CN107693022A - A kind of method and device for detecting falling over of human body - Google Patents

A kind of method and device for detecting falling over of human body Download PDF

Info

Publication number
CN107693022A
CN107693022A CN201710888350.XA CN201710888350A CN107693022A CN 107693022 A CN107693022 A CN 107693022A CN 201710888350 A CN201710888350 A CN 201710888350A CN 107693022 A CN107693022 A CN 107693022A
Authority
CN
China
Prior art keywords
human body
height
mrow
value
state
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN201710888350.XA
Other languages
Chinese (zh)
Inventor
张顺淼
王乾廷
宋天文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian University of Technology
Original Assignee
Fujian University of Technology
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 Fujian University of Technology filed Critical Fujian University of Technology
Priority to CN201710888350.XA priority Critical patent/CN107693022A/en
Publication of CN107693022A publication Critical patent/CN107693022A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1112—Global tracking of patients, e.g. by using GPS
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A61B5/1117—Fall detection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/08—Elderly

Abstract

The invention discloses a kind of device for detecting falling over of human body, including Wearable carrier and the detection means for being arranged at the carrier, detection means to include controller, and controller is connected to locating module, remote alarming device, collection terminal；Collection terminal includes 3-axis acceleration sensor, height sensor；Controller is by judging whether human body attitude angle exceedes normal range (NR), calculating human body attitude angle exceedes the probability of normal range (NR) in follow-up time, confirming human body with the presence or absence of height recovery, the subsequently accumulative step number of calculating human body to confirm whether human body is fallen down.The present invention fallen down by detection algorithm combination people during attitude angle and height variation feature be identified to falling down, not only increase substantially the accuracy rate for falling down detection, but also it may determine that the specific posture after falling over of human body, such as prostrate, lie on the back or lie on one's side, so that judged result is more accurate specific, this has pragmatic meaning for the development of tele-medicine.

