CN103606248A - Automatic detection method and system for human body falling-over - Google Patents
Automatic detection method and system for human body falling-over Download PDFInfo
- Publication number
- CN103606248A CN103606248A CN201310456860.1A CN201310456860A CN103606248A CN 103606248 A CN103606248 A CN 103606248A CN 201310456860 A CN201310456860 A CN 201310456860A CN 103606248 A CN103606248 A CN 103606248A
- Authority
- CN
- China
- Prior art keywords
- human body
- channel state
- state information
- action
- abnormal
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012706 support-vector machine Methods 0.000 claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 17
- 230000008054 signal transmission Effects 0.000 claims abstract description 8
- 230000009471 action Effects 0.000 claims description 90
- 230000002159 abnormal effect Effects 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 14
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 230000013016 learning Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000011895 specific detection Methods 0.000 abstract 1
- 238000013450 outlier detection Methods 0.000 description 13
- 238000012360 testing method Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010070834 Sensitisation Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000008313 sensitization Effects 0.000 description 1
Images
Landscapes
- Alarm Systems (AREA)
Abstract
An automatic detection method and a system for human body falling-over are based on a wireless network signal transmission technology. The method comprises the following steps: a wireless receiving terminal receives wireless signals from a wireless transmitting terminal and assesses channel state information; abnormity of the channel state information change is identified by using an abnormity detection algorithm; based on a one-class support vector machine which distinguishes a target motion kind from other motion kinds, an abnormity mode that a human body falling-over motion leads to a channel state information change is set as the target motion kind to determine whether a human body falling-over motion happens; if the human body falling-over motion happens, a falling-over alarm signal is emitted. The false alarm rate of the detection method provided by the invention is low; by utilizing a present wireless network and a device, other specific detection devices are not needed, and the detection method is high in universality; and at the same time people to be detected do not need to carry any extra sensing equipment, and inconvenience caused by that people to be detected carry detection equipment is avoided.
Description
Technical field
The present invention relates to the information processing technology, relate in particular to a kind of falling over of human body automatic testing method and system.
Background technology
Nowadays, world population is in an aging trend unique and that do not allow change.As the topmost health threat of the elderly and the obstacle living by oneself, has no the pressure that emissary falling down aggravated senior health and fitness and first aid cause.Therefore, we need to find a kind of can facilitating and the effective method that detection the elderly falls down and gives a response automatically in a hurry.In order to realize the accurate detection to action, people have proposed the method for utilizing environmental unit, vision or sensor to detect.Yet adopt the detection system itself that these methods are built all to exist all deficiencies.Utilizing surrounding environment equipment to fall down in the system of detection, specific equipment and instrument need to be installed in the residing environment of detected person in advance, and the vibration on the video of experiencing by equipment, audio and floor judges detected person's action.Detected person's other sound or other environmental factors is around easy to the work of interference environment equipment, thus make the mistake fall down alarming result.And utilize the detection system of falling down of vision, high-resolution camera need to be installed in the residing testing environment of detected person and take a large amount of images, and then by captured image, judge whether the generation of falling down.Yet, camera is installed and under to a certain degree, can be invaded detected person's individual privacy.Meanwhile, due to the impact of light factor, utilize falling down detection system and can not effectively working of vision under dark condition.These systems all exist the shortcoming that is subject to such environmental effects large, and the existing limitation of these systems is all that the detection of accurately also carrying out easily the elderly to fall down has caused obstacle.
Along with the development of wireless communication technology, increasing wireless device is applied in the middle of life by people.Therefore, utilizing wireless communication technology to detect the elderly's the action of falling down, to be construed to be a kind of effective and feasible method.Existing wireless communication technology has proposed the method for multiple human body exercises.Such as the 3-axis acceleration sensor by mobile device gathers the above three-dimensional acceleration information of metastomium of user, and information is carried out to fusion treatment, comprehensive human body is hit and impacts the upper angle of inclination of body in front and back and judges whether human body is fallen down, it is still effective that the method is fallen down the detection of falling down with roll-down type to many impact types, has high detection rate; But use the method, detected person need to carry mobile device, still can bring inconvenience.Separately there is a kind of detection and location device of falling down to equip inertial navigation module and GPS module, described inertial navigation module is by three-axis gyroscope, three axle magnetometers and three axis accelerometer form, this falls down detection and location device by GSM/GPRS and relatives' mobile phone of binding tested personnel, monitoring station connects, and designed the detection algorithm of falling down based on neural network and machine learning, human body is fallen down state and positional information exactly, tested personnel's the situation of falling down can be detected exactly, and can be to its real-time track and localization, system is convenient and practical, accuracy rate is high, stability is strong, but it need to be provided with specific professional equipment, cost is high and popularization is poor.Further, the sensor of carrying for utilization or be equipped with application program smart mobile phone fall down detection system, although can fall down detection in the situation that not using other particular devices, but detected person cannot guarantee carry sensors or mobile phone at any time, and carry sensors causes inconvenience to a certain degree can to detected person's life.
