an operating system, at least one application program, other program modules, and program data. Each of these examples or some combination may include an implementation of the network environment.
  • the program module 442 generally performs at least one of the functions and methods in the embodiments described in this application.
  • the device 412 may also communicate with at least one external device 414 (eg, keyboard, pointing terminal, display 424, etc.), at least one terminal that enables a user to interact with the device 412, and with the device 412 to enable at least one other computing terminal At least one of any terminals (eg, network card, modem, etc.) that communicates communicates. Such communication may be performed through an input / output (I / O) interface 422.
  • the device 412 can also communicate with at least one network, such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN), and a public network (such as the Internet) through a network adapter 420. As shown in FIG.
  • the network adapter 420 communicates with other modules of the device 412 through the bus 418. It should be understood that although not shown in the figure, at least one of other hardware modules and software modules may be used in conjunction with the device 412, including but not limited to: microcode, terminal driver, redundant processor, external disk drive array, disk array (Redundant Arrays of Independent Disks, RAID) systems, tape drives and data backup storage systems, etc.
  • the processor 416 executes programs stored in the storage device 428 to execute various functional applications and data processing.
  • the fall detection method provided by the embodiment of the present application may be implemented.
  • the method includes: acquiring the triaxial acceleration of the riding user and calculating the vector sum of the triaxial acceleration; judging whether the riding user enters according to whether the vector sum satisfies the weightlessness condition Weightlessness state; if the rider enters the weightlessness state, then during the weightlessness state, according to whether the vector sum meets the impact conditions, determine whether the rider has an impact; if the rider has an impact, determine the rider after the impact According to whether the first displacement speed before the preset time interval of the riding stop time satisfies the riding conditions, to determine whether the riding user is in an effective riding state before the preset time interval of the riding stop time; If the riding user is in the effective riding state before the preset time interval at the moment when the riding stops, it is determined that the riding user has fallen.
  • the helmet may include an acceleration sensor 514, a positioning module 516, an emergency help module 522, a voice input module 520, a wireless communication module 518, and at least one processor 512.
  • the acceleration sensor 514 built in the helmet device may be a three-axis acceleration sensor. Through the acceleration sensor 514 and the positioning module 516, the three-axis acceleration value of the helmet during riding and the speed information of the current position are obtained, and the obtained information is sent to The processor 512 performs calculation to determine whether an accident of falling during riding occurs. If a fall accident occurs while riding, the emergency help module 522 prompts the user to enter the emergency mode. If the user does not cancel the emergency mode within the safe time, the processor 512 sends out a help call and information through the wireless communication module 518. When the phone is connected, the voice input / output module 520 talks to the outside world to get help.
  • An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored.
  • a fall detection method as provided in the embodiment of the present application is implemented.
  • the method includes: obtaining a ride Calculate the three-axis acceleration of the user and calculate the vector sum of the three-axis acceleration; according to whether the vector sum meets the weightlessness condition, determine whether the riding user enters the weightless state; if the riding user enters the weightless state, within the duration of the weightless state, according to the vector And whether the impact conditions are met, to determine whether the rider has a collision; if the rider has a collision, determine the rider's stop time after the collision; according to the first displacement before the preset time interval of the stop time Whether the speed satisfies the riding conditions, and judges whether the riding user is in an effective riding state before the preset time interval at the time when the riding stops; if the riding user is in the effective riding state before the preset time interval at the time when the riding stops, It is
  • the computer storage medium in the embodiments of the present application may use any combination of at least one computer-readable medium.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with at least one wire, portable computer disk, hard disk, random access memory (RAM), read only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal that is propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. .
  • the program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • the computer program code for performing the operations of the present application can be written in at least one programming language or a combination thereof, the programming language includes object-oriented programming languages-such as Java, Smalltalk, C ++, and also includes conventional procedural Programming language-such as "C" language or similar programming language.
  • the program code may be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or terminal.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), and the remote computer can also be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).
  • LAN local area network
  • WAN wide area network

Abstract

本申请实施例公开了一种摔倒检测方法、装置、设备以及存储介质，该方法包括：获取骑行用户的三轴加速度并计算三轴加速度的矢量和；根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态；若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击；若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻；根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑行用户摔倒。

