CN105551191A - Falling detection method - Google Patents
Falling detection method Download PDFInfo
- Publication number
- CN105551191A CN105551191A CN201610058318.4A CN201610058318A CN105551191A CN 105551191 A CN105551191 A CN 105551191A CN 201610058318 A CN201610058318 A CN 201610058318A CN 105551191 A CN105551191 A CN 105551191A
- Authority
- CN
- China
- Prior art keywords
- threshold
- svm
- value
- exceedes
- falling
- 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.)
- Granted
Links
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
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- 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
- G08B21/0438—Sensor means for detecting
- G08B21/0446—Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention discloses a falling detection method. The method comprises the following steps: the step S1, detecting human activity state information in real time through adoption of a triaxial accelerometer, and obtaining triaxial acceleration data; the step S2, obtaining an acceleration signal calculation amplitude vector value SVM based on the triaxial accelerometer; and the step S3, determining the current activity in a certain state through comparison of the SVM value with a preset threshold value, and detecting whether the falling phenomenon occurs or not according to the variation of states. Through adoption of the technical scheme of the invention, the human falling detection may be accurately realized.
Description
Technical field
The present invention relates to field of sensing technologies, particularly relate to a kind of fall detection method.
Background technology
Falling down the part as physical activity, is the large factor affecting health, especially for patient and the elderly, fall down detect most important.Research shows, in the elderly of China's over-65s, have quite a few people once to fall down, and the incidence of falling down raises with advancing age, and thus succouring the elderly fallen down in time will reduce disability rate and mortality ratio greatly; What also cannot realize human body at present falls down detection.
Summary of the invention
The technical problem to be solved in the present invention is, provides a kind of fall detection method of activity personal security exception.
For solving the problem, the present invention adopts following technical scheme:
A kind of fall detection method, comprises the steps:
Step S1, by the real-time human body moving state information of 3-axis acceleration sensor, obtain 3-axis acceleration data;
Step S2, to obtain acceleration information based on 3-axis acceleration sensor and calculate amplitude vector value SVM;
Step S3, to compare with the threshold values pre-set according to described SVM value, judge that current active is in above-mentioned some states, detect whether there is the phenomenon of falling according to the change of state.
As preferably, according to each component value obtaining X, Y, Z tri-directions from 3-axis acceleration sensor; Then according to the employing exploitation difference of front and back twice; Again calculate the square value of each three component differences, i.e. SVM value, computing formula model is:
SVM＝(X
n-X
n-1)
2+(Y
n-Y
n-1)
2+(Z
n-Z
n-1)
2
Wherein: X
nrepresent the X component value of the 3-axis acceleration of current acquisition, X
n-1represent the X component value of the last 3-axis acceleration obtained; Y
nrepresent the Y-component value of the 3-axis acceleration of current acquisition, Y
n-1represent the Y-component value of the last 3-axis acceleration obtained; Z
nrepresent the Z component value of the 3-axis acceleration of current acquisition, Z
n-1represent the Z component value of the last 3-axis acceleration obtained.
As preferably, in step S3, deterministic process is as follows:
Judge whether current SVM value exceedes first threshold, if so, then SVM value exceedes the number of times increase of described first threshold; If whether the number of times that SVM value exceedes described first threshold exceedes preset times, then current state is updated to falling state of falling;
Judge whether current SVM value exceedes described first threshold, if, then judge the number of sample points whether number of times that SVM value exceedes described first threshold is less than SVM value and exceedes described first threshold, if, then SVM value exceedes the number of times increase of described first threshold, judge whether the number of times that SVM value exceedes first threshold exceedes falling state threshold number of falling, and if so, then current state is updated to crash situation of falling;
Judge whether current SVM value exceedes Second Threshold, if, then judge the number of sample points whether number of times that SVM value exceedes Second Threshold is less than SVM value and exceedes described Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes shock threshold number of falling, if, judge whether current maximum sampling SVM value exceedes current SVM value, if so, then current state is updated to stationary state of falling;
Judge that whether current SVM value is lower than Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes the static threshold number of times that falls down to the ground, and if so, then current state is updated to preparation alarm condition.
Wherein, described first threshold is falling state SVM threshold values of falling, and Second Threshold is crash situation SVM threshold value of falling.