Summary of the invention
In order to overcome the weak point of the prior art of above-mentioned indication, the invention provides a kind of falling over of human body automatic testing method and system, with in specific indoor environment, by utilizing existing wireless network and equipment, the effective detection of realization to falling over of human body action, and reach and the function of alarm and feedback.
The present invention is achieved by the following technical solutions:
A falling over of human body automatic testing method, based on wireless network signal transmission technology, its step comprises:
S1, wireless receiving termination are received the wireless signal from wireless transmitting terminals, and are assessed channel condition information;
S2, utilize the abnormal of Outlier Detection Algorithm identification channel state information change;
S3, based on target being moved to the class support vector machines that class and other action class distinguishes, it is target action class that the falling over of human body of take action causes the abnormal patterns that channel condition information changes, judge whether to occur falling over of human body action, if so, send and fall down alarm signal.
Further, the number of described wireless transmitting terminals is one or more, and the number of described wireless interface receiving end is one or more.
Described step S1 assessment channel condition information comprises:
S11, collection initial channel status data, based on MIMO technique, described initial channel status data comprises the CSI value of N the subcarrier of the M in spatial flow, N and M are the natural number that is greater than 1;
S12, to each spatial flow, the P on asking at one time the mean value of the CSI value of subcarrier continuously, using this mean value as channel condition information, P is greater than 1 natural number that is less than M;
S13, utilize data filtering technology and running mean method to carry out smoothing processing to channel condition information.
What described step S2 utilized Outlier Detection Algorithm identification channel state information change is the time series Outlier Detection Algorithm based on local outlier factor extremely.
Further, described step S2 comprises:
S21, the time series implementation data of channel condition information is cut apart and obtained subsequence, calculate the local outlier factor of subsequence;
S22, when described local outlier factor is more than or equal to predetermined threshold value, subsequence is exported as abnormal patterns.
Further, described step S3 comprises:
S31, based on Statistical Learning Theory, set up in advance and using in setting space because every human action causes abnormal patterns that channel condition information changes as the high dimensional feature model of training sample;
S32, the abnormal patterns that step S23 is exported map in the high dimensional feature model of a class support vector machines, isolate target action class;
There is falling over of human body action in S33, judgement, sends and fall down alarm signal.
Falling over of human body automatic testing method of the present invention also comprises: step S4, feedback, for the response message of falling down alarm signal, is adjusted the high dimensional feature model of a class support vector machines.
The present invention also provides a kind of falling over of human body automatic checkout system, based on wireless network signal transmission technology, comprising:
CSI acquisition module, receives the wireless signal from wireless transmitting terminals for wireless receiving termination, and assesses channel condition information;
Abnormality detection module, for utilizing the abnormal of Outlier Detection Algorithm identification channel state information change;
Action judge module, for based on target being moved to the class support vector machines that class and other action classes distinguish, the abnormal patterns that the falling over of human body of take action is caused, as target action class, judges whether to occur falling over of human body action;
Alarm modules, while moving for there is falling over of human body when judgement, sends and falls down alarm signal.
Further, described CSI acquisition module comprises:
Sensing unit, for gathering initial channel status data, based on MIMO technique, described initial channel status data comprises the CSI value of N the subcarrier of the M in spatial flow, N and M are the natural number that is greater than 1;
Data processing unit, for to each spatial flow, on asking at one time P the mean value of the CSI value of subcarrier continuously, using this mean value as channel condition information, P is greater than 1 natural number that is less than M;
Smooth unit, for utilizing data filtering technology and running mean method to carry out smoothing processing to channel condition information.
Further, the time series Outlier Detection Algorithm of described abnormality detection module based on local outlier factor, comprising:
LOF computing unit, cuts apart and obtains subsequence for the time series implementation data to channel condition information, calculates the local outlier factor of subsequence;
Abnormal output unit, for when described local outlier factor is more than or equal to predetermined threshold value, exports subsequence as abnormal patterns.
Further, described action judge module comprises:
Set up model unit, for based on Statistical Learning Theory, set up in advance and using in setting space because every human action causes abnormal patterns that channel condition information changes as the high dimensional feature model of training sample;
Action recognition unit, maps to the high dimensional feature model of a class support vector machines for the abnormal patterns that abnormal output unit is exported, isolate target action class.
Falling over of human body automatic checkout system of the present invention also comprises a feedback module, for feeding back for the response message of falling down alarm signal, adjusts the high dimensional feature model of a class support vector machines.