Description

摔倒检测方法、装置、设备以及存储介质 技术领域
本申请实施例涉及运动保护技术领域，例如涉及一种摔倒检测方法、装置、设备以及存储介质。
背景技术
目前，骑行运动越来越多的成为人们喜爱的一个户外运动，但是，在骑行过程中通常会有一些意外状况发生，最常见的就是滑倒摔倒。摔倒的骑行者摔倒之后若不方便使用通讯工具，或者通讯工具无法找到时，不利于通知同伴，也不便于帮助摔倒的骑行者。因此需要对骑行用户的摔倒实现自动检测并及时通知外部人员。
相关技术中，主要基于压力传感器或图像识别检测摔倒。基于压力传感器的摔倒检测系统，通过检测并分析脚底压力在正常行走和摔倒状态下的变化，实现跌倒事件的实时检测。基于图像识别检测摔倒的方法，在特定区域内安装视频监视器，对该区域内的环境和摆设进行识别，对该区域内的人体进行跟踪检测，当发现人体在某个位置的位置卧倒过长时间时，可判定为摔倒。或者根据人体的异常动作来判断跌倒。
基于压力传感器检测摔倒的方法主要是针对站立状态的体征，通过对脚底压力的变化分析来判断，这种方法会带来很多误检测，比如坐在沙发上或者主动躺下等行为都可能会被检测为是摔倒动作，因为这种方法无法判断脚底的压力变化是被检测者主动还是被动的行为，加上被检测者的脚底压力在正常生活状态下本来就有很多种变化的可能，所以该方式检测摔倒行为可靠度较低，在骑行场景下，脚底压力在踏板上一直处于一个变化的状态，更难去判断骑行是否真的摔倒。基于图像识别检测摔倒的方法受制于空间上的限制，只能在可检测的区域内检测跌倒，并要根据环境的不同来配置设备，同时视频检测可能还会产生隐私问题，用户会有使用中的排斥心理，针对室内的骑行场地具有一定的可行性，但是针对户外环境来配置设备几乎不可能实现。
发明内容
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的 保护范围。
本申请实施例提供了一种摔倒检测方法、装置、设备以及存储介质，可以提高摔倒检测的准确率。
第一方面，本申请实施例提供了一种摔倒检测方法，包括：获取骑行用户的三轴加速度并计算所述三轴加速度的矢量和；根据所述矢量和是否满足失重条件，判断所述骑行用户是否进入失重状态；若所述骑行用户进入失重状态，则在所述失重状态持续时间内，根据所述矢量和是否满足撞击条件，判断所述骑行用户是否发生撞击；若所述骑行用户发生撞击，则在撞击之后确定所述骑行用户的骑行停止时刻；根据所述骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断所述骑行用户在所述骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；若所述骑行用户在所述骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定所述骑行用户摔倒。
第二方面，本申请实施例还提供了一种摔倒检测装置，该装置包括：加速度获取模块，设置为获取骑行用户的三轴加速度并计算所述三轴加速度的矢量和；失重状态判断模块，设置为根据所述矢量和是否满足失重条件，判断所述骑行用户是否进入失重状态；撞击发生判断模块，设置为若所述骑行用户进入失重状态，则在所述失重状态持续时间内，根据所述矢量和是否满足撞击条件，判断所述骑行用户是否发生撞击；骑行停止确定模块，设置为若所述骑行用户发生撞击，则在撞击之后确定所述骑行用户的骑行停止时刻；骑行状态判断模块，设置为根据所述骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断所述骑行用户在所述骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；摔倒状态确定模块，设置为若所述骑行用户在所述骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定所述骑行用户处于摔倒状态。
第三方面，本申请实施例还提供了一种设备，所述设备包括：至少一个处理器；存储装置，设置为存储至少一个程序；当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如上所述的摔倒检测方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上所述的摔倒检测方法。
在阅读并理解了附图和详细描述后，可以明白其他方面。
附图说明
图1为本申请一实施例中的摔倒检测方法的流程图；
图2为本申请又一实施例中的摔倒检测方法的流程图；
图3为本申请一实施例中的摔倒检测装置的结构示意图；
图4为本申请一实施例中的设备的结构示意图；
图5为本申请又一实施例中的设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作详细说明。可以理解的是，此处所描述的实施例仅仅用于解释本申请，而非对本申请的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
图1为本申请一实施例中的摔倒检测方法的流程图，本实施例可适用于实现摔倒检测的情况，该方法可以由摔倒检测装置执行，该装置可以采用软件和硬件中至少一种的方式实现，该装置可配置于设备中，该设备可以为头盔等用户可以穿戴或随身携带的设备。该方法包括步骤S110至步骤S160。
在步骤S110中，获取骑行用户的三轴加速度并计算三轴加速度的矢量和。
其中，骑行用户为当前进行骑行运动的用户，骑行运动的具体类型本实施例中不做限定，例如骑行运动包括自行车运动和摩托运动等。
加速度是描述物体速度变化快慢的物理量，是空间矢量，三轴加速度表示物体加速度在三个坐标轴上的分量。在本实施例中，预先不知道骑行用户的运动方向，可以通过三轴加速度传感器获取骑行用户当前的三轴加速度。
在一实施例中，通过三轴加速度传感器获取骑行用户当前的三轴加速度a x、a y和a z，并根据公式
Figure PCTCN2018115718-appb-000001
计算三轴加速度的矢量和，其中vector_ suma为矢量和，a x、a y和a z均为矢量。
