CN102289911A - Falling detection system based on pyroelectric infrared rays - Google Patents
Falling detection system based on pyroelectric infrared rays Download PDFInfo
- Publication number
- CN102289911A CN102289911A CN2011102025495A CN201110202549A CN102289911A CN 102289911 A CN102289911 A CN 102289911A CN 2011102025495 A CN2011102025495 A CN 2011102025495A CN 201110202549 A CN201110202549 A CN 201110202549A CN 102289911 A CN102289911 A CN 102289911A
- Authority
- CN
- China
- Prior art keywords
- hmm
- signal
- module
- model
- human body
- 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.)
- Pending
Links
Images
Landscapes
- Emergency Alarm Devices (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a detection system based on pyroelectric infrared rays. The system comprises a data acquisition module, an analog to digital conversion module, a filtering and denoising module, a data processing module and an alarm module, wherein the data acquisition module comprises two pyroelectric infrared ray sensors, and is used for acquiring signals; the analog to digital conversion module is used for converting an analog signal acquired by using pyroelectric infrared rays into a digital signal; the filtering and denoising module is used for eliminating the influences of various interferences and reducing negative influences caused by noise; and the data processing module is used for performing detection and analysis, matching falling detection in a hidden Markov model (HMM) mode to obtain a detection result and making an alarm. In the technical scheme of the invention, a user is not required to use wearing type equipment, the privacy of the user is protected, and the falling detection system can run in dark environment and has high sensitivity, so that great convenience is brought to the user.
Description
Technical field
The present invention relates to digital home technical field, be specifically related to a kind of fall detection system based on rpyroelectric infrared.
Background technology
But behavior identification is as a kind of biological identification technology of remote identification, and background is widely used.Falling is a kind of in the typical behavior (walk, sit, crouch, fall etc.), is the relatively large a kind of behavior of productive life influence to people.And fall detection is widely used in the safety monitoring system in various important places such as family, hospital, office or industrial environment as an aspect of behavior identification.The fall detection technology is very important in some application scenario.Such as, fall detection as an important component part of healthy ancillary technique, old man who lives by oneself for being in or hospital patient, it can in time notify the caretaker with the incident of promptly falling, and guarantees that the person of falling will obtain emergency aid or treatment.This is for the quality of life that improves them or alleviate their the injured degree of falling and play an important role.
Current, in passive pyroelectric infrared radio sensor network, people have carried out partition encoding to the rpyroelectric infrared guarded region, and the research of on this basis human body being carried out aspects such as target detection, target classification, goal orientation, target following has obtained certain achievement.Present fall detection method has shortcoming separately, has mandatoryly based on the fall detection method of Wearable equipment, requires the user must carry Wearable equipment, makes troubles to the user; Can relate to user's privacy based on the fall detection method of visual apparatus, can not work under dark surrounds, and equipment price be higher relatively, calculated amount is big; Based on the fall detection method of surrounding environment equipment all must working pressure or vibration transducer measure user's position, could make detection to falling.
Summary of the invention
The technical problem to be solved in the present invention provides a kind of fall detection system based on rpyroelectric infrared, can improve the sensitivity of detection, and more convenient user's use.
In order to realize goal of the invention, the technical solution used in the present invention is as follows:
The invention provides a kind of fall detection system based on rpyroelectric infrared:
Comprise data acquisition module, analog-to-digital conversion module, filtering and removal noise module, data processing module, alarm module;
Described data acquisition module comprises two pyroelectric infrared sensors, is used for acquired signal;
Analog-to-digital conversion module is used for the analog signal conversion that is collected by rpyroelectric infrared is become digital signal;
Filtering and remove the noise module is used to remove the influence of various interference, reduces the negative effect that noise brings;
Data processing module is used to carry out check and analysis, and fall detection is adopted hidden Markov model HMM pattern match, obtains testing result, and gives the alarm.
Optionally, in two pyroelectric infrared sensors, the upper part of the body of sensor 2 monitoring human targets, the lower part of the body of sensor 1 monitoring human target, the side-looking angle A of two sensors monitored area is 52.5 °, H is a sensor node vertical range overhead, and D is the horizontal range of human body target from sensor node.