Compared with prior art, the present invention is based on the radio propagation mechanism under indoor environment, channel condition information CSI and human action foundation are contacted, variation by CSI judges the action that human body occurs, determine the action whether detected person falls down, thereby realize the function of effectively reporting to the police, its beneficial effect comprises: in the less indoor environment of ornament (as laboratory), the Detection accuracy of detected action is 84%～94%, and in the more indoor environment of ornament (as dormitory), Detection accuracy also reaches 78%, rate of false alarm is lower, only have 15%～22%, can realize falling down the signal that gives the alarm after action judgement, and utilize the self-learning function of system to process wrong report situation, further reduce rate of false alarm, this detection method is on the basis of existing wireless network and equipment, fall down the testing of action, be detected in environment without other specific checkout equipments are installed, can in any environment of family, use, there is high popularization, detected person does not need to carry any extra sensing equipment simultaneously, has avoided detected person to carry the inconvenience that checkout equipment causes, for its life is provided convenience.
Accompanying drawing explanation
The hardware of the falling over of human body automatic checkout system that accompanying drawing 1 is a kind of embodiment of the present invention forms schematic diagram;
Accompanying drawing 2 is the realization flow sketch of falling over of human body automatic testing method of the present invention;
The realization flow schematic diagram of the falling over of human body automatic testing method that accompanying drawing 3 is a kind of embodiment of the present invention;
The frame diagram of the falling over of human body automatic checkout system that accompanying drawing 4 is a kind of embodiment of the present invention.
Embodiment
For the ease of those skilled in the art's understanding, below in conjunction with drawings and Examples, the invention will be further described.
A falling over of human body automatic testing method, based on wireless network signal transmission technology, its step comprises:
S1, wireless receiving termination are received the wireless signal from wireless transmitting terminals, and are assessed channel condition information;
S2, utilize the abnormal of Outlier Detection Algorithm identification channel state information change;
S3, based on target being moved to the class support vector machines that class and other action class distinguishes, it is target action class that the falling over of human body of take action causes the abnormal patterns that channel condition information changes, judge whether to occur falling over of human body action, if so, send and fall down alarm signal.
In actual applications, falling over of human body automatic testing method of the present invention can be realized on application server.Preferably, described wireless interface receiving end is wireless network card, described wireless transmitting terminals is wireless router, the radio propagation mechanism of the method based under indoor environment, set up the relation of wireless signal and human action, only need to use the existing Wireless Communication Equipment of family, the change that can change by detected person is moved the wireless signal causing is analyzed, judge the action of falling down whether detected person occur and report to the police, reduced surrounding environment factor to falling down the impact of motion detection, by improve greatly fall down detection accuracy.In specific indoor environment, can collect by wireless network card the abundant channel condition information of wireless network.In the present invention, the number of described wireless transmitting terminals is one or more, and the number of described wireless interface receiving end is one or more.In system, by many antennas, carry out sending and receiving wireless signal respectively; The wireless network card that system is used can receiving channel state information.Preferably, the number of wireless transmitting terminals and wireless interface receiving end is 2 or 3.As described in Figure 1, in detected environment, there are two wireless transmitting terminals (the first transmitter and the second transmitter) and two wireless interface receiving ends (the first receiving end and the second receiving end).Wherein the first receiving end receives the abbreviation from the CSI(Channel State Information of the first transmitter, it is channel condition information, at wireless communication field, CSI is exactly the channel attribute of communication link, the weak factor of signal on every transmission paths described), the second receiving end receives the CSI from the second transmitter.In detected environment, detected person is without carrying other extras.System detects the CSI that utilizes two wireless interface receiving ends to receive to detected person's action, thereby and judges whether detected person falls down.
In order to set up the contact between wireless signal and human action, the present invention adopts the channel condition information CSI of wireless network as indicant.CSI can describe out under the joint effect of time delay, amplitude fading and phase shift, the route of transmission of a signal.Radio propagation model based under indoor environment, the present invention has set up contacting between CSI and human action.In a specific indoor environment (as a room), there is a main travel path and a plurality of reflection paths producing because of surrounding environment (ceiling, floor and wall) impact.When detected person is in this room, his health can produce many scattering paths.When detected person keeps stationary state in this environment, the receiving end in this environment can receive stable Propagation of Energy.And change when detected person's generation action, for example, when detected person falls down, by human body, affected and the scattering point that produces scattering path can change position rapidly, and the energy that this sudden change can cause receiving end to be received changes.And by this variation, the present invention will judge human body which kind of action variation has specifically occurred.The present invention utilizes orthogonal frequency carrier multiplexing (Orthogonal Frequency Division Multiplex, OFDM) to obtain the CSI existing with subcarrier (subcarrier) form.And make to set up to contact between the CSI that obtains in this way and human action to improve the accuracy rate to action judgement.
Particularly, in described step S1, assessment channel condition information comprises:
S11, collection initial channel status data, based on MIMO technique, described initial channel status data comprises the CSI value of N the subcarrier of the M in spatial flow, N and M are the natural number that is greater than 1;
S12, to each spatial flow, the P on asking at one time the mean value of the CSI value of subcarrier continuously, using this mean value as channel condition information, P is greater than 1 natural number that is less than M;
S13, utilize data filtering technology and running mean method to carry out smoothing processing to channel condition information.