在步骤S120中，根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态。
其中，失重条件可以为矢量和持续小于或等于第一阈值且持续时间超过第一时长，第一阈值的和第一时长可以根据骑行用户的骑行运动以及骑行状态的特点进行设置。本实施例中根据骑行用户在骑行时的高度范围可以将第一阈值的取值范围设置为0.2m/s 2～0.3m/s 2，例如可以为0.25m/s 2，将第一时长的取值范围设置为250ms-350ms，例如可以为300ms。
在一实施例中，若矢量和持续小于或等于第一阈值且持续时间超过第一时长时，确定骑行用户进入失重状态。反之则骑行用户未进入失重状态，继续获取骑行用户的三轴加速度。
在步骤S130中，若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击。
其中，撞击条件为矢量和大于或等于第二阈值，该第二阈值和失重状态持续时间可以根据骑行用户的骑行运动以及骑行状态的特点进行设置。本实施例中根据骑行用户在骑行时的速度范围可以将第二阈值的取值范围设置为3m/s 2～4m/s 2，例如可以为3.5m/s 2，将失重状态持续时间的取值范围设置为1s-2s，例如可以为2s。
在一实施例中，骑行用户进入失重状态之后，在失重状态持续时间内，若矢量和大于或等于第二阈值，则确定骑行用户发生撞击，反之则骑行用户未发生撞击。若骑行用户的失重状态持续时间大于或等于2s，则骑行用户的摔落高度已经超过骑行工具的实际高度，该数据为骑行中摔倒的异常数据，不做处理。
在步骤S140中，若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻。
在一实施例中，一种可能的在撞击之后确定所述骑行用户的骑行停止时刻的方式为：在撞击之后，若一个时刻的实时位移速度小于第二位移速度阈值，则将该时刻确定为骑行停止时刻。其中，第二位移速度阈值的取值范围设置为0m/s～0.3m/s，例如可以为0.2m/s。实时位移速度可以通过定位模块获取，该定位模块也可以获取骑行用户的当前位置。
在一实施例中，若骑行用户发生撞击，则在撞击之后根据骑行用户的实时位移速度确定骑行用户的骑行停止时刻。
在步骤S150中，根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态。
其中，骑行条件为第一位移速度大于或等于第一位移速度阈值。第一位移速度阈值也可以根据骑行用户的骑行运动以及骑行状态的特点进行设置。本实施例中第一位移速度阈值的取值范围为0.5m/s～2m/s，例如为0.8m/s。第一位移速度为骑行停止时刻的预设时间间隔之前的实时位移速度，该预设时间间隔可以根据需要进行设置，本实施例中可以为10s。
在一实施例中，若骑行用户在骑行停止时刻的预设时间间隔之前的第一位移速度大于或等于第一位移速度阈值，则确定骑行用户在停止时刻的预设时间间隔之前处于有效骑行状态，反之则骑行用户未处于有效骑行状态。
一般物品的跌落以及自主意识形态下的卧倒，与骑行中的摔倒相比，骑行中的摔倒时骑行用户是从一个具有水平位移速度骤降为水平位移速度停止的过程。因此，本实施例中增加有效骑行状态的判断，可以有效避免设备例如头盔等随手扔到沙发或从桌面跌落等状况发生时误判，提高摔倒检测的准确率，进而在需要求助的场景中，不会给骑行用户和紧急联系人带来打扰。
在步骤S160中，若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑行用户摔倒。
若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则可以确定骑行用户摔倒，并进行报警处理。具体的报警方式可以根据需要进行设置，本实施例中不作限定。
上述实施例中，通过获取骑行用户的三轴加速度并计算三轴加速度的矢量和，根据矢量和判断骑行用户是否进入失重状态以及是否发生撞击，若骑行用户发生失重以及撞击，则根据骑行用户在骑行停止时刻的预设时间间隔前的第一位移速度判断是否处于有效骑行状态，若骑行用户处于有效骑行状态，则确定骑行用户摔倒。本实施例增加了有效骑行状态的判断，避免了人为操作时的误判，提高了摔倒检测的准确率。
图2为本申请又一实施例中的摔倒检测方法的流程图。该方法包括步骤S210至步骤S290。
在步骤S210中，获取骑行用户的三轴加速度并计算三轴加速度的矢量和。
在步骤S220中，根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态。
在一实施例中，若矢量和持续小于或等于第一阈值且持续时间超过第一时长时，确定骑行用户进入失重状态。反之则骑行用户未进入失重状态，继续获取骑行用户的三轴加速度。
在步骤S230中，若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击。
在一实施例中，骑行用户进入失重状态之后，在失重状态持续时间内，若矢量和大于或等于第二阈值，则确定骑行用户发生撞击，反之则骑行用户未发 生撞击。
在步骤S240中，若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻。
在一实施例中，若骑行用户发生撞击，则在撞击之后，若一个时刻的实时位移速度小于第二位移速度阈值，则将该时刻确定为骑行停止时刻。
在步骤S250中，根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态。
在一实施例中，若骑行用户在骑行停止时刻的预设时间间隔之前的第一位移速度大于或等于第一位移速度阈值，则确定骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，反之则骑行用户未处于有效骑行状态。
在步骤S260中，若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑行用户摔倒。
在步骤S270中，发出紧急求助倒计时的信号并进入紧急求助模式。