Optionally, in two pyroelectric infrared sensors, the upper part of the body of sensor 2 monitoring human targets, the lower part of the body of sensor 1 monitoring human target, the side-looking angle A of two sensors monitored area is 52.5 °, H is a sensor node vertical range overhead, and D is the horizontal range of human body target from sensor node.
Optionally, when carrying out check and analysis, utilize HMM to carry out fall detection and mainly be divided into two stages: HMM training stage and HMM cognitive phase;
In the training stage, human body target walking data that sensor node is collected and the human body target data of falling are handled, obtain a plurality of walking sequences and a plurality of sequence of falling respectively, set up the HMM walking model by the Baum-welch algorithm in the HMM rudimentary algorithm for walking then, set up the HMM model of falling for falling, the fall parameter of model of HMM walking model and HMM is preserved, set up the model bank that comprises two behavior models;
At cognitive phase, to unknown behavior sequence by obtaining after the identical signal Processing, forward direction-back in the use HMM rudimentary algorithm is to algorithm or Viterbi algorithm, calculate the output probability under unknown behavior sequence each model parameter condition in model bank, the size that compares each probability, make the judgement which model unknown behavior sequence belongs to, with the recognition result output of behavior.
Technique scheme as can be seen, the present invention has following beneficial effect:
1) compare fall detection method based on Wearable equipment, require the user must carry Wearable equipment, the present invention can not make troubles to the user.
2) compare the privacy that can relate to the user based on the fall detection method of visual apparatus, can not work under dark surrounds, the present invention can not relate to user's privacy, and can work under dark surrounds.
3) equipment price is relatively cheap, and it is a lot of that the monitoring camera low price is compared in the rpyroelectric infrared collection.
4) fall detection is very accurate, and sensitivity is very high.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is a system schematic of the present invention;
Fig. 2 is a functional block diagram of the present invention;
Fig. 3 is the synoptic diagram of data acquisition module of the present invention;
Fig. 4 is the basic framework figure of fall detection model of the present invention;
Fig. 5 is that Matlab serial ports of the present invention receives and storage data program process flow diagram;
Fig. 6 is the double threshold end-point detection algorithm synoptic diagram based on short-time energy and amplitude of the present invention;
Fig. 7 is that method of the present invention is used process flow diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making all other embodiment that obtained under the creative work prerequisite.
The invention provides a kind of detection system, can improve the sensitivity of detection based on rpyroelectric infrared, and more convenient user's use.
The present invention be with hidden Markov model HMM (Hidden Markov Model, HMM) universality of model with and the characteristics of pyroelectric infrared sensor acquired signal mutually combine, a kind of rpyroelectric infrared fall detection system based on HMM has been proposed.By rpyroelectric infrared fall detection equipment, remove to gather the multidate information of removing the human body target behavior after the background information, then the data of gathering are handled, by the model of cognition of falling, make detection to falling then based on HMM.Give the alarm after falling detecting, notify family members.
Fig. 1 is a system schematic of the present invention.
As shown in Figure 1, the present invention gathers people's body heat source data with pyroelectric infrared sensor, through analog to digital conversion, after filtering and the removal noise processed, is sent to data processor processes, utilizes HMM to carry out fall detection, has the people to fall as judgement, then gives the alarm.
Fig. 2 is a functional block diagram of the present invention.As shown in Figure 2, this fall detection system comprises data acquisition module, analog-to-digital conversion module, filtering and removal noise module, data processing module, alarm module.The hierarchical relationship of each module as shown in the figure.
Fig. 3 is the synoptic diagram of data acquisition module of the present invention.As shown in Figure 3, comprise that sensor 1 and sensor 2 are two pyroelectric infrared sensors in the sensor node (node is installed on the wall).The upper part of the body of sensor 2 monitoring human targets, the lower part of the body of sensor 1 monitoring human target, the side-looking angle A of two sensors monitored area is 52.5 °, and H is a sensor node vertical range overhead, and D is the horizontal range of human body target from sensor node.