Description

A kind of method and device for detecting falling over of human body
Technical field
The present invention relates to health monitoring field, more particularly to a kind of method and device for detecting falling over of human body.
Background technology
The elderly, which belongs to, easily falls down crowd, and the elderly is fallen down with the very high death rate, admission rate, is brought for the people huge Big economy and burden on society, research show, in the elderly of China's over-65s, have quite a few people once to fall down Cross, and the incidence fallen down raises with advancing age, thus succour the elderly fallen down in time to substantially reduce wound Residual rate and the death rate.
Also occur many wearable devices at present to be used for detecting falling down for old man, such as girdle ring, bracelet etc., girdle ring is placed old The waist of people, old man are required for removing girdle ring in laundry, and are placed on activity of the loins to old man and have certain shadow Ring；Compared to girdle ring, bracelet is more convenient and can more be received by old man, but current bracelet is mostly only with acceleration sensing Device, the accuracy rate of detection is fallen down than relatively low.Such as Application No. CN206210062U patent application, a kind of old man falls down calling for help intelligence Can bracelet.Such bracelet needs old man oneself to go, by alarm button, can just be alarmed, then some old men after falling down not It is clear-headed, can not be alarmed, so the limitation of this kind of bracelet is very big.Such as Application No. CN106971503A patents Shen Please, a kind of fall monitoring device and method.Acceleration change during such bracelet is fallen down using people is examined to falling down Survey, because human hand has six degree of freedom, can be moved to all directions, and the direction of motion of hand can not react human body body Dry change, which results in judging to fall down with relatively more wrong reports using only acceleration, accuracy rate is than relatively low.
In addition, also many detection means of falling down that fall monitoring is carried out using pulse transducer, heart rate sensor, and Anxious state of mind, strenuous exercise etc. are all likely to result in warning device wrong report, reduce the accuracy rate of detection.
For falling down Detection accuracy at present than relatively low situation, applicant proposed the application, and detection is fallen down to improve Accuracy rate.
The content of the invention
Patent of the present invention mainly for fall down at present in detection field accuracy rate than it is relatively low the problem of, it is proposed that one kind utilizes Acceleration transducer, height sensor and the outstanding algorithm of combination fall down the method and device of Detection accuracy significantly to submit.
To achieve the above object, the technical scheme is that：A kind of method for detecting falling over of human body, including following step Suddenly：
Establish coordinate, using human body fore-and-aft direction as X-axis, human body left and right directions be Y-axis, that vertical direction is that Z axis is established is three-dimensional The right-handed Cartesian coordinate in space；
Data acquisition, 3-axis acceleration value ax, ay, az and human body when gathering a certain moment human motion gather position Height value；
Attitude angle is calculated, Kalman filtering is carried out to 3-axis acceleration value ax, ay, az, by filtered 3-axis acceleration When value ax, ay, az are converted into this human body around the anglec of rotation pitch of X-axis, human body around the anglec of rotation roll of Y-axis, human body about the z axis Anglec of rotation yaw,
Confirm that first falls down condition, judge whether pitch or roll exceedes the normal model of daily life human motion respectively Enclose, if exceeding, tentatively draw human body to fall down state；
Confirm second to fall down condition, meet first fall down condition on the basis of, extraction human body is falls down after state in 1s Pitch and roll data, show that pitch or roll exceedes the probability of human motion normal range (NR), if pitch or roll exceedes just Whether the probability of normal scope is more than 2/3, judge the height value at human body collection position and reduce, if height value, which reduces, exceedes height threshold Value, then human body is from which further followed that to fall down state；
Confirm that the 3rd falls down condition, meet second fall down condition on the basis of, collection human body is falls down after state in 10s Human body gathers position height value, and judges that human body recovers with the presence or absence of height by height recovery algorithms, if in the absence of highly extensive It is multiple, then human body is further drawn to fall down state；The height recovery algorithms include：
Step 1: it is that Height value data after the state of falling down in 10s carries out mean filter to human body；
Step 2: the height value for taking first data point is initial value, and a height is taken in the data point subsequently every 1s Angle value；
Step 3: judge whether the difference of initial value subsequent data point height value and initial value is more than discrepancy in elevation threshold value, if being more than Discrepancy in elevation threshold value, then tentatively confirm that the point has height and recovered, into next step；
