CN110703241A - Human body falling detection self-adaptive system and device based on UWB radar - Google Patents
Human body falling detection self-adaptive system and device based on UWB radar Download PDFInfo
- Publication number
- CN110703241A CN110703241A CN201910918192.7A CN201910918192A CN110703241A CN 110703241 A CN110703241 A CN 110703241A CN 201910918192 A CN201910918192 A CN 201910918192A CN 110703241 A CN110703241 A CN 110703241A
- Authority
- CN
- China
- Prior art keywords
- fall
- human body
- falling
- detected person
- value
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
- G01S13/08—Systems for measuring distance only
Abstract
The invention discloses a human body fall detection self-adaptive system and a device based on a UWB radar, wherein human body characteristic detection is analyzed, different characteristic parameters are set according to different people, whether a detected person falls or not is judged, after the detected person falls, confirmation information is sent to the detected person and confirmed by the detected person, whether the detected person falls or not is confirmed according to feedback information of the detected person, if the detected person falls, alarming is carried out, and if the detected person does not fall, the characteristic parameters are corrected, wherein the correction comprises prolonging the set time length, increasing the height change value h, increasing the acceleration alpha during falling, reducing the height d after falling, increasing the fall holding time length t, reducing the fall model reliability P and the like; this application confirms whether really falling down and form the closed loop by being detected the people through dynamic setting characteristic parameter, improves the accuracy that falls down to detect.
Description
Technical Field
The invention relates to the technical field of human body fall detection, in particular to a UWB radar-based human body fall detection self-adaptive system and device.
Background
With the continuous improvement of living standard and medical technology, the aging problem of population is increasingly prominent, and young people have to be far away from home and parents for life, so that many old people can live alone, in this case, the old people can not be found and rescued in time due to the falling down caused by inconvenient actions or diseases, which can have serious consequences, and the detection of the home state of the old people is very needed in order to find the old people in time when accidents happen.
At present, related products exist for detecting the body state of the old, related patents also exist for detecting by adopting radar waves, for example, the application number is 1810981493, X is named as a human body detection method and device based on millimeter waves, whether a human body falls down or not is detected by adopting the radar waves, but the heights of the human body are different, the installation heights of radar equipment are also different, in the technology, the technology does not relate to the aim at different human body heights and different installation heights of the radar equipment, and the aim of setting parameters pertinently and improving the accuracy of human body fall-down detection is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a human body fall detection self-adaptive system and device based on a UWB radar.
The above object of the present invention is achieved by the following technical solutions:
a human body fall detection self-adaptive system based on a UWB radar comprises the following steps:
s1, detecting human body characteristics;
s2, establishing a general human body tumbling characteristic library, and setting human body tumbling characteristic parameters;
s3, establishing a private feature library according to the height of the human body;
s4, detecting the state of the detected person in real time;
s5, judging whether the detected person falls down or not according to the detection result, if not, turning to S4, and if so, entering the next step;
s6, sending tumbling information to the detected person;
s7, receiving feedback information of the detected person;
s8, judging whether the feedback information is a fall or not, if so, turning to S10, and if not, entering the next step;
s9, correcting the characteristic parameters of human body tumble, and turning to S4;
and S10, warning of falling.
The invention is further configured to: in step S1, the distance between the object and the radar observation point is calculated based on the time interval T between the detection of the radar transmission wave and the detection of the reflection wave reflected from the human body.
The invention is further configured to: in step S2, a general human body fall characteristic library is established in a dynamic manner, that is, a corresponding initial fall model is set according to the initial installation height of the radar transmitting device and different human body heights.
The invention is further configured to: in step S2, the human body fall characteristic parameters include a height variation value h, a fall acceleration α, a fall height d, a fall retention time t, and a fall model reliability p, and a threshold value is set corresponding to each characteristic parameter.
The invention is further configured to: after a fall, the initial value of the height change is calculated by the following formula:
Wherein alpha is0Indicating acceleration at fall, t0Indicating an initial value of the duration of fall holding time, HtallIndicating the height of the human body.