Human body target plays a decisive role from the output that the thermal source of the speed of the distance of pyroelectric infrared sensor, human body target motion, human body target distributes to pyroelectric infrared sensor.Analyze human body target below under the walking and the two kinds of situations of falling, the characteristics of two sensors voltage output value.
Human body target is when normal walking, and its upper part of the body and the lower part of the body are all in motion, and whole pace is more or less the same, and the feature of the voltage output value size of the sensor 2 of the sensor 1 of the monitoring lower part of the body and the monitoring upper part of the body has following 2 details to need to consider:
1) frequency of double-legged motion alternate is bigger with respect to above the waist, therefore, in theory the frequency ratio sensor 2 that changes of the variable quantity of the infrared energy that receives of sensor 1 greatly, the voltage output value of the voltage output value ratio sensor 2 of sensor 1 is big.
2) Shang Banshen thermal source distribution range is bigger than the thermal source distribution range of the lower part of the body, sensor 2 is big by the variable quantity of the infrared energy that the inevitable ratio sensor 1 of the variable quantity of the infrared energy of the upper part of the body of Fresnel Lenses reception receives, therefore, the voltage output value that the voltage output value of sensor 2 should ratio sensor 1 in theory is big.
Consider that based on above two aspects when human body target was normally walked, the output valve of sensor 1 and sensor 2 should be more or less the same.Most of data of gathering conclusion therewith are consistent.
Human body target is when falling, and the feature of the voltage output value size of two sensors is apparent in view.
1) take place early stage in the behavior of falling, in short time, at first run-off the straight above the waist, and because its thermal source distributes greatly, amplitude is big, speed is fast, the voltage output value of sensor 2 can reach a peak value earlier, and the amplitude of peak value can be bigger, and sensor 1 this moment voltage output value size during this period of time is identical when walking.
2) in the action of falling take place the later stage, upper half of human body drops to the monitored area of sensor 1, equally because of upper part of the body thermal source distributes greatly, amplitude is big, speed is fast, the thermal source that adds both feet distributes and speed, so the time sensor 1 output valve should reach a peak value, and amplitude is bigger, and the output valve of sensor 2 is then less relatively.
The characteristics of the output valve of sensor 1 and sensor 2 when table 1 is normally walked and fallen
Analog-to-digital conversion module and filtering and removal noise module, it is the module that present device is used for interim data, be used for the analog signal conversion that is collected by rpyroelectric infrared is become digital signal, and remove the influence of various interference, reduce the negative effect that noise brings, the clean real data of reduction as much as possible make things convenient for analyzing and processing.
Data processing module is a nucleus module of the present invention.What fall detection was adopted is the principle of hidden Markov model (HMM) pattern match, the HMM model is applied in the real world basic problem that has three needs to solve:
Probability estimation problem: given HMM model λ=(A, B, π) and an observed value sequence O=O
1, O
2..., O
TUnder the condition, how to calculate observed value sequence O=O
1, O
2..., O
TProbability P (O/ λ).
Model training problem: at a given observed value sequence O=O
1, O
2..., O
TCondition under, how to determine that a new optimal model parameter lambda=(A, B π), make P (O/ λ) maximum.
The state decode problem: given HMM model λ=(A, B, π) and an observed value sequence O=O
1, O
2..., O
TCondition under, how to try to achieve one and O
1, O
2..., O
TCorresponding optimum condition conversion sequence q
*, make and work as q=q
*The time, P (O, q/ λ) has maximal value.
The present invention uses three basic problems of forward direction-back above algorithm, Baum-welch algorithm and Viterbi algorithm solve respectively.
Fig. 4 is the basic framework figure of fall detection model of the present invention.As shown in Figure 4, utilize HMM to carry out fall detection and mainly be divided into two stages: HMM training stage and HMM cognitive phase.
In the training stage, human body target walking data that sensor node is collected and the human body target data of falling are handled, obtain a plurality of walking sequences and a plurality of sequence of falling respectively, set up the HMM walking model by the Baum-welch algorithm in the HMM rudimentary algorithm for walking then, set up the HMM model of falling for falling.The fall parameter of model of HMM walking model and HMM is preserved, thereby set up the model bank that comprises two behavior models.