Step 4: judging point height recovery time, if being more than 3s, confirm that height be present recovers, otherwise, entrance is next Step；
Step 5: judging follow-up remainder strong point length, if being more than 3s, height is not present and recovers；If it is less than or equal to 3s, then remove a data point height value, three-step 5 of repeat step；
Confirm that the 4th falls down condition, meet the 3rd fall down condition on the basis of, obtain human body by counting step algorithm to fall Add up step number after state in 10s, the meter step algorithm includes：
1) calculate human body be acceleration after the state of falling down in 10s and；
2) the potential peak value of acceleration sum is searched by acceleration sliding window；
3) a potential peak value is selected, judges the state of the potential peak value, if the potential peak value >=1.2g, and ＜ 2g, meter For walking states；If the potential peak value is more than 2g, the state of running is calculated as；
4) calculate the different conditions potential peak value and previous time to peak is poor, if the walking states lower time difference belongs to time threshold Value [0.3s, 0.8s] or running state lower time difference belong to time threshold [0.2s, 0.5s], then carry out in next step；Otherwise, select Select another potential peak value, repeat 3) -4)；
5) calculate the potential pre-and post-peaking neighborhood acceleration and judge whether the potential peak value is maximum in neighborhood Value, if maximum in neighborhood, then counts a step；If it is not, another potential peak value of selection, 3) -5 are repeated)；
6) calculate and add up step number in 10s, if accumulative step number is less than step number threshold value, confirm as falling down, if more than or equal to step Number threshold value, then do not fall down.
A kind of device for detecting falling over of human body, including Wearable carrier and the detection means for being arranged at the carrier, The detection means includes controller, and controller is connected to locating module, remote alarming device, collection terminal；
The collection terminal includes 3-axis acceleration sensor, height sensor.
The application method of device fallen down that detects is：
Detection means is arranged on to the carrier for being worn on human body；
Locating module, for positioning current location information；
Collection terminal, for gather 3-axis acceleration value during human motion, carrier height value, and people is calculated Body attitude angle and height reduction value；
Controller is used to judge whether human body is to fall down according to a kind of above-mentioned method for detecting falling over of human body, if being judged as falling , the positional information in locating module is obtained, and positional information and warning message are sent to by distal end by remote alarming device User.
Further, the 3-axis acceleration sensor uses MEMS 3-axis acceleration sensors, and the height sensor is adopted With MEMS baroceptors.
Further, described device also includes power supply, buzzer, hand push button.
The beneficial effects of the invention are as follows：
1st, the application propose a kind of method of new detection falling over of human body, this method combination people fall down during attitude angle And height variation feature is identified to falling down, the accuracy rate for falling down detection is not only increased substantially, but also can sentence Break the specific posture after falling over of human body, such as prostrate, lie on the back or lie on one's side so that judged result is more accurate specific, and this is right There is pragmatic meaning in the development of tele-medicine.
2nd, the present invention not only detects to the characteristics of human body during falling down, herein in connection with the characteristics of human body after falling down and Height recovery algorithms, meter step algorithm come further verify human body it is no be to fall down, so as to further improve the accuracy rate of detection.
3rd, the present invention also provides a kind of device of the detection falling over of human body based on the above method, and the device is easy to use, by mistake Report rate is low.
Brief description of the drawings
Fig. 1 is a kind of flow chart for the method for detecting falling over of human body；
Fig. 2 is the flow chart of height recovery algorithms in Fig. 1；
Fig. 3 falls into a trap for Fig. 1 walks the flow chart of algorithm；
Fig. 4 is a kind of structural representation for the device for detecting falling over of human body.
Embodiment
The technical scheme in the embodiment of the present invention is clearly and completely described below in conjunction with accompanying drawing.
Embodiment 1
As shown in figure 1, a kind of method for detecting falling over of human body, comprises the following steps：
Establish coordinate, using human body fore-and-aft direction as X-axis, human body left and right directions be Y-axis, that vertical direction is that Z axis is established is three-dimensional The right-handed Cartesian coordinate in space；
Data acquisition, 3-axis acceleration value ax, ay, az and human body when gathering a certain moment human motion gather position Height value；
Attitude angle is calculated, Kalman filtering is carried out to 3-axis acceleration value ax, ay, az, by filtered 3-axis acceleration When value ax, ay, az are converted into this human body around the anglec of rotation pitch of X-axis, human body around the anglec of rotation roll of Y-axis, human body about the z axis Anglec of rotation yaw,