其中，可以通过紧急求助设备实现上述步骤，紧急求助设备可以为灯光或语音播放器等可以发出信号的设备。
在步骤S280中，若在预设倒计时时长内未收到骑行用户取消紧急求助模式的操作信号，则对外发出紧急求助信息。
其中，预设倒计时时长可以根据需要进行设置，本实施例中预设倒计时时长可以为30s。
若骑行用户在预设倒计时时长内未取消进行求助模式，则说明骑行用户发生昏迷不醒或无法行动的紧急状态，可以通过无线模块对外拨打紧急求助电话或发送包含摔倒时的当前位置信息的紧急求助短信。无线模块可以为蓝牙模块，摔倒检测装置通过蓝牙模块控制骑行用户的手机对外拨打紧急求助电话；摔倒检测装置通过蓝牙连接的应用程序可以向服务器发送包含摔倒时的当前位置信息和求救信号，服务器发送包含摔倒时的当前位置信息的紧急求助短信。
在步骤S290中，若预设紧急联系人的电话接入，则自动接听并播放预设录音。
其中，预设紧急联系人和预设录音可以根据需要进行设置。
本实施例中，对外发出紧急求助信息之后，若存在预设紧急联系人的电话接入，则自动接听并播放预设录音。播放预设录音的同时，骑行用户也可以跟 预设紧急联系人电话沟通。
当预设紧急联系人的电话接通并保持通话超过有效时间则视为一次有效通话，将结束紧急求助模式，但依然会自动接听预设紧急联系人的电话，并进入省电模式等待被救援。其中有效时间可以设置为预设录音的时间，也可以根据需要进行设置，例如设置为30s。
上述实施例中，通过获取骑行用户的三轴加速度并计算三轴加速度的矢量和，根据矢量和判断骑行用户是否进入失重状态以及是否发生撞击，若骑行用户发生失重以及撞击，则根据骑行用户在骑行停止时刻的预设时间间隔前的第一位移速度判断是否处于有效骑行状态，若骑行用户处于有效骑行状态，则确定骑行用户摔倒。本实施例增加了有效骑行状态的判断，避免了人为操作时的误判，提高了摔倒检测的准确率；并且骑行用户摔倒之后通过增加紧急求助倒计时，提供了骑行用户足够的反应时间，在保证救援及时性的同时确保不会给骑行用户带来生活中的打扰和不便，提高了紧急求助的实时性和可靠性。
图3为本申请提供的一个实施例中的摔倒检测装置的结构示意图，本实施例可适用于实现摔倒检测的情况。本申请实施例所提供的摔倒检测装置可执行本申请任意实施例所提供的摔倒检测方法，具备执行方法相应的功能模块。该装置包括加速度获取模块310、失重状态判断模块320、撞击发生判断模块330、骑行停止确定模块340、骑行状态判断模块350和摔倒状态确定模块360。
加速度获取模块310，设置为获取骑行用户的三轴加速度并计算三轴加速度的矢量和。
失重状态判断模块320，设置为根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态。
撞击发生判断模块330，设置为若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击。
骑行停止确定模块340，设置为若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻。
骑行状态判断模块350，设置为根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态。
摔倒状态确定模块360，设置为若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑行用户处于摔倒状态。
在一实施例中，骑行停止确定模块340设置为：在撞击之后，若一个时刻的实时位移速度小于第二位移速度阈值，则将该时刻确定为骑行停止时刻。
在一实施例中，失重条件为矢量和持续小于或等于第一阈值且持续时间超过第一时长，撞击条件为矢量和大于或等于第二阈值，骑行条件为第一位移速度大于或等于第一位移速度阈值。
在一实施例中，第一阈值为0.25m/s 2，第一时长为300ms，第二阈值为3.5m/s 2，第一位移速度阈值为0.8m/s，第二位移速度阈值为0.2m/s。
在一实施例中，该装置还包括紧急求助模块，该紧急求助模块包括：紧急求助倒计时单元，设置为发出紧急求助倒计时的信号并进入紧急求助模式；紧急求助发送单元，设置为若在预设倒计时时长内未收到骑行用户取消紧急求助模式的操作信号，则对外发出紧急求助信息。
在一实施例中，该紧急求助发送模单元设置为：对外拨打紧急求助电话或发送包含摔倒时的当前位置信息的紧急求助短信。
在一实施例中，该装置还包括：自动接听模块，设置为若预设紧急联系人的电话接入，则自动接听并播放预设录音。
本申请实施例所提供的摔倒检测装置可执行本申请任意实施例所提供的摔倒检测方法，具备执行方法相应的功能模块。
图4为本申请一实施例中的设备的结构示意图。图4示出了适于用来实现本申请实施方式的示例性设备412的框图。图4显示的设备412仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图4所示，设备412以通用设备的形式表现。设备412的组件可以包括但不限于：加速度传感器、定位模块、紧急求助设备、语音输入设备、无线模块、至少一个处理器416、存储装置428和连接不同系统组件(包括存储装置428和处理器416)的总线418，加速度传感器、定位模块、紧急求助设备、语音输入设备、无线模块分别与处理器416连接(图4中未示出)。
总线418表示几类总线结构中的至少一种，包括存储装置总线或者存储装置控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Subversive Alliance，ISA)总线，微通道体系结构(Micro Channel Architecture，MAC)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component  Interconnect，PCI)总线。
设备412典型地包括多种计算机系统可读介质。这些介质可以是任何能够被设备412访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