When system of the present invention is started working, wireless transmitting terminals is propagated wireless network signal, and the wireless interface receiving end in the specific region computer of network interface card (as be equipped with) can be collected CSI as initial channel status data simultaneously, then carries out data processing.Take that to use 3 * 3 Multiple Input Multiple Output (Multiple-Input Multiple-Out-put, MIMO) be example, the initial channel status data obtaining at phase of sensitization can be divided into 9 spatial flows, and has 30 subcarriers in each stream.Through experiment, find, the data that the variation meeting of human action comprises different spatial flows exert an influence, and on all subcarriers in each spatial flow, can produce similar impact.Meanwhile, experiment shows, environmental factor (as temperature, the setting in room) also can cause the CSI of collection to rise and fall to some extent.Therefore, in the present invention, each independently the CSI value of 30 subcarriers in spatial flow be aggregated into an independent channel condition information.Preferably, to each spatial flow, first try to achieve the CSI mean value of continuous 5 subcarriers, and the CSI mean value that 9 spatial flows are got respectively to same time point is as channel condition information.In order to reduce the interference of environmental factor, the present invention utilizes data filtering technology and running mean method, particularly, use the method for weighted moving average (weighted moving average) to carry out smoothing processing to the channel condition information by above-mentioned processing, to reduce the noise in data.
Described step S2 is intended to detect the abnormal change of wireless signal.Although different fixing human postures can cause different signal intensities, it has identical signal intensity tendency in time domain, and along with the time tends towards stability gradually.And the action of human body, as walking, upright, fall down the unexpected fluctuating that can cause obvious channel condition information.Preferably, the Outlier Detection Algorithm of utilization of the present invention based on local outlier factor (Local Outlier Factor), first estimates normal profile, then calculates local outlier factor, thereby isolates the abnormal patterns being caused by various human actions.
What described step S2 utilized Outlier Detection Algorithm identification channel state information change is the time series Outlier Detection Algorithm based on local outlier factor extremely, further, comprising:
S21, the time series implementation data of channel condition information is cut apart and obtained some subsequences, calculate the local outlier factor of subsequence;
S22, when described local outlier factor is more than or equal to predetermined threshold value, subsequence is exported as abnormal patterns.
Preferably, utilize time series Outlier Detection Algorithm, can limit by more accurate examination criteria, the two kinds of corresponding time serieses of posture of will walking and stand are separated, and get rid of this two kinds of abnormal patterns that common human action causes.
After completing abnormality detection module, groups of people's body action will be exported corresponding abnormal patterns because cause the significant change of channel condition information to be detected.Then, to these abnormal patterns, will enter motion analysis, thereby judgement abnormal patterns is to belong to which kind of action.In order to distinguish and to fall down action from these patterns, the present invention has used a class support vector machines (one-class Support Vector Machine, one-class SVM) of the feature based on being extracted from abnormal patterns.One class SVM is a kind of algorithm of support vector machine of expansion.At a class SVM, all samples are divided into target class and other classes.In order to solve the problem of Nonlinear Classification, input sample is mapped to a higher-dimension image.In the present invention, the abnormal patterns of falling down action is considered target action class, and the abnormal patterns of other actions is regarded as other action classes.The abnormal patterns of falling down action has also been mapped to a higher-dimension image in advance.By utilizing a class SVM to judge, can from the abnormal patterns of previous step output, isolate to fall down and move, depend on by the abnormal patterns of exporting and selected model, thereby determine to have occurred which kind of action.
Further, described step S3 comprises:
S31, based on Statistical Learning Theory, set up in advance and using in setting space because every human action causes abnormal patterns that channel condition information changes as the high dimensional feature model of training sample;
S32, the abnormal patterns that step S23 is exported map in the high dimensional feature model of a class support vector machines, isolate target action class;
There is falling over of human body action in S33, judgement, sends and fall down alarm signal.
Falling over of human body automatic testing method of the present invention also comprises: step S4, feedback, for the response message of falling down alarm signal, is adjusted the high dimensional feature model of a class support vector machines.When fall down action be detected after, will enter the alarm processing stage.When certain abnormal patterns is identified as, falling down action, can there is alarm in system.If alarm is closed in time, illustrate that detected person does not need or obtained help, the response message of now system utilization feedback, upgrade the historical record of falling over of human body action judgement, and for adjusting and improving the high dimensional feature model of a class support vector machines, providing can optimum detection and the system feedback of decision making algorithm.If alarm is not closed in time, system can be sent help information to other people by other equipment of signal association, such as apply transmission instant messages or note etc. by third party, seeks help.
Process flow diagram as shown in Figure 2, discloses three important steps of detection method of the present invention, comprising: CSI data processing, abnormality detection and the classification of motion.