Confirm that first falls down condition, judge whether pitch or roll exceedes the normal model of daily life human motion respectively Enclose, if exceeding, tentatively draw human body to fall down state；
Confirm second to fall down condition, meet first fall down condition on the basis of, extraction human body is falls down after state in 1s Pitch and roll data, show that pitch or roll exceedes the probability of human motion normal range (NR), if pitch or roll exceedes just Whether the probability of normal scope is more than 2/3, judge the height value at human body collection position and reduce, if height value, which reduces, exceedes height threshold Value, then human body is from which further followed that to fall down state；
Confirm that the 3rd falls down condition, meet second fall down condition on the basis of, collection human body is falls down after state in 10s Human body gathers position height value, and judges that human body recovers with the presence or absence of height by height recovery algorithms, as shown in Fig. 2 described Height recovery algorithms include：
Step 1: it is that Height value data after the state of falling down in 10s carries out mean filter to human body；
Step 2: the height value for taking first data point is initial value, and a height is taken in the data point subsequently every 1s Angle value；
Step 3: judge whether the difference of initial value subsequent data point height value and initial value is more than discrepancy in elevation threshold value, if being more than Discrepancy in elevation threshold value, then tentatively confirm that the point has height and recovered, into next step；
Step 4: judging point height recovery time, if being more than 3s, confirm that height be present recovers, otherwise, entrance is next Step；
Step 5: judging follow-up remainder strong point length, if being more than 3s, height is not present and recovers, then further Go out human body to fall down state；If being less than or equal to 3s, a data point height value, three-step 5 of repeat step are removed.
Confirm that the 4th falls down condition, meet the 3rd fall down condition on the basis of, obtain human body by counting step algorithm to fall Add up step number after state in 10s, as shown in figure 3, the meter step algorithm includes：
1) calculate human body be acceleration after the state of falling down in 10s and；
2) the potential peak value of acceleration sum is searched by acceleration sliding window；
3) a potential peak value is selected, judges the state of the potential peak value, if the potential peak value >=1.2g, and ＜ 2g, meter For walking states；If the potential peak value is more than 2g, the state of running is calculated as；
4) calculate the different conditions potential peak value and previous time to peak is poor, if the walking states lower time difference belongs to time threshold Value [0.3s, 0.8s] or running state lower time difference belong to time threshold [0.2s, 0.5s], then carry out in next step；Otherwise, select Select another potential peak value, repeat 3) -4)；
5) calculate the potential pre-and post-peaking neighborhood acceleration and judge whether the potential peak value is maximum in neighborhood Value, if maximum in neighborhood, then counts a step；If it is not, another potential peak value of selection, 3) -5 are repeated)；
6) calculate and add up step number in 10s, if accumulative step number is less than step number threshold value, confirm as falling over of human body, if more than etc. In step number threshold value, then do not fall down.
Embodiment 2
The device of falling over of human body is detected as shown in figure 4, a kind of, including Wearable carrier and is arranged at the carrier Detection means, the detection means include controller, and controller is connected to locating module, remote alarming device, collection terminal； Collection terminal includes 3-axis acceleration sensor, height sensor, and 3-axis acceleration sensor, height sensor are preferably MEMS tri- Axle acceleration sensor, MEMS baroceptors.
The application method of device fallen down that detects is：
Detection means is arranged on to the carrier for being worn on human body, carrier can be bracelet, watchband, pendant；
Three axles gathered respectively during human motion using MEMS 3-axis acceleration sensors, MEMS baroceptors are added The height value of velocity amplitude, carrier, and human body attitude angle and height reduction value is calculated；
Controller according to it is above-mentioned it is a kind of detect falling over of human body method human body attitude angle and height reduction value are analyzed, Calculate, exceed normal range (NR) in follow-up 1s by judging whether human body attitude angle exceedes normal range (NR), calculates human body attitude angle Probability, confirm that human body recovers with the presence or absence of height, calculates the subsequently accumulative step number of human body to confirm whether human body is fallen down；If judge Human body then obtains the positional information in locating module to fall down, and by remote alarming device by positional information and warning message It is sent to remote subscriber.
The controller is also associated with power supply, buzzer, hand push button.
Described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Based on the present invention In embodiment, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made Example, belongs to the scope of the present invention.