At cognitive phase, to unknown behavior sequence by obtaining after the identical signal Processing, forward direction-back in the use HMM rudimentary algorithm is to algorithm or Viterbi algorithm, calculate the output probability under unknown behavior sequence each model parameter condition in model bank, the size that compares each probability, make the judgement which model unknown behavior sequence belongs to, thereby the recognition result of behavior is exported.
After recognition result comes out, the result who discerns is passed to the result treatment module.If the behavior of human body target is to fall, then monitoring person may be reported to the police or notify to the result treatment module, if the result is walking, then do not report to the police, and increases the walking record once.
This module uses IAR Embedded Workbench software programming sensor node data to gather and router wxldemo.c, and with the TS-Z-CC2430 module of this program burn writing to the sensor node, makes its automatic operation.This program is used the constantly mode of inquiry, every 20ms (50Hz) 3 sensor assembly passages on the sensor node are inquired about, and will on serial ports and antenna, be sent with wired and wireless dual mode respectively from the human body infrared data that passage collects.
Use Matlab software programming Matlab Data Receiving and stored programme main_start.m on the PC, this program is used timer, reads a secondary data every 20ms (50Hz) from the serial ports impact damper of PC.The storage format of data is the .txt file, the data that the three column data representative of .txt file the inside collects from three sensor assembly passages separately.Matlab Data Receiving and stored programme process flow diagram are as shown in Figure 5.Fig. 5 is that Matlab serial ports of the present invention receives and storage data program process flow diagram.
Behavior sequence extracts and program design.If only judge whether that target is movable in the monitored area of sensor node, only need to use the end-point detection journey in this section can judge the result, its basic thought is: when human body target is movable in the monitored area, the two paths of data that two sensor assemblies collect on the sensor node inevitable in a period of time (1-4 second) amplitude very big fluctuation be arranged, and repeatedly surpass 2.0V, can be provided with thus one in a period of time signal amplitude surpass the number of times threshold value of 2.0V and the threshold value of a behavior sequence length, the sequence that satisfies two threshold values simultaneously is judged as the behavior sequence of goal activities, and the sequence that can not satisfy two threshold values simultaneously then is judged as the non-behavior sequence that does not have goal activities.
Fall detection of the present invention is not whether to have detected target travel simply, and need the further detection generation of whether falling, this need extract the one section continuous signal section of the human body target starting point that subordinate act takes place in the monitored area of sensor node to end point, be the behavior sequence, because this section continuous signal section has implied the feature of human body target activity.In fact the infrared signal that collects is by the useful signal section (behavior sequence) that human body target motion is arranged and do not have the garbage signal section (non-behavior sequence) of human body target travel to form, how the useful signal section of human body target motion is collected from all that to extract the signal then be the problem of a needs solution.
The fall detection that the present invention proposes only need be used the useful signal section that comprises the human body target active characteristics, for the garbage signal Duan Zeying removal as far as possible of no human body goal activities.Therefore, require from the signal of gathering, to extract exactly the behavior sequence of human body target motion as far as possible, improve the accuracy and the reliability of fall detection.
Fig. 6 is the double threshold end-point detection algorithm synoptic diagram based on short-time energy and amplitude of the present invention.
The present invention adopts based on the double threshold end-point detection algorithm and the human body target behavior sequence of short-time energy and amplitude peak the extraction of human body target behavior sequence and works in coordination with algorithm, purpose is from the signal that collects, find out all behavior sequences starting point and end point, thereby only store and handle effective infrared signal.
Can find out the useful signal section of first human body target motion in the road signal of being given based on the double threshold end-point detection algorithm of short-time energy and amplitude.Its concrete algorithm flow may further comprise the steps as shown in Figure 6:
(1) initialization with signal normalization, is provided with short-time energy threshold value and a voltage threshold;
(2) signal of gathering is carried out the branch frame, per 25 sampled points are a frame, and it is 5 that frame moves, and calculates the short-time energy of each branch frame signal;
(3) in chronological order, find out a possible useful signal section of forming by the continuous branch frame signal that surpasses threshold value of some, can not find then and quit a program, can find and then carry out the 4th and go on foot;
(4) judge that whether maximum voltage value in (3) the possible useful signal section that finds of step is greater than voltage threshold, if greater than this possible useful new section would be decided to be first human body target behavior signal segment, if were not more than program return (3) step, according to time sequencing, continue to seek next possible useful signal section.