Particularly, as shown in Figure 3, the present invention also provides the realization flow of the falling over of human body automatic testing method of a kind of embodiment, and its step comprises:
S301, wireless receiving termination are received the wireless signal from wireless transmitting terminals, gather initial channel status data simultaneously;
S302, ask for merge subcarrier CSI mean value as channel condition information;
S303, channel condition information is carried out to smoothing processing;
S304, the normal profile of channel condition information is estimated, utilized Outlier Detection Algorithm to calculate local outlier factor;
S305, output abnormality pattern;
S306, the abnormal patterns of output is mapped in the high dimensional feature model of a class support vector machines;
S307, utilize a class support vector machines to classify, it is target action class that the falling over of human body of wherein take action causes the abnormal patterns that channel condition information changes;
S308, judge whether to isolate target action class, if so, perform step S209, otherwise return to step S301;
There is falling over of human body action in S309, judgement, sends and fall down alarm signal;
S310, judge whether alarm is closed in time in a setting-up time interval, if so, performs step S311, otherwise, execution step S312;
S311, to system feedback shutoff operation and abnormal patterns parameter, optimum detection and action evaluation algorithm;
S312, outwards send help information.
The present invention also provides a kind of falling over of human body automatic checkout system, as shown in Figure 4, based on wireless network signal transmission technology, comprising:
CSI acquisition module 41, receives the wireless signal from wireless transmitting terminals for wireless receiving termination, and assesses channel condition information;
Abnormality detection module 42, for utilizing the abnormal of Outlier Detection Algorithm identification channel state information change;
Action judge module 43, for based on target being moved to the class support vector machines that class and other action classes distinguish, the abnormal patterns that the falling over of human body of take action is caused, as target action class, judges whether to occur falling over of human body action;
Alarm modules 44, while moving for there is falling over of human body when judgement, sends and falls down alarm signal.
In falling over of human body automatic checkout system of the present invention, the number of described wireless transmitting terminals is one or more, and the number of described wireless interface receiving end is one or more.Preferably, the number of wireless transmitting terminals and wireless interface receiving end is 2 or 3.
Further, described CSI acquisition module comprises:
Sensing unit 411, for gathering initial channel status data, based on MIMO technique, described initial channel status data comprises the CSI value of N the subcarrier of the M in spatial flow, N and M are the natural number that is greater than 1;
Data processing unit 412, for to each spatial flow, on asking at one time P the mean value of the CSI value of subcarrier continuously, using this mean value as channel condition information, P is greater than 1 natural number that is less than M;
Smooth unit 413, for utilizing data filtering technology and running mean method to carry out smoothing processing to channel condition information.
Further, the time series Outlier Detection Algorithm of described abnormality detection module based on local outlier factor, comprising:
LOF computing unit 421, cuts apart and obtains some subsequences for the time series implementation data to channel condition information, calculates the local outlier factor of subsequence;
Abnormal output unit 422, for when described local outlier factor is more than or equal to predetermined threshold value, exports subsequence as abnormal patterns.
Further, described action judge module comprises:
Set up model unit 431, for based on Statistical Learning Theory, set up in advance and using in setting space because every human action causes abnormal patterns that channel condition information changes as the high dimensional feature model of training sample;
Action recognition unit 432, maps to the high dimensional feature model of a class support vector machines for the abnormal patterns that abnormal output unit is exported, isolate target action class.
Falling over of human body automatic checkout system of the present invention also comprises a feedback module 45, for feeding back for the response message of falling down alarm signal, adjusts the high dimensional feature model of a class support vector machines.
Above content is in conjunction with concrete optimal way further description made for the present invention, should not assert that specific embodiment of the invention is confined to above explanation.For those skilled in the art, without departing from the inventive concept of the premise, can also make some simple deduction or replace, within the definite protection domain of the claim that all should be considered as being submitted to by the present invention.