Claims (7)

  1. A kind of 1. method for detecting falling over of human body, it is characterised in that comprise the following steps：
    Establish coordinate, using human body fore-and-aft direction as X-axis, human body left and right directions be Y-axis, vertical direction be that Z axis establishes three dimensions Right-handed Cartesian coordinate；
    Data acquisition, 3-axis acceleration value ax, ay, az and human body when gathering a certain moment human motion gather the height at position Angle value；
    Calculate attitude angle, to 3-axis acceleration value ax, ay, az carry out Kalman filtering, by filtered 3-axis acceleration value ax, Anglec of rotation pitch, human body anglec of rotation roll around Y-axis of the human body around X-axis, the anglec of rotation of human body about the z axis when ay, az are converted into this Yaw,
    <mrow> <mi>p</mi> <mi>i</mi> <mi>t</mi> <mi>c</mi> <mi>h</mi> <mo>=</mo> <mi>arctan</mi> <mrow> <mo>(</mo> <mfrac> <mrow> <mi>a</mi> <mi>x</mi> </mrow> <msqrt> <mrow> <msup> <mi>ay</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>az</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> <mo>)</mo> </mrow> </mrow>
    <mrow> <mi>r</mi> <mi>o</mi> <mi>l</mi> <mi>l</mi> <mo>=</mo> <mi>arctan</mi> <mrow> <mo>(</mo> <mfrac> <mrow> <mi>a</mi> <mi>y</mi> </mrow> <msqrt> <mrow> <msup> <mi>ax</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>az</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> <mo>)</mo> </mrow> </mrow>
    <mrow> <mi>y</mi> <mi>a</mi> <mi>w</mi> <mo>=</mo> <mi>arctan</mi> <mrow> <mo>(</mo> <mfrac> <msqrt> <mrow> <msup> <mi>ay</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>ax</mi> <mn>2</mn> </msup> </mrow> </msqrt> <mrow> <mi>a</mi> <mi>z</mi> </mrow> </mfrac> <mo>)</mo> </mrow> </mrow>
    Confirm that first falls down condition, judge whether pitch or roll exceedes the normal range (NR) of daily life human motion respectively, if Exceed, then tentatively draw human body to fall down state；
    Confirm second to fall down condition, meet first fall down condition on the basis of, extraction human body is falls down after state pitch in 1s With roll data, show that pitch or roll exceedes the probability of human motion normal range (NR), if pitch or roll exceedes normal model Whether the probability enclosed is more than 2/3, judge the height value at human body collection position and reduce, if height value, which reduces, exceedes height threshold, Human body is from which further followed that to fall down state；
    Confirm that the 3rd falls down condition, meet second fall down condition on the basis of, collection human body is falls down after state human body in 10s Position height value is gathered, and judges that human body recovers with the presence or absence of height by height recovery algorithms, if recovering in the absence of height, Human body is further drawn to fall down state；
    Confirm that the 4th falls down condition, meet the 3rd fall down condition on the basis of, obtain human body by counting step algorithm to fall down shape Add up step number after state in 10s, if accumulative step number is less than step number threshold value, further draws human body to fall down state, confirm people Body is fallen down.
  2. A kind of 2. method for detecting falling over of human body as claimed in claim 1, it is characterised in that the height recovery algorithms bag Include：
    Step 1: it is that Height value data after the state of falling down in 10s carries out mean filter to human body；
    Step 2: the height value for taking first data point is initial value, and a height value is taken in the data point subsequently every 1s；
    Step 3: judge whether the difference of initial value subsequent data point height value and initial value is more than discrepancy in elevation threshold value, if being more than the discrepancy in elevation Threshold value, then tentatively confirm that the point has height and recovered, into next step；
    Step 4: judging point height recovery time, if being more than 3s, confirm that height be present recovers, otherwise, into next step；
    Step 5: judging follow-up remainder strong point length, if being more than 3s, height is not present and recovers；If being less than or equal to 3s, Remove a data point height value, three-step 5 of repeat step.
  3. A kind of 3. method of detection falling over of human body as described in claim 1-2 is any, it is characterised in that the meter step algorithm bag Include：
    1) calculate human body be acceleration after the state of falling down in 10s and；
    2) the potential peak value of acceleration sum is searched by acceleration sliding window；
    3) a potential peak value is selected, judges the state of the potential peak value, if the potential peak value >=1.2g, and ＜ 2g, it is calculated as going Walk state；If the potential peak value is more than 2g, the state of running is calculated as；
    4) calculate the different conditions potential peak value and previous time to peak is poor, if the walking states lower time difference belongs to time threshold [0.3s, 0.8s] or running state lower time difference belong to time threshold [0.2s, 0.5s], then carry out in next step；Otherwise, select Another potential peak value, repeat 3) -4)；
    5) calculate the potential pre-and post-peaking neighborhood acceleration and, judge whether the potential peak value is maximum in neighborhood, if It is maximum in neighborhood, then counts a step；If it is not, another potential peak value of selection, 3) -5 are repeated)；
    6) calculate and add up step number in 10s, if accumulative step number is less than step number threshold value, confirm as falling down, if being more than or equal to step number threshold Value, then do not fall down.
  4. 4. a kind of device for detecting falling over of human body, including Wearable carrier and the detection means for being arranged at the carrier, its It is characterised by, the detection means includes controller, and controller is connected to locating module, remote alarming device, collection terminal；
    The collection terminal includes 3-axis acceleration sensor, height sensor.
  5. A kind of 5. device for detecting falling over of human body as claimed in claim 4, it is characterised in that the 3-axis acceleration sensor Using MEMS 3-axis acceleration sensors, the height sensor uses MEMS baroceptors.
  6. A kind of 6. device for detecting falling over of human body as claimed in claim 4, it is characterised in that described device also include power supply, Buzzer, hand push button.
  7. 7. a kind of device for detecting falling over of human body as claimed in claim 4, it is characterised in that the device that the detection is fallen down Application method is：
    Detection means is arranged on to the carrier for being worn on human body；
    Locating module, for positioning current location information；
    Collection terminal, for gather 3-axis acceleration value during human motion, carrier height value, and human body appearance is calculated State angle and height reduction value；
    Controller is used to judge whether human body is to fall according to a kind of any methods for detecting falling over of human body of claim 1-3 , if being judged as falling down, the positional information in locating module is obtained, and by remote alarming device by positional information and alarm signal Breath is sent to remote subscriber.
CN201710888350.XA 2017-09-27 2017-09-27 A kind of method and device for detecting falling over of human body Withdrawn CN107693022A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710888350.XA CN107693022A (en) 2017-09-27 2017-09-27 A kind of method and device for detecting falling over of human body