Fig. 7 is the use process flow diagram of the inventive method.
What as shown in Figure 7, this figure described is the use of fall detection.At first, heat is installed releases infrared data ' s acquisition equipment, connect data processor and alarm then.Then begin the HMM training, carry out the training of falling more than 20 times, allow database set up model.Begin fall detection then.Fall if detect the someone, give the alarm.
In sum, the inventive method has the following advantages:
1) compare fall detection method based on Wearable equipment, require the user must carry Wearable equipment, the present invention can not make troubles to the user.
2) compare the privacy that can relate to the user based on the fall detection method of visual apparatus, can not work under dark surrounds, the present invention can not relate to user's privacy, and can work under dark surrounds.
3) equipment price is relatively cheap, and it is a lot of that the monitoring camera low price is compared in the rpyroelectric infrared collection.
4) fall detection is very accurate, and sensitivity is very high.
More than a kind of detection system and method based on rpyroelectric infrared that the embodiment of the invention provided is described in detail, used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (4)
1. fall detection system based on rpyroelectric infrared is characterized in that:
This system be with the universality of hidden Markov model HMM with and the characteristics of pyroelectric infrared sensor acquired signal mutually combine, a kind of rpyroelectric infrared fall detection system based on HMM has been proposed; By rpyroelectric infrared fall detection equipment, remove to gather the multidate information of removing the human body target behavior after the background information, then the data of gathering are handled, by the model of cognition of falling, make detection to falling then based on HMM; Give the alarm after falling detecting;
This system comprises data acquisition module, analog-to-digital conversion module, filtering and removal noise module, data processing module, alarm module;
Described data acquisition module comprises two pyroelectric infrared sensors, is used for acquired signal;
Analog-to-digital conversion module is used for the analog signal conversion that is collected by rpyroelectric infrared is become digital signal;
Filtering and remove the noise module is used to remove the influence of various interference, reduces the negative effect that noise brings;
Data processing module is used to carry out check and analysis, and fall detection is adopted hidden Markov model HMM pattern match, obtains testing result, and gives the alarm.
2. system according to claim 1 is characterized in that:
In two pyroelectric infrared sensors, the upper part of the body of sensor 2 monitoring human targets, the lower part of the body of sensor 1 monitoring human target, the side-looking angle A of two sensors monitored area is 52.5 °, H is a sensor node vertical range overhead, and D is the horizontal range of human body target from sensor node.
3. system according to claim 1 is characterized in that: utilize HMM to carry out fall detection and mainly be divided into two stages: HMM training stage and HMM cognitive phase;
In the training stage, human body target walking data that sensor node is collected and the human body target data of falling are handled, obtain a plurality of walking sequences and a plurality of sequence of falling respectively, set up the HMM walking model by the Baum-welch algorithm in the HMM rudimentary algorithm for walking then, set up the HMM model of falling for falling, the fall parameter of model of HMM walking model and HMM is preserved, set up the model bank that comprises two behavior models;
At cognitive phase, to unknown behavior sequence by obtaining after the identical signal Processing, forward direction-back in the use HMM rudimentary algorithm is to algorithm or Viterbi algorithm, calculate the output probability under unknown behavior sequence each model parameter condition in model bank, the size that compares each probability, make the judgement which model unknown behavior sequence belongs to, with the recognition result output of behavior.