Claims (12)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310456860.1A CN103606248B (en) | 2013-09-30 | 2013-09-30 | A method and system for automatic detection of human fall |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310456860.1A CN103606248B (en) | 2013-09-30 | 2013-09-30 | A method and system for automatic detection of human fall |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103606248A true CN103606248A (en) | 2014-02-26 |
| CN103606248B CN103606248B (en) | 2016-08-10 |
Family
ID=50124467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310456860.1A Expired - Fee Related CN103606248B (en) | 2013-09-30 | 2013-09-30 | A method and system for automatic detection of human fall |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103606248B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927851A (en) * | 2014-04-04 | 2014-07-16 | 余志峰 | Individualized multi-threshold tumble detection method and system |
| CN103971108A (en) * | 2014-05-28 | 2014-08-06 | 北京邮电大学 | Wireless communication-based human body posture recognition method and device |
| CN104065928A (en) * | 2014-06-26 | 2014-09-24 | 北京小鱼儿科技有限公司 | Behavior pattern counting device and behavior pattern counting method |
| CN104361361A (en) * | 2014-11-14 | 2015-02-18 | 北京天地弘毅科技有限公司 | Method and system for judging fall through cloud computing and machine learning algorithm |
| CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
| CN104766427A (en) * | 2015-04-27 | 2015-07-08 | 太原理工大学 | Detection method for illegal invasion of house based on Wi-Fi |
| CN105761407A (en) * | 2016-01-06 | 2016-07-13 | 深圳大学 | Indoor fire detection and alarming method and system based on wireless network signal transmission |
| CN105809110A (en) * | 2016-02-24 | 2016-07-27 | 南京大学 | Behavior identification system and method based on wireless signal identity |
| WO2017124816A1 (en) * | 2016-01-20 | 2017-07-27 | 北京大学 | Fall detection method and system |
| CN107146377A (en) * | 2017-04-14 | 2017-09-08 | 深圳大学 | Pre-collision fall detection method and device |
| WO2018006798A1 (en) * | 2016-07-05 | 2018-01-11 | 深圳大学 | Wireless sensing-based temperature detection method and system |
| CN107749143A (en) * | 2017-10-30 | 2018-03-02 | 安徽工业大学 | A kind of indoor occupant fall detection system and method through walls based on WiFi signal |
| WO2018133264A1 (en) * | 2017-01-18 | 2018-07-26 | 深圳大学 | Indoor automatic human body positioning detection method and system |
| CN108833036A (en) * | 2018-05-31 | 2018-11-16 | 湖南大学 | Human fall detection method |
| CN109190605A (en) * | 2018-10-30 | 2019-01-11 | 宁波大学 | A kind of human body continuous action method of counting based on CSI |
| CN109745026A (en) * | 2017-11-07 | 2019-05-14 | 深圳欧德蒙科技有限公司 | A kind of method for measuring heart rate and system |
| CN110706463A (en) * | 2019-06-11 | 2020-01-17 | 南京信息工程大学 | WIFI passive sensing method and system suitable for tumble monitoring |
| WO2020103411A1 (en) * | 2018-11-22 | 2020-05-28 | 九牧厨卫股份有限公司 | Fall detection method, device, and system |
| CN111512178A (en) * | 2017-12-08 | 2020-08-07 | 认知系统公司 | Motion Detection Based on Machine Learning of Wireless Signal Properties |
| CN111759305A (en) * | 2019-04-02 | 2020-10-13 | 纬创资通股份有限公司 | Liveness detection method and liveness detection system |
| CN112446426A (en) * | 2020-11-23 | 2021-03-05 | 中国科学技术大学 | Tumble detection method and device, electronic device and storage medium |
| CN112446244A (en) * | 2019-08-29 | 2021-03-05 | 华为技术有限公司 | Human body action recognition method, neural network training method, related device and equipment |
| CN112545496A (en) * | 2020-11-09 | 2021-03-26 | 金茂智慧科技(广州)有限公司 | Wireless technology identification method for detecting human body tumble |
| CN113499064A (en) * | 2021-07-07 | 2021-10-15 | 郑州大学 | Wi-Fi perception human body tumbling detection method and system in bathroom scene |
| CN113870528A (en) * | 2021-09-17 | 2021-12-31 | 四川华能宝兴河水电有限责任公司 | Method for rapidly sensing dangerous events through intelligent safety helmet |
| CN114758476A (en) * | 2022-04-18 | 2022-07-15 | 上海物骐微电子有限公司 | Activity information monitoring method, device, system, equipment and storage medium |
| WO2022179948A1 (en) * | 2021-02-24 | 2022-09-01 | Signify Holding B.V. | Fall-classification device and arrangement |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7076102B2 (en) * | 2001-09-27 | 2006-07-11 | Koninklijke Philips Electronics N.V. | Video monitoring system employing hierarchical hidden markov model (HMM) event learning and classification |
| US20090161915A1 (en) * | 2007-12-24 | 2009-06-25 | National Chiao Tung University Of Taiwan | Multi-person pose recognition system using a zigbee wireless sensor network |
| CN102136180A (en) * | 2011-03-11 | 2011-07-27 | 北京航空航天大学 | Device for detecting and alarming human body tumble |