存储装置428可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)430和高速缓存存储器432中的至少一种。设备412可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统434可以用于读写不可移动的、非易失性磁介质(图4未显示，通常称为“硬盘驱动器”)。尽管图4中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘，例如只读光盘(Compact Disc Read-Only Memory，CD-ROM)，数字视盘(Digital Video Disc-Read Only Memory，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过至少一个数据介质接口与总线418相连。存储装置428可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请每个实施例的功能。
具有一组(至少一个)程序模块442的程序/实用工具440，可以存储在例如存储装置428中，这样的程序模块442包括但不限于操作系统、至少一个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块442通常执行本申请所描述的实施例中的功能和方法中的至少一种。
设备412也可以与至少一个外部设备414(例如键盘、指向终端、显示器424等)通信，至少一个使得用户能与该设备412交互的终端通信，和与使得该设备412能与至少一个其它计算终端进行通信的任何终端中的至少一种(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口422进行。并且，设备412还可以通过网络适配器420与至少一个网络，例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)，和公共网络(例如因特网)中的至少一种通信。如图4所示，网络适配器420通过总线418与设备412的其它模块通信。应当明白，尽管图中未示出，可以结合设备412使用其它硬件模块和软件模块中的至少一种，包括但不限于：微代码、终端驱动器、冗余处理器、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of  Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理器416通过运行存储在存储装置428中的程序，从而执行多种功能应用以及数据处理。例如可以实现本申请实施例所提供的摔倒检测方法，该方法包括：获取骑行用户的三轴加速度并计算三轴加速度的矢量和；根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态；若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击；若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻；根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑行用户摔倒。
图5为本申请另一实施例中的设备的结构示意图。下面以头盔为例对提供摔倒检测设备进行具体说明。如图5所示，头盔可以包括加速度传感器514、定位模块516、紧急求助模块522、语音输入模块520、无线通信模块518、至少一个处理器512。
头盔设备中内置的加速度传感器514可以为三轴加速度传感器，通过加速度传感器514和定位模块516，获取在骑行运动中头盔的三轴加速值和当前位置的速度信息，将获取到的信息发送至处理器512进行计算，判断，是否发生了骑行中摔倒意外事故。如果发生骑行中的摔倒事故，通过紧急求助模块522提示用户进入紧急模式，如果用户没有在安全时间内取消紧急模式，处理器512通过无线通信模块518对外发出求助电话和信息，期间如有电话接通的情况，通过语音输入/输出模块520与外界进行对话以便得到救助。
本申请一实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请实施例所提供的摔倒检测方法，该方法包括：获取骑行用户的三轴加速度并计算三轴加速度的矢量和；根据矢量和是否满足失重条件，判断骑行用户是否进入失重状态；若骑行用户进入失重状态，则在失重状态持续时间内，根据矢量和是否满足撞击条件，判断骑行用户是否发生撞击；若骑行用户发生撞击，则在撞击之后确定骑行用户的骑行停止时刻；根据骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断骑行用户在骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；若骑行用户在骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定骑 行用户摔倒。
本申请实施例的计算机存储介质，可以采用至少一个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括——但不限于无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以至少一种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言-诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言-诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或终端上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)-连接到用户计算机，远程计算机也可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。