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710888350.XA CN107693022A (en) 2017-09-27 2017-09-27 A kind of method and device for detecting falling over of human body

Publications (1)

Publication Number Publication Date
CN107693022A true CN107693022A (en) 2018-02-16

Family

ID=61176170

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710888350.XA Withdrawn CN107693022A (en) 2017-09-27 2017-09-27 A kind of method and device for detecting falling over of human body

Country Status (1)

Country Link
CN (1) CN107693022A (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446733A (en) * 2018-03-19 2018-08-24 上海玺翎智能科技有限公司 A kind of human body behavior monitoring and intelligent identification Method based on multi-sensor data
CN110781808A (en) * 2019-10-23 2020-02-11 泰康保险集团股份有限公司 Fall detection method, device, equipment and storage medium
CN111524320A (en) * 2020-04-20 2020-08-11 金科龙软件科技(深圳)有限公司 Tumble detection device and method and storage medium
CN111627185A (en) * 2019-02-27 2020-09-04 富士通株式会社 Fall alarm method and device and fall detection system
CN111743545A (en) * 2020-07-07 2020-10-09 天津城建大学 Old people falling detection method based on deep learning, detection bracelet and storage medium
CN111914619A (en) * 2020-06-12 2020-11-10 华南理工大学 Wrestling detection method based on human posture and orientation estimation
CN112162595A (en) * 2020-09-23 2021-01-01 深圳市爱都科技有限公司 Vertical arm rotation identification method and wearable terminal
CN112261221A (en) * 2020-09-21 2021-01-22 电子科技大学 Human body falling detection method based on intelligent terminal
CN112669568A (en) * 2020-12-18 2021-04-16 浙江工商大学 Multi-mode human body falling detection method
CN113223281A (en) * 2021-04-28 2021-08-06 北京阿帕科蓝科技有限公司 Vehicle tumble detection method and system and vehicle
CN113269144A (en) * 2021-06-21 2021-08-17 临沂边锋自动化设备有限公司 Traffic video monitoring system
CN115024717A (en) * 2022-08-09 2022-09-09 广东百年医疗健康科技发展有限公司 Fall detection method, device, equipment and storage medium