| CN202033874U (en) * | 2011-03-29 | 2011-11-09 | 江洪 | Tumbling alarm system |
| CN102289911A (en) * | 2011-07-19 | 2011-12-21 | 中山大学深圳研究院 | Falling detection system based on pyroelectric infrared rays |
| CN102421189A (en) * | 2011-11-22 | 2012-04-18 | 中山大学 | Method and device for realizing wireless network indoor positioning based on physical layer |
| CN102595324A (en) * | 2012-03-31 | 2012-07-18 | 上海交通大学 | Wireless sensor network-based regional falling detection positioning system and method |
| CN103211599A (en) * | 2013-05-13 | 2013-07-24 | 桂林电子科技大学 | Method and device for monitoring tumble |
-
2013
- 2013-09-30 CN CN201310456860.1A patent/CN103606248B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7076102B2 (en) * | 2001-09-27 | 2006-07-11 | Koninklijke Philips Electronics N.V. | Video monitoring system employing hierarchical hidden markov model (HMM) event learning and classification |
| US20090161915A1 (en) * | 2007-12-24 | 2009-06-25 | National Chiao Tung University Of Taiwan | Multi-person pose recognition system using a zigbee wireless sensor network |
| CN102136180A (en) * | 2011-03-11 | 2011-07-27 | 北京航空航天大学 | Device for detecting and alarming human body tumble |
| CN202033874U (en) * | 2011-03-29 | 2011-11-09 | 江洪 | Tumbling alarm system |
| CN102289911A (en) * | 2011-07-19 | 2011-12-21 | 中山大学深圳研究院 | Falling detection system based on pyroelectric infrared rays |
| CN102421189A (en) * | 2011-11-22 | 2012-04-18 | 中山大学 | Method and device for realizing wireless network indoor positioning based on physical layer |
| CN102595324A (en) * | 2012-03-31 | 2012-07-18 | 上海交通大学 | Wireless sensor network-based regional falling detection positioning system and method |
| CN103211599A (en) * | 2013-05-13 | 2013-07-24 | 桂林电子科技大学 | Method and device for monitoring tumble |
Non-Patent Citations (1)
| Title |
|---|
| 霍宏伟等: "基于室内无线传感器网络射频信号的老年人跌倒检测研究", 《电子学报》 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927851A (en) * | 2014-04-04 | 2014-07-16 | 余志峰 | Individualized multi-threshold tumble detection method and system |
| CN103971108A (en) * | 2014-05-28 | 2014-08-06 | 北京邮电大学 | Wireless communication-based human body posture recognition method and device |
| CN104065928A (en) * | 2014-06-26 | 2014-09-24 | 北京小鱼儿科技有限公司 | Behavior pattern counting device and behavior pattern counting method |
| CN104361361B (en) * | 2014-11-14 | 2018-04-03 | 北京天地弘毅科技有限公司 | The method and system for judging to fall down by cloud computing and machine learning algorithm |
| CN104361361A (en) * | 2014-11-14 | 2015-02-18 | 北京天地弘毅科技有限公司 | Method and system for judging fall through cloud computing and machine learning algorithm |
| CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
| CN104766427A (en) * | 2015-04-27 | 2015-07-08 | 太原理工大学 | Detection method for illegal invasion of house based on Wi-Fi |
| CN104766427B (en) * | 2015-04-27 | 2017-04-05 | 太原理工大学 | A kind of house illegal invasion detection method based on Wi Fi |
| CN105761407A (en) * | 2016-01-06 | 2016-07-13 | 深圳大学 | Indoor fire detection and alarming method and system based on wireless network signal transmission |
| WO2017117910A1 (en) * | 2016-01-06 | 2017-07-13 | 深圳大学 | Indoor fire detection and alarm method and system based on wireless network signal transmission |
| CN105761407B (en) * | 2016-01-06 | 2019-05-10 | 深圳大学 | Indoor fire detection and alarm method and system based on wireless network signal transmission |
| US20190175074A1 (en) * | 2016-01-20 | 2019-06-13 | Peking University | Fall detection method and system |
| WO2017124816A1 (en) * | 2016-01-20 | 2017-07-27 | 北京大学 | Fall detection method and system |
| US10531817B2 (en) * | 2016-01-20 | 2020-01-14 | Peking University | Fall detection method and system |
| CN105809110A (en) * | 2016-02-24 | 2016-07-27 | 南京大学 | Behavior identification system and method based on wireless signal identity |
| WO2018006798A1 (en) * | 2016-07-05 | 2018-01-11 | 深圳大学 | Wireless sensing-based temperature detection method and system |
| WO2018133264A1 (en) * | 2017-01-18 | 2018-07-26 | 深圳大学 | Indoor automatic human body positioning detection method and system |
| CN107146377A (en) * | 2017-04-14 | 2017-09-08 | 深圳大学 | Pre-collision fall detection method and device |
| CN107749143A (en) * | 2017-10-30 | 2018-03-02 | 安徽工业大学 | A kind of indoor occupant fall detection system and method through walls based on WiFi signal |
| CN107749143B (en) * | 2017-10-30 | 2023-09-19 | 安徽工业大学 | A system and method for detecting falls of indoor people through walls based on WiFi signals |
| CN109745026A (en) * | 2017-11-07 | 2019-05-14 | 深圳欧德蒙科技有限公司 | A kind of method for measuring heart rate and system |
| CN111512178A (en) * | 2017-12-08 | 2020-08-07 | 认知系统公司 | Motion Detection Based on Machine Learning of Wireless Signal Properties |
| CN111512178B (en) * | 2017-12-08 | 2024-06-04 | 认知系统公司 | Motion detection based on machine learning of wireless signal properties |