Claims (15)

  1. 一种摔倒检测方法，包括：
    获取骑行用户的三轴加速度并计算所述三轴加速度的矢量和；
    根据所述矢量和是否满足失重条件，判断所述骑行用户是否进入失重状态；
    若所述骑行用户进入所述失重状态，则在所述失重状态持续时间内，根据所述矢量和是否满足撞击条件，判断所述骑行用户是否发生撞击；
    若所述骑行用户发生撞击，则在撞击之后确定所述骑行用户的骑行停止时刻；
    根据所述骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断所述骑行用户在所述骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；
    若所述骑行用户在所述骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定所述骑行用户摔倒。
  2. 根据权利要求1所述的方法，其中，所述在撞击之后确定所述骑行用户的骑行停止时刻，包括：
    在撞击之后，若一个时刻的实时位移速度小于第二位移速度阈值，则将该时刻确定为所述骑行停止时刻。
  3. 根据权利要求2所述的方法，其中，所述失重条件为所述矢量和持续小于或等于第一阈值且持续时间超过第一时长，所述撞击条件为所述矢量和大于或等于第二阈值，所述骑行条件为所述第一位移速度大于或等于第一位移速度阈值。
  4. 根据权利要求3所述的方法，其中，所述第一阈值的取值范围为0.2m/s 2～0.3m/s 2，所述第一时长的取值范围为250ms～350ms，所述第二阈值的取值范围为3m/s 2～4m/s 2，所述第一位移速度阈值的取值范围为0.5m/s～2m/s，所述第二位移速度阈值的取值范围为0m/s～0.3m/s。
  5. 根据权利要求1所述的方法，所述确定所述骑行用户摔倒之后，还包括：
    发出紧急求助倒计时的信号并进入紧急求助模式；
    若在预设倒计时时长内未收到用户取消所述紧急求助模式的操作信号，则对外发出紧急求助信息。
  6. 根据权利要求5所述的方法，其中，所述对外发出紧急求助信息，包括：
    对外拨打紧急求助电话或发送包含摔倒时的当前位置信息的紧急求助短信。
  7. 根据权利要求5所述的方法，所述对外发出紧急求助信息之后，还包括：
    若预设紧急联系人的电话接入，则自动接听并播放预设录音。
  8. 一种摔倒检测装置，包括：
    加速度获取模块，设置为获取骑行用户的三轴加速度并计算所述三轴加速度的矢量和；
    失重状态判断模块，设置为根据所述矢量和是否满足失重条件，判断所述骑行用户是否进入失重状态；
    撞击发生判断模块，设置为若所述骑行用户进入所述失重状态，则在所述失重状态持续时间内，根据所述矢量和是否满足撞击条件，判断所述骑行用户是否发生撞击；
    骑行停止确定模块，设置为若所述骑行用户发生撞击，则在撞击之后确定所述骑行用户的骑行停止时刻；
    骑行状态判断模块，设置为根据所述骑行停止时刻的预设时间间隔之前的第一位移速度是否满足骑行条件，判断所述骑行用户在所述骑行停止时刻的预设时间间隔之前是否处于有效骑行状态；
    摔倒状态确定模块，设置为若所述骑行用户在所述骑行停止时刻的预设时间间隔之前处于有效骑行状态，则确定所述骑行用户处于摔倒状态。
  9. 根据权利要求8所述的装置，其中，所述骑行停止确定模块设置为：在撞击之后，若一个时刻的实时位移速度小于第二位移速度阈值，则将该时刻确定为所述骑行停止时刻。
  10. 根据权利要求9所述的装置，其中，所述失重条件为所述矢量和持续小于或等于第一阈值且持续时间超过第一时长，所述撞击条件为所述矢量和大于或等于第二阈值，所述骑行条件为所述第一位移速度大于或等于第一位移速度阈值。
  11. 根据权利要求8所述的装置，还包括紧急求助模块；所述紧急求助模块包括：紧急求助倒计时单元以及紧急求助发送单元；
    所述紧急求助倒计时单元，设置为发出紧急求助倒计时的信号并进入紧急求助模式；
    所述紧急求助发送单元，设置为在预设倒计时时长内未收到骑行用户取消紧急求助模式的操作信号，则对外发出紧急求助信息。
  12. 根据权利要求11所述的装置，其中，所述紧急求助发送单元设置为：对外拨打紧急求助电话或发送包含摔倒时的当前位置信息的紧急求助短信。
  13. 根据权利要求11所述的装置，所述装置还包括自动接听模块；
    所述自动接听模块，设置为若预设紧急联系人的电话接入，则自动接听并播放预设录音。
  14. 一种服务器，所述服务器包括：
    至少一个处理器；
    存储装置，设置为存储至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1～7中任一所述的摔倒检测方法。
  15. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如权利要求1～7中任一所述的摔倒检测方法。
PCT/CN2018/115718 2018-11-15 2018-11-15 摔倒检测方法、装置、设备以及存储介质 WO2020097875A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/115718 WO2020097875A1 (zh) 2018-11-15 2018-11-15 摔倒检测方法、装置、设备以及存储介质
CN201880098049.1A CN112805760B (zh) 2018-11-15 2018-11-15 摔倒检测方法、装置、设备以及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/115718 WO2020097875A1 (zh) 2018-11-15 2018-11-15 摔倒检测方法、装置、设备以及存储介质