4. according to claim 1 or 3 described systems, it is characterized in that: the extraction of human body target behavior sequence is adopted based on the double threshold end-point detection algorithm of short-time energy and amplitude peak and the collaborative algorithm of human body target behavior sequence, purpose is from the signal that collects, find out all behavior sequences starting point and end point, thereby only store and handle effective infrared signal;
Can find out the useful signal section that first human body target in the road signal of being given moves based on the double threshold end-point detection algorithm of short-time energy and amplitude, its concrete algorithm may further comprise the steps:
S1, initialization with signal normalization, are provided with short-time energy threshold value and a voltage threshold;
S2, the signal of gathering is carried out the branch frame, per 25 sampled points are a frame, and it is 5 that frame moves, and calculates the short-time energy of each branch frame signal;
S3, in chronological order finds out a possible useful signal section of being made up of the continuous branch frame signal that surpasses threshold value of some, can not find then to quit a program, and can find then to carry out the 4th and go on foot;
S4, judge that whether maximum voltage value in the possible useful signal section that S3 step finds is greater than voltage threshold, if greater than this possible useful new section would be decided to be first human body target behavior signal segment, if be not more than then program is returned S3 step, according to time sequencing, continue to seek next possible useful signal section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102025495A CN102289911A (en) | 2011-07-19 | 2011-07-19 | Falling detection system based on pyroelectric infrared rays |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102025495A CN102289911A (en) | 2011-07-19 | 2011-07-19 | Falling detection system based on pyroelectric infrared rays |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102289911A true CN102289911A (en) | 2011-12-21 |
Family
ID=45336290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102025495A Pending CN102289911A (en) | 2011-07-19 | 2011-07-19 | Falling detection system based on pyroelectric infrared rays |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102289911A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567715A (en) * | 2011-12-14 | 2012-07-11 | 天津大学 | Human body action hierarchical identification method based on pyroelectric infrared detection |
| CN103606248A (en) * | 2013-09-30 | 2014-02-26 | 广州市香港科大霍英东研究院 | Automatic detection method and system for human body falling-over |
| EP2763116A1 (en) | 2013-02-01 | 2014-08-06 | FamilyEye BVBA | Fall detection system and method for detecting a fall of a monitored person |
| CN105007463A (en) * | 2015-07-16 | 2015-10-28 | 盛玉伟 | Total management system and management method of apartment for the aged |
| CN105559789A (en) * | 2015-12-31 | 2016-05-11 | 成都麦杰康科技有限公司 | Fall detection system and method |
| CN105765639A (en) * | 2013-09-19 | 2016-07-13 | 乌纳利沃尔有限公司 | Assist device and system |
| CN107886678A (en) * | 2017-11-10 | 2018-04-06 | 泰康保险集团股份有限公司 | Indoor monitoring method, device, medium and electronic equipment |
| CN109805936A (en) * | 2019-01-18 | 2019-05-28 | 深圳大学 | Falling over of human body detection system based on ground vibration signal |
| US10687193B2 (en) | 2013-09-19 | 2020-06-16 | Unaliwear, Inc. | Assist device and system |
| CN112244818A (en) * | 2020-09-30 | 2021-01-22 | 仲恺农业工程学院 | Falling detection device and method based on human body infrared perception |
| JP2021068363A (en) * | 2019-10-28 | 2021-04-30 | 株式会社ノーリツ | Abnormality detection system |
| US11250683B2 (en) | 2016-04-22 | 2022-02-15 | Maricare Oy | Sensor and system for monitoring |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1874497A (en) * | 2006-05-30 | 2006-12-06 | 浙江工业大学 | Household safe and security equipment for solitary old person based on omnibearing computer vision |
| US20080186189A1 (en) * | 2007-02-06 | 2008-08-07 | General Electric Company | System and method for predicting fall risk for a resident |
-
2011
- 2011-07-19 CN CN2011102025495A patent/CN102289911A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1874497A (en) * | 2006-05-30 | 2006-12-06 | 浙江工业大学 | Household safe and security equipment for solitary old person based on omnibearing computer vision |