| CN108833036B (en) * | 2018-05-31 | 2020-11-03 | 湖南大学 | Human fall detection method |
| CN108833036A (en) * | 2018-05-31 | 2018-11-16 | 湖南大学 | Human fall detection method |
| CN109190605A (en) * | 2018-10-30 | 2019-01-11 | 宁波大学 | A kind of human body continuous action method of counting based on CSI |
| WO2020103411A1 (en) * | 2018-11-22 | 2020-05-28 | 九牧厨卫股份有限公司 | Fall detection method, device, and system |
| TWI761671B (en) * | 2019-04-02 | 2022-04-21 | 緯創資通股份有限公司 | Living body detection method and living body detection system |
| CN111759305A (en) * | 2019-04-02 | 2020-10-13 | 纬创资通股份有限公司 | Liveness detection method and liveness detection system |
| US11023718B2 (en) | 2019-04-02 | 2021-06-01 | Wistron Corporation | Living body detection method and living body detection system |
| CN111759305B (en) * | 2019-04-02 | 2023-08-25 | 纬创资通股份有限公司 | Living body detection method and living body detection system |
| CN110706463A (en) * | 2019-06-11 | 2020-01-17 | 南京信息工程大学 | WIFI passive sensing method and system suitable for tumble monitoring |
| CN112446244A (en) * | 2019-08-29 | 2021-03-05 | 华为技术有限公司 | Human body action recognition method, neural network training method, related device and equipment |
| CN112545496A (en) * | 2020-11-09 | 2021-03-26 | 金茂智慧科技(广州)有限公司 | Wireless technology identification method for detecting human body tumble |
| CN112446426A (en) * | 2020-11-23 | 2021-03-05 | 中国科学技术大学 | Tumble detection method and device, electronic device and storage medium |
| WO2022179948A1 (en) * | 2021-02-24 | 2022-09-01 | Signify Holding B.V. | Fall-classification device and arrangement |
| CN113499064A (en) * | 2021-07-07 | 2021-10-15 | 郑州大学 | Wi-Fi perception human body tumbling detection method and system in bathroom scene |
| CN113870528A (en) * | 2021-09-17 | 2021-12-31 | 四川华能宝兴河水电有限责任公司 | Method for rapidly sensing dangerous events through intelligent safety helmet |
| CN114758476A (en) * | 2022-04-18 | 2022-07-15 | 上海物骐微电子有限公司 | Activity information monitoring method, device, system, equipment and storage medium |
| CN114758476B (en) * | 2022-04-18 | 2024-04-26 | 上海物骐微电子有限公司 | Activity information monitoring method, device, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103606248B (en) | 2016-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103606248A (en) | Automatic detection method and system for human body falling-over | |
| Gu et al. | Paws: Passive human activity recognition based on wifi ambient signals | |
| Zhang et al. | Anti-fall: A non-intrusive and real-time fall detector leveraging CSI from commodity WiFi devices | |
| Vlahogianni et al. | Driving analytics using smartphones: Algorithms, comparisons and challenges | |
| Jia et al. | WiFind: Driver fatigue detection with fine-grained Wi-Fi signal features | |
| CN113609976B (en) | A direction-sensitive multi-gesture recognition system and method based on WiFi devices | |
| CN106802404B (en) | A kind of human body indoor positioning automatic testing method and system | |
| CN104615244A (en) | Automatic gesture recognizing method and system | |
| CN105809110A (en) | Behavior identification system and method based on wireless signal identity | |
| CN110706463A (en) | WIFI passive sensing method and system suitable for tumble monitoring | |
| Wittenburg et al. | Cooperative event detection in wireless sensor networks | |
| CN106846729A (en) | A kind of fall detection method and system based on convolutional neural networks | |
| Chen et al. | AFall: Wi-Fi-based device-free fall detection system using spatial angle of arrival | |
| CN120032474A (en) | An intelligent monitoring method and system based on fall risk warning | |
| CN119091360B (en) | A posture recognition management system and method for factory workers | |
| CN108898079A (en) | A kind of monitoring method and device, storage medium, camera terminal | |
| CN114999643A (en) | WiFi-based intelligent monitoring method for old people | |
| CN106411433A (en) | WLAN-based fine-grained indoor passive intrusion detection method | |
| Hao et al. | CSI‐HC: a WiFi‐based indoor complex human motion recognition method | |
| CN106650300B (en) | An elderly monitoring system and method based on extreme learning machine | |
| CN113225144A (en) | Wireless sensing method based on channel state information decomposition | |
| CN104392583A (en) | Fall detection and alarm system and method based on KNN algorithm | |
| CN109431526A (en) | Driving condition recognition methods and system based on WIFI | |
| Chen et al. | WITM: Intelligent traffic monitoring using fine-grained wireless signal | |
| Doukas et al. | Enabling human status awareness in assistive environments based on advanced sound and motion data classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| 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: 20160810 |