Publications (1)

Publication Number Publication Date
WO2020097875A1 true WO2020097875A1 (zh) 2020-05-22

Family

ID=70731275

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/115718 WO2020097875A1 (zh) 2018-11-15 2018-11-15 摔倒检测方法、装置、设备以及存储介质

Country Status (2)

Country Link
CN (1) CN112805760B (zh)
WO (1) WO2020097875A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410341A (zh) * 2021-05-27 2022-11-29 北京金坤科创技术有限公司 一种塌方砸倒智能监测报警方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103501336A (zh) * 2013-09-30 2014-01-08 东北大学 一种基于物联网的救援人员安全防护监控系统及方法
CN106652347A (zh) * 2017-01-24 2017-05-10 深圳前海零距物联网科技有限公司 智能头盔摔倒检测方法及智能头盔
CN108734921A (zh) * 2018-03-30 2018-11-02 北京医健保健康管理有限公司 跌倒检测算法及其检测装置

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ATE525660T1 (de) * 2006-06-21 2011-10-15 Nxp Bv Sensor zur messung von beschleunigungen
JP2008080999A (ja) * 2006-09-28 2008-04-10 Takata Corp サイドエアバッグ装置
US9704369B2 (en) * 2008-06-27 2017-07-11 Barron Associates, Inc. Autonomous fall monitor using an altimeter with opposed sensing ports
CN102542724B (zh) * 2011-12-15 2014-01-01 上海移为通信技术有限公司 跌落检测报警方法
CN202694517U (zh) * 2012-07-16 2013-01-23 深圳市富晶科技有限公司 跌倒报警仪
JP2014229199A (ja) * 2013-05-24 2014-12-08 一般社団法人Ｊｍｉｉ 転倒時通報システム及び転倒時通報システム用プログラム
ES2744423T3 (es) * 2013-09-11 2020-02-25 Koninklijke Philips Nv Método y sistema de detección de caídas
CN103600792B (zh) * 2013-11-07 2016-04-13 陕西科技大学 一种电动车单手骑行提醒及主动安全保护系统及方法
CN103561144A (zh) * 2013-11-18 2014-02-05 中国人民解放军信息工程大学 基于智能手机的摔倒检测方法及装置
DE102013224725B4 (de) * 2013-12-03 2019-06-19 Robert Bosch Gmbh Verfahren zur Erkennung eines Sturzes eines Fahrers eines Zweirads sowie Vorrichtung hierzu
US9861151B2 (en) * 2014-12-05 2018-01-09 SaPHIBeat Technologies, Inc. Activity monitoring systems and methods for accident detection and response
CN105894730A (zh) * 2014-12-26 2016-08-24 陆婷 一种便携式gsm&gps跌倒检测器的研究与设计
CN104867309A (zh) * 2015-04-30 2015-08-26 深圳市全球锁安防系统工程有限公司 一种中老龄人安康服务智能穿戴设备及深度学习方法
AU2016293616B2 (en) * 2015-07-16 2020-03-12 Blast Motion Inc. Integrated sensor and video motion analysis method
KR20170048107A (ko) * 2015-09-17 2017-05-08 오민택 위급상황의 자동 통지가 가능한 알림 시스템
CN105342623B (zh) * 2015-09-25 2018-05-29 广东乐源数字技术有限公司 智能跌倒监护装置及其处理方法
CN206075495U (zh) * 2016-05-10 2017-04-05 深圳市吉声科技有限公司 骑行摔倒自动报警的系统