Based on the physical activity acceleration signal that 3-axis acceleration sensor gathers, propose a kind of signal amplitude based on fixed threshold vector moving average method.The method is according to acceleration signal feature during physical activity, the threshold value preset is utilized to adjudicate acceleration signal amplitude vector SVM value, use multiple sampling and state variation tendency to distinguish the strenuous exercises such as running fast, what accurately achieve human body falls down detection simultaneously.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of fall detection method of the present invention;
Fig. 2 is the test result adopting detection method.
Embodiment
Below in conjunction with embodiment and accompanying drawing, technical scheme of the present invention is further elaborated.
As shown in Figure 1, the embodiment of the present invention provides a kind of fall detection method, comprises the following steps:
Step S1, by the real-time human body moving state information of 3-axis acceleration sensor, obtain 3-axis acceleration data.
Step S2, to obtain acceleration information based on 3-axis acceleration sensor and calculate amplitude vector value SVM.
The component value in X, Y, Z tri-directions is obtained from 3-axis acceleration sensor, then according to the employing exploitation difference of front and back twice according to each; Again calculate the square value of each three component differences, i.e. SVM value, computing formula model is:
SVM＝(X
n-X
n-1)
2+(Y
n-Y
n-1)
2+(Z
n-Z
n-1)
2
Wherein: X
nrepresent the X component value of the 3-axis acceleration of current acquisition, X
n-1represent the X component value of the last 3-axis acceleration obtained; Y
nrepresent the Y-component value of the 3-axis acceleration of current acquisition, Y
n-1represent the Y-component value of the last 3-axis acceleration obtained; Z
nrepresent the Z component value of the 3-axis acceleration of current acquisition, Z
n-1represent the Z component value of the last 3-axis acceleration obtained.
Step S3, to compare with the threshold values pre-set according to described SVM value, judge that current active is in above-mentioned some states, detect whether there is the phenomenon of falling according to the change of state.
Deterministic process is as follows:
Judge whether current SVM value exceedes first threshold, if so, then SVM value exceedes the number of times increase of described first threshold; If whether the number of times that SVM value exceedes described first threshold exceedes preset times, then current state is updated to falling state of falling, wherein, preset times is three times;
Judge whether current SVM value exceedes described first threshold, if, then judge the number of sample points whether number of times that SVM value exceedes described first threshold is less than SVM value and exceedes described first threshold, if, then SVM value exceedes the number of times increase of described first threshold, judge whether the number of times that SVM value exceedes first threshold exceedes falling state threshold number of falling, and if so, then current state is updated to crash situation of falling;
Judge whether current SVM value exceedes Second Threshold, if, then judge the number of sample points whether number of times that SVM value exceedes Second Threshold is less than SVM value and exceedes described Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes shock threshold number of falling, if, judge whether current maximum sampling SVM value exceedes current SVM value, if so, then current state is updated to stationary state of falling; Wherein, maximal value in current maximum sampling SVM value and the SVM value that calculates of each sampled value.
Judge that whether current SVM value is lower than Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes the static threshold number of times that falls down to the ground, and if so, then current state is updated to preparation alarm condition.
Wherein, described first threshold is falling state SVM threshold values of falling, and Second Threshold is crash situation SVM threshold value of falling.
In sum, the 3-axis acceleration data that method of the present invention gathers based on 3-axis acceleration sensor, calculate the variation characteristic of data by mathematical analysis, thus judge falling or other motion states of the elderly.
Adopt detection method of the present invention, the loins that a danger button wearable device is worn on old man can be made based on 3-axis acceleration sensor, test result as shown in Figure 2, can find out, all running activities are not all divided into falls down, namely, when distinguishing running and running especially fast and fall down, 100% accuracy is achieved.Falling down in detection, achieving the accuracy of 94.4%.
The present invention is based on 3-axis acceleration sensor write and optimize, main employing CC2541 single-chip microcomputer and ADXL362 3-axis acceleration sensor module and relevant button and switch, the loins that the wearable device making a miniature danger button is worn on old man detects in real time and reports to the police.