The invention is further configured to: initial height value d after falling0Calculated according to the following formula:
d0＝H-(W×Htall)+q；
wherein H represents the distance between the radar wave transmitting point and the ground; w represents the human shoulder width coefficient, HtallAnd q is an error correction value.
The invention is further configured to: the method from human body characteristic detection to human body tumble characteristic parameter correction comprises the following steps:
a1, setting initial value h of height change0Initial value of acceleration alpha0Initial height value d after falling0Initial value t of tumble holding time0；
A2, setting the initial value of the falling model credibility p as 1;
a3, detecting the detected person in real time, and calculating the characteristic parameters of the detected person;
a4, comparing the detected data with a set value;
a5, judging whether the detected person falls down or not according to the comparison result, if not, turning to A3, and if so, entering the next step;
a6, sending fall information to the detected person;
a7, judging whether the feedback information of the detected person is a fall, if so, turning to A14, and if not, entering the next step;
a8, p is p-m, and the reliability p value of the falling model is corrected;
a9, starting timing;
a10, when the timing duration is equal to the set timing duration, judging whether the height after falling is less than or equal to the set value, if so, turning to A14, and if not, entering the next step;
a11, judging whether the p value is equal to zero, if not, turning to A13, and if so, entering the next step;
a12, increasing the height change value h-h + n, the acceleration set value alpha-alpha + i, the fall keeping time period t-t + j, or reducing the height after falling, or prolonging the set time period, and turning to a 2;
a13, ending the process, and turning to A3;
a14, warning of falling;
wherein m, n, i, j represent the respective step sizes.
The invention is further configured to: in step a3, the feedback information of the detected person includes at least one of the detected person replying to confirm the fall, clicking the robot screen to confirm the fall button, and not responding for a set time.
The invention is further configured to: in step a5, when the real-time detection parameters simultaneously satisfy: real-time altitude change is greater than or equal to altitude change set value hsAdding in real timeThe speed is more than or equal to the set value alpha of the acceleration, and the real-time height is less than or equal to the set value d of the height after fallingsAnd when the real-time falling holding time length is more than or equal to the set value t of the falling holding time length, judging that the falling is carried out.
The invention is further configured to: in step a10, the set time period varies with the detection frequency, and decreases when the detection frequency increases, whereas increases when the detection frequency decreases.
The above object of the present invention is also achieved by the following technical solutions:
a human body fall detection self-adaptive device based on a UWB radar comprises a radar transmitting and receiving device and a robot device, wherein the radar transmitting and receiving device is used for transmitting UWB radar waves and calculating and obtaining whether a human body falls or not according to the time interval between the transmitted and received radar waves; when the human body is detected to fall down, the robot is controlled to send a confirmation instruction, and the detected person confirms whether the human body falls down or not to form a closed loop; when the detected person confirms that the person falls, an alarm is given, and when the person confirms that the person does not fall, the parameters are corrected to reduce false alarm.
Compared with the prior art, the invention has the beneficial technical effects that:
1. the self-adaptive system disclosed by the application enables the characteristic parameters to accord with individual characteristics by setting and correcting the characteristic parameters, so that the accuracy of fall detection is improved;
2. furthermore, a universal human body falling characteristic library is established in a dynamic mode, so that wide characteristic data are provided for human body falling, and applicable groups of falling are expanded;
3. furthermore, the state of the detected person is fed back in real time through the robot to form a closed loop, characteristic parameters are corrected, real-time and timely correspondence between detection and real-time is achieved, and accuracy of judgment is improved.
Drawings
FIG. 1 is a schematic flow diagram of one embodiment of the present invention;
FIG. 2 is a schematic flow chart of another embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Detailed description of the invention
The invention discloses a human body fall detection self-adaptive system based on a UWB radar, which comprises the following steps as shown in figure 1:
s1, detecting human body characteristics;
s2, establishing a general human body tumbling characteristic library, and setting human body tumbling characteristic parameters;
s3, establishing a private feature library according to the height of the human body;
s4, detecting the state of the detected person in real time;
s5, judging whether the detected person falls down or not according to the detection result, if not, turning to S4, and if so, entering the next step;
s6, sending tumbling information to the detected person;
s7, receiving feedback information of the detected person;
s8, judging whether the feedback information is a fall or not, if so, turning to S10, and if not, entering the next step;
s9, correcting the characteristic parameters of human body tumble, and turning to S4;
and S10, warning of falling.