WO2018033882A1 (en) * 2016-08-19 2018-02-22 Tvs Motor Company Limited Safety system for a two-wheeler
CN106143738A (zh) * 2016-08-19 2016-11-23 广东濠绅科技有限公司 一种具有摔倒智能报警功能的自行车
CN106131792B (zh) * 2016-08-26 2019-11-01 北京小米移动软件有限公司 用户运动状态监测方法和装置
JP6964279B2 (ja) * 2017-01-19 2021-11-10 パナソニックＩｐマネジメント株式会社 歩行転倒防止装置、の制御装置、制御方法、並びに、プログラム
CN106981169B (zh) * 2017-04-10 2019-01-11 南京大学 一种低头族骑车安全监测与警告方法
CN108109336B (zh) * 2017-11-28 2020-11-13 北京品驰医疗设备有限公司 一种基于加速度传感器的人体跌倒识别方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103501336A (zh) * 2013-09-30 2014-01-08 东北大学 一种基于物联网的救援人员安全防护监控系统及方法
CN106652347A (zh) * 2017-01-24 2017-05-10 深圳前海零距物联网科技有限公司 智能头盔摔倒检测方法及智能头盔
CN108734921A (zh) * 2018-03-30 2018-11-02 北京医健保健康管理有限公司 跌倒检测算法及其检测装置

Also Published As

Publication number Publication date
CN112805760A (zh) 2021-05-14
CN112805760B (zh) 2022-09-06

Similar Documents

Publication Publication Date Title
US10416740B2 (en) Upsampling sensors to auto-detect a fitness activity
KR102546249B1 (ko) 오디오 신호를 출력하는 출력 장치 및 출력 장치의 제어 방법
US8531414B2 (en) Bump suppression
US9996161B2 (en) Buttonless display activation
US20100304757A1 (en) Mobile device and method for identifying location thereof
WO2019184499A1 (zh) 一种视频通话的方法、设备和计算机存储介质
CN108681498B (zh) 一种cpu占用率的监测方法、装置以及移动终端
CN109407871A (zh) 一种识别浸水状态的方法及装置、电子设备
KR20180116843A (ko) 모션 감지 방법 및 이를 지원하는 전자 장치
WO2020097875A1 (zh) 摔倒检测方法、装置、设备以及存储介质
CN108322602B (zh) 一种处理应用无响应的方法、终端和计算机可读存储介质
US9983693B2 (en) Spatial motion-based user interactivity
CN110072010B (zh) 一种跌落检测方法及终端设备
US11231766B2 (en) Multipoint sensor system for efficient power consumption
CN113778255A (zh) 触摸识别方法和装置
KR20210015638A (ko) 센서를 이용한 저전력 낙상 감지 방법 및 장치
CN108600517B (zh) 一种切换屏幕状态的方法及终端
KR102015981B1 (ko) 대상자 상태 정보를 제공하기 위한 장치, 로봇 및 방법
CN109995849B (zh) 一种信息记录方法及终端设备
CN108635805B (zh) 一种运动提醒方法及终端设备
CN114283556B (zh) 用于自主呼救的方法、装置、电子设备和存储介质
CN113647935B (zh) 跌落姿态识别方法及系统
CN116540862B (zh) 触控操作响应方法和电子设备
CN112506337B (zh) 操作请求处理方法、装置、计算机设备和存储介质
CN109886199A (zh) 信息处理方法、装置、车辆及移动终端

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940285

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 20/08/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18940285

Country of ref document: EP

Kind code of ref document: A1