Last it is noted that above embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (3)
1. a fall detection method, is characterized in that, comprises the steps:
Step S1, by the real-time human body moving state information of 3-axis acceleration sensor, obtain 3-axis acceleration data;
Step S2, to obtain acceleration information based on 3-axis acceleration sensor and calculate amplitude vector value SVM;
Step S3, to compare with the threshold values pre-set according to described SVM value, judge according to the change of state, current active is in above-mentioned some states, judges whether current human falls.
2. fall detection method as claimed in claim 1, is characterized in that, according to each component value obtaining X, Y, Z tri-directions from 3-axis acceleration sensor, then according to the employing exploitation difference of front and back twice; Again calculate the square value of each three component differences, i.e. SVM value, computing formula model is:
SVM＝(X
n-X
n-1)
2+(Y
n-Y
n-1)
2+(Z
n-Z
n-1)
2
Wherein: X
nrepresent the X component value of the 3-axis acceleration of current acquisition, X
n-1represent the X component value of the last 3-axis acceleration obtained; Y
nrepresent the Y-component value of the 3-axis acceleration of current acquisition, Y
n-1represent the Y-component value of the last 3-axis acceleration obtained; Z
nrepresent the Z component value of the 3-axis acceleration of current acquisition, Z
n-1represent the Z component value of the last 3-axis acceleration obtained.
3. fall detection method as claimed in claim 1, it is characterized in that, in step S3, deterministic process is as follows:
Judge whether current SVM value exceedes first threshold, if so, then SVM value exceedes the number of times increase of described first threshold; If whether the number of times that SVM value exceedes described first threshold exceedes preset times, then current state is updated to falling state of falling;
Judge whether current SVM value exceedes described first threshold, if, then judge the number of sample points whether number of times that SVM value exceedes described first threshold is less than SVM value and exceedes described first threshold, if, then SVM value exceedes the number of times increase of described first threshold, judge whether the number of times that SVM value exceedes first threshold exceedes falling state threshold number of falling, and if so, then current state is updated to crash situation of falling;
Judge whether current SVM value exceedes Second Threshold, if, then judge the number of sample points whether number of times that SVM value exceedes Second Threshold is less than SVM value and exceedes described Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes shock threshold number of falling, if, judge whether current maximum sampling SVM value exceedes current SVM value, if so, then current state is updated to stationary state of falling;
Judge that whether current SVM value is lower than Second Threshold, if so, then the number of times that SVM value exceedes Second Threshold increases, and judges whether the number of times that SVM value exceedes Second Threshold exceedes the static threshold number of times that falls down to the ground, and if so, then current state is updated to preparation alarm condition.
Wherein, described first threshold is falling state SVM threshold values of falling, and Second Threshold is crash situation SVM threshold value of falling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610058318.4A CN105551191B (en) | 2016-01-28 | 2016-01-28 | A kind of fall detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610058318.4A CN105551191B (en) | 2016-01-28 | 2016-01-28 | A kind of fall detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105551191A true CN105551191A (en) | 2016-05-04 |
| CN105551191B CN105551191B (en) | 2018-05-29 |
Family
ID=55830362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610058318.4A Expired - Fee Related CN105551191B (en) | 2016-01-28 | 2016-01-28 | A kind of fall detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105551191B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108040182A (en) * | 2018-01-16 | 2018-05-15 | 维沃移动通信有限公司 | A kind of alarm method and mobile terminal |
| CN108153408A (en) * | 2016-12-05 | 2018-06-12 | 中国移动通信有限公司研究院 | A kind of method and device of Activity recognition |
| CN108451517A (en) * | 2018-02-13 | 2018-08-28 | 安徽奇智科技有限公司 | A kind of health detecting method based on wearable device |
| CN108720840A (en) * | 2018-02-13 | 2018-11-02 | 安徽奇智科技有限公司 | A kind of method and system detecting health data based on Worn type equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004026138A1 (en) * | 2002-09-19 | 2004-04-01 | Matsushita Electric Industrial Co., Ltd. | Physical movement evaluation device and physical movement evaluation system |