Specifically, in step S1, the distance between the object and the radar observation point is calculated based on the time interval T between the detection of the radar transmission wave and the detection of the reflection wave reflected from the human body.
The radar transmitting device is arranged on the ceiling, and the radar transmitting waves are transmitted back after being reflected by the ground according to the transmission time t1Calculating the distance H from the ground to the radar transmitting device,
the human body stands under the radar transmitting device, and the transmission time t of the transmitted waves of the radar after being reflected by the ground is detected2Calculating the distance H2 between the head of the human body and the radar transmitting device,
thereby obtaining the height of the human body as Htall＝H-H2；
In step S2, a general human body fall model is first established, and the characteristic parameters of the human body fall include:
height variation value h, fall acceleration α, fall height d, fall hold duration threshold t, and fall model confidence level p.
Due to the fact that the radar wave devices are different in installation height, the height difference of detected people can cause the accuracy rate of the general human body characteristic checking algorithm to be too low, and a method for adapting to different environments and different people is unavailable. Obviously, the height change value h is very different between 1.8 m and 1.6 m, after the person lies down, the person of 1.6 m is judged to fall, and the person of 1.8 m may just make a squatting action. There is also a difference between the minimum distance of a person from a radar wave detected after a human body falls, between a device installed at a height of 3 meters and a device installed at a height of 2.5 meters. In order to overcome the factors that can produce the error above, this application adopts the dynamic mode to establish general human body and falls down the characteristic storehouse, according to radar transmitting equipment initial installation height, different human height promptly, the different detection condition values that fall down of automatic configuration, wherein, to the radar transmitting equipment that concrete installation is good, its height apart from ground is exactly a definite value, and the people of different heights, height variation value h after falling down, height d after falling down adopt following formula to calculate:
height variation value
And H is less than or equal to Htall；
Wherein alpha represents the acceleration of the fall, t represents the value of the duration of the fall, HtallIndicating the height of the human body.
Height after falling d ═ H- (WXH)tall)+q；
Wherein H represents the distance between the radar wave transmitting point and the ground; w represents the human shoulder width coefficient, HtallAnd q is an error correction value.
Wherein, W is multiplied by HtallThe shoulder width.
After the person lies down, the person also occupies a certain height, and the maximum value is the shoulder width value.
The average human shoulder width coefficient for asian males is 0.2319.
And establishing a general human body tumbling characteristic library by setting the characteristic parameters.
Judging whether the detected person falls or not by detecting the state of the detected person, sending fall information to the detected person when the detected person is found to fall, confirming whether the detected person falls or not by the detected person to form a closed loop, and immediately judging that the detected person falls and giving an alarm when the same characteristic parameters appear next time if the detected person confirms that the detected person falls; if the detected person confirms that the person is not fallen, after the person is fallen for a plurality of times, the characteristic parameters are corrected, and the detection accuracy is improved.
And when the value of the falling model credibility p is equal to A in the detected result, judging that the falling is carried out.
When the falling examinee confirms that the person is not falling, the reliability of the falling model is low, and the reliability p of the falling model is reduced, wherein p is p-m, and m represents the step length of the reliability of the falling model.
When the reliability p of the falling model is between 0 and A, after falling occurs, carrying out waiting cyclic judgment according to a set time length:
when the falling duration is equal to the set duration, judging whether the height d after falling is less than or equal to the set height value d after fallingsIf yes, judging that the detected person is in a tumbling state, and giving an alarm;
when the falling duration is equal to the set duration, and the height d after falling is larger than the set value, the false alarm is judged, the set duration is increased, and the detection is finished.
After multiple false alarms occur, characteristic parameters are corrected, the value of the fall model reliability p is equal to 0, parameter correction is carried out, the value of a height change value h & lth + n, a fall acceleration alpha & ltalpha + i & gt, a fall height d & ltd + j & gt, a fall keeping time threshold t & ltt + l & gt is increased, the value of the fall model reliability p is reset to be equal to 1, wherein n, i, j and l respectively represent respective step lengths or set time lengths are prolonged, and then the next round of detection is carried out.