| US20080186189A1 (en) * | 2007-02-06 | 2008-08-07 | General Electric Company | System and method for predicting fall risk for a resident |
Non-Patent Citations (1)
| Title |
|---|
| 熊先锋: "面向行为识别的热释电红外传感器设计与实现", 《中山大学硕士学位论文》, 31 December 2010 (2010-12-31), pages 1 - 60 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567715B (en) * | 2011-12-14 | 2014-01-29 | 天津大学 | Human body action hierarchical identification method based on pyroelectric infrared detection |
| CN102567715A (en) * | 2011-12-14 | 2012-07-11 | 天津大学 | Human body action hierarchical identification method based on pyroelectric infrared detection |
| EP2763116A1 (en) | 2013-02-01 | 2014-08-06 | FamilyEye BVBA | Fall detection system and method for detecting a fall of a monitored person |
| CN105765639A (en) * | 2013-09-19 | 2016-07-13 | 乌纳利沃尔有限公司 | Assist device and system |
| US10051410B2 (en) | 2013-09-19 | 2018-08-14 | Unaliwear, Inc. | Assist device and system |
| US10687193B2 (en) | 2013-09-19 | 2020-06-16 | Unaliwear, Inc. | Assist device and system |
| CN103606248A (en) * | 2013-09-30 | 2014-02-26 | 广州市香港科大霍英东研究院 | Automatic detection method and system for human body falling-over |
| CN105007463A (en) * | 2015-07-16 | 2015-10-28 | 盛玉伟 | Total management system and management method of apartment for the aged |
| CN105559789A (en) * | 2015-12-31 | 2016-05-11 | 成都麦杰康科技有限公司 | Fall detection system and method |
| US11250683B2 (en) | 2016-04-22 | 2022-02-15 | Maricare Oy | Sensor and system for monitoring |
| CN107886678A (en) * | 2017-11-10 | 2018-04-06 | 泰康保险集团股份有限公司 | Indoor monitoring method, device, medium and electronic equipment |
| CN109805936A (en) * | 2019-01-18 | 2019-05-28 | 深圳大学 | Falling over of human body detection system based on ground vibration signal |
| CN109805936B (en) * | 2019-01-18 | 2021-08-13 | 深圳大学 | Human body tumbling detection system based on ground vibration signal |
| JP2021068363A (en) * | 2019-10-28 | 2021-04-30 | 株式会社ノーリツ | Abnormality detection system |
| CN112244818A (en) * | 2020-09-30 | 2021-01-22 | 仲恺农业工程学院 | Falling detection device and method based on human body infrared perception |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102289911A (en) | Falling detection system based on pyroelectric infrared rays | |
| CN105051799A (en) | Method for detecting falls and a fall detector. | |
| CN103337132B (en) | Tumble detection method for human body based on 3-axis acceleration sensor | |
| CN107422643A (en) | Smart home monitoring method and system based on vibration detection | |
| CN203931100U (en) | The terminal that human body is fallen | |
| CN104406603B (en) | A kind of step-recording method and device based on acceleration transducer | |
| CN104188652B (en) | Electrocardiographic quality of data real-time control method and system thereof | |
| CN106228200A (en) | A kind of action identification method not relying on action message collecting device | |
| CN107693022A (en) | A kind of method and device for detecting falling over of human body | |
| CN102302370A (en) | Method and device for detecting tumbling | |
| CN106725445B (en) | A kind of the portable body injury gained in sports monitor system and method for brain wave control | |
| CN203898284U (en) | Living anomaly detection device for old people | |
| CN108519465B (en) | air pollution intelligent monitoring system based on big data | |
| CN101953682A (en) | Heartbeat detection method based on cuff device | |
| CN110675596B (en) | Fall detection method applied to wearable terminal | |
| CN102567715B (en) | Human body action hierarchical identification method based on pyroelectric infrared detection | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN205286364U (en) | Wireless Intelligence exercise heart monitors earphone | |
| CN114038012A (en) | Fall detection method and system based on millimeter wave radar and machine learning | |
| CN108955719B (en) | Step counting detection method and system based on wrist type device | |
| Zitouni et al. | Design of a smart sole with advanced fall detection algorithm | |
| CN109743667A (en) | Earphone wears detection method and earphone | |
| Fida et al. | Real time event-based segmentation to classify locomotion activities through a single inertial sensor | |
| CN106503667B (en) | A kind of fall detection method based on WISP and pattern-recognition | |
| CN110650244A (en) | Intelligent mobile phone earthquake abnormal event detection method based on STA/LTA + DTW and intelligent mobile phone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20111221 |