| CN102646319A (en) * | 2012-04-13 | 2012-08-22 | 无锡先凯智能科技有限公司 | Organism-falling detection device and method |
| CN103337132A (en) * | 2013-06-08 | 2013-10-02 | 山东师范大学 | Tumble detection method for human body based on three-axis acceleration sensor |
| CN204791433U (en) * | 2015-07-09 | 2015-11-18 | 北京安易康医疗技术服务有限公司 | Waistband formula human body orientation inspect device of tumbleing |
-
2016
- 2016-01-28 CN CN201610058318.4A patent/CN105551191B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004026138A1 (en) * | 2002-09-19 | 2004-04-01 | Matsushita Electric Industrial Co., Ltd. | Physical movement evaluation device and physical movement evaluation system |
| CN102646319A (en) * | 2012-04-13 | 2012-08-22 | 无锡先凯智能科技有限公司 | Organism-falling detection device and method |
| CN103337132A (en) * | 2013-06-08 | 2013-10-02 | 山东师范大学 | Tumble detection method for human body based on three-axis acceleration sensor |
| CN204791433U (en) * | 2015-07-09 | 2015-11-18 | 北京安易康医疗技术服务有限公司 | Waistband formula human body orientation inspect device of tumbleing |
Non-Patent Citations (2)
| Title |
|---|
| 秦瑀阳: "老年人跌倒检测报警装置的研究与设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 赵祥欣: "基于三维加速度传感器的跌倒监测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153408A (en) * | 2016-12-05 | 2018-06-12 | 中国移动通信有限公司研究院 | A kind of method and device of Activity recognition |
| CN108040182A (en) * | 2018-01-16 | 2018-05-15 | 维沃移动通信有限公司 | A kind of alarm method and mobile terminal |
| CN108451517A (en) * | 2018-02-13 | 2018-08-28 | 安徽奇智科技有限公司 | A kind of health detecting method based on wearable device |
| CN108720840A (en) * | 2018-02-13 | 2018-11-02 | 安徽奇智科技有限公司 | A kind of method and system detecting health data based on Worn type equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105551191B (en) | 2018-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10506990B2 (en) | Devices and methods for fall detection based on phase segmentation | |
| Kozina et al. | Efficient activity recognition and fall detection using accelerometers | |
| CN104135911B (en) | Activity classification in multi-axial cord movement monitoring device | |
| CN103927851B (en) | A kind of individualized multi thresholds fall detection method and system | |
| Hsieh et al. | A wrist-worn fall detection system using accelerometers and gyroscopes | |
| Krupitzer et al. | Hips do lie! a position-aware mobile fall detection system | |
| CN105051799A (en) | Method for detecting falls and a fall detector. | |
| CN105551191A (en) | Falling detection method | |
| CN103337132A (en) | Tumble detection method for human body based on three-axis acceleration sensor | |
| CN105212941B (en) | A kind of human body active state recognition methods and system | |
| US11410521B2 (en) | Fall detector incorporating physiological sensing | |
| CN104473648A (en) | Physiological parameter monitoring-combined human body tumble warning and detecting method | |
| Krupitzer et al. | Beyond position-awareness—Extending a self-adaptive fall detection system | |
| CN107146378A (en) | A kind of human body tumble decision method and device | |
| CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
| Luqian et al. | Human activity recognition using time series pattern recognition model-based on tsfresh features | |
| Zhao et al. | Fall detecting and alarming based on mobile phone | |
| Prudêncio et al. | Physical activity recognition from smartphone embedded sensors | |
| Rowlands et al. | Accelerometer wear-site detection: When one site does not suit all, all of the time | |
| CN115299937A (en) | Intelligence detection platform that tumbles | |
| CN107569234A (en) | A kind of fall detection algorithm based on Wrist belt-type equipment | |
| US11280634B2 (en) | System, method and article for counting steps using an accelerometer | |
| Kreil et al. | Muscle activity evaluation using force sensitive resistors | |
| Weng et al. | Fall detection based on tilt angle and acceleration variations | |
| Pipanmaekaporn et al. | Mining Acceleration Data for Smartphone-based Fall Detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210324 Address after: 430000 room 1401, unit 1, building 1, sunshine, California, No. 11, Guanggu street, Hongshan District, Wuhan City, Hubei Province Patentee after: Qiu Congbo Address before: Room 409, 411, 4 / F, building a11, Huazhong Software Park (Optical Valley Software Park), No.1, Guanshan 1st Road, Donghu Development Zone, Wuhan City, Hubei Province, 430000 Patentee before: DRAGONWAKE TECHNOLOGY Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180529 Termination date: 20220128 |