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446733A (en) * 2018-03-19 2018-08-24 上海玺翎智能科技有限公司 A kind of human body behavior monitoring and intelligent identification Method based on multi-sensor data
CN111627185A (en) * 2019-02-27 2020-09-04 富士通株式会社 Fall alarm method and device and fall detection system
CN110781808A (en) * 2019-10-23 2020-02-11 泰康保险集团股份有限公司 Fall detection method, device, equipment and storage medium
CN111524320A (en) * 2020-04-20 2020-08-11 金科龙软件科技(深圳)有限公司 Tumble detection device and method and storage medium
CN111914619A (en) * 2020-06-12 2020-11-10 华南理工大学 Wrestling detection method based on human posture and orientation estimation
CN111743545B (en) * 2020-07-07 2023-11-28 天津城建大学 Deep learning-based old man fall detection method, detection bracelet and storage medium
CN111743545A (en) * 2020-07-07 2020-10-09 天津城建大学 Old people falling detection method based on deep learning, detection bracelet and storage medium
CN112261221A (en) * 2020-09-21 2021-01-22 电子科技大学 Human body falling detection method based on intelligent terminal
CN112162595A (en) * 2020-09-23 2021-01-01 深圳市爱都科技有限公司 Vertical arm rotation identification method and wearable terminal
CN112669568A (en) * 2020-12-18 2021-04-16 浙江工商大学 Multi-mode human body falling detection method
CN113223281A (en) * 2021-04-28 2021-08-06 北京阿帕科蓝科技有限公司 Vehicle tumble detection method and system and vehicle
CN113269144A (en) * 2021-06-21 2021-08-17 临沂边锋自动化设备有限公司 Traffic video monitoring system
CN115024717A (en) * 2022-08-09 2022-09-09 广东百年医疗健康科技发展有限公司 Fall detection method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107693022A (en) A kind of method and device for detecting falling over of human body
CN205041401U (en) Equipment is worn detection device and is had and wears guardianship device that detects function
CN101702258B (en) Information processing method of automatic detection alarming system for falling over of human body
CN201387660Y (en) Automatic detecting and alarming system for human body falling-over
CN103961109B (en) Based on the human body attitude checkout gear of acceleration signal and angular velocity signal
CN101650869B (en) Human body tumbling automatic detecting and alarming device and information processing method thereof
CN105342623A (en) Intelligent fall monitoring device and processing method thereof
Pannurat et al. A hybrid temporal reasoning framework for fall monitoring
Hsieh et al. A wrist-worn fall detection system using accelerometers and gyroscopes
CN104297519B (en) Human motion gesture recognition method and mobile terminal
CN105561567A (en) Step counting and motion state evaluation device
CN103927851B (en) A kind of individualized multi thresholds fall detection method and system
CN104224182B (en) Method and device for monitoring human tumbling
CN203931101U (en) A kind of wearable human paralysis device of falling detection alarm
CN105708470A (en) Falling detection system and method based on combination of Doppler detector and sensor
CN104571837B (en) A kind of method and system for realizing man-machine interaction
CN103637782B (en) A kind of health monitoring system based on intelligent terminal and method
CN111693024A (en) Wearable human body sensing monitoring equipment based on nine-axis inertia measurement unit
CN205103993U (en) Intelligence human body guardianship device of tumbleing
Hou et al. Triaxial accelerometer-based real time fall event detection
Nukala et al. A real-time robust fall detection system using a wireless gait analysis sensor and an artificial neural network
Song et al. A phone for human activity recognition using triaxial acceleration sensor
Zhen et al. Wearable preimpact fall detector using SVM
Xie et al. ART: adaptive and real-time fall detection using COTS smart watch
CN116491935B (en) Exercise health monitoring method, system and medium of intelligent wearable equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20180216

WW01 Invention patent application withdrawn after publication