For the correction of the characteristic parameters, a plurality of parameters are corrected at the same time, or only one of the parameters is corrected.
Preferably, for the selection of the initial characteristic parameter, a smaller value is selected to improve the accuracy, and when the determined number of non-tumbling times reaches a certain amount, the value of the characteristic parameter is increased to reduce the misjudgment probability.
Detailed description of the invention
According to the UWB radar-based human body fall detection adaptive system, human body characteristic detection is performed to correct human body fall characteristic parameters, and as shown in figure 2, the UWB radar-based human body fall detection adaptive system comprises the following steps:
a1, setting initial value h of height change0Initial value of acceleration alpha0Initial height value d after falling0Initial value t of tumble holding time0；
A2, setting the initial value of the falling model credibility p as 1;
a3, detecting the detected person in real time, and calculating the characteristic parameters of the detected person;
a4, comparing the detected data with a set value;
a5, judging whether the detected person falls down or not according to the comparison result, if not, turning to A3, and if so, entering the next step;
a6, sending fall information to the detected person;
a7, judging whether the feedback information of the detected person is a fall, if so, turning to A14, otherwise, entering into the room
One step;
a8, p is p-m, and the reliability p value of the falling model is corrected;
a9, starting timing;
a10, when the timing duration is equal to the set timing duration, judging whether the height after falling is less than or equal to the set value, if so, turning to A14, and if not, entering the next step;
a11, judging whether the p value is equal to zero, if not, turning to A13, and if so, entering the next step;
a12, increasing the altitude change value h ═ h + n, or/and increasing the acceleration setpoint α ═ α + i, or ═ r
And increasing the fall retention time period t ═ t + j, or/and decreasing the height after the fall, or/and extending the set time period, turn a 2;
a13, ending the process, and turning to A3;
a14, warning of falling;
wherein m, n, i, j represent the respective step sizes.
Specifically, at the initial value setting, the initial value h of the height change0Calculated from the following formula:
Wherein alpha is0Indicating acceleration at fall, t0Indicating an initial value of the duration of fall holding time, HtallIndicating the height of the human body.
In step A4, the setting value includes setting an initial value h of height change0Initial value of acceleration alpha0Initial height value d after falling0Initial value t of tumble holding time0The initial value and the corrected value of the height change corrected value h, the acceleration corrected value alpha, the height change value d after falling, the falling holding time length corrected value t and the falling model reliability p.
In step a5, when the real-time detection parameters simultaneously satisfy: real-time altitude change is greater than or equal to altitude change set value hsReal-time acceleration is more than or equal to the acceleration set value alpha, and real-time height is less than or equal to the height set value d after fallingsAnd when the real-time falling holding time length is more than or equal to the set value t of the falling holding time length, judging that the falling is carried out.
In step a7, the feedback information of the detected person includes: the detected person replies with voice to confirm the fall, clicks a robot screen to confirm a fall button, and judges the person to fall when no response is given after overtime.
The feedback information of the detected person is that the detected person does not fall, and comprises the following steps: and judging the detected person to be not fallen when the voice of the detected person returns that the person is not fallen or does not need help.
The value range of the reliability p value of the falling model is (0-1), the initial value is 1, which indicates complete credibility, the falling is immediately judged when the model is completely credible, when p <1 indicates incomplete credibility, when a falling monitoring event is generated, time delay confirmation is needed, and the value of the falling characteristic detection condition is corrected and set according to the confirmation result.
When the set time length is reached, and the height change value at the time is more than or equal to the height change set value hsAnd when the detected person is in a falling state, the detected person is judged, and an alarm is given. And the reliability p value of the falling model is 1, and the next falling is immediately judged.
When the set time length is reached, and the height change value at the moment is less than the height change set value hsAnd judging that the falling is mistaken for the report, judging that the falling is not caused, and ending the process.
When the number of false alarms reaches a certain number, the p value will be reduced to 0, and the characteristic parameters are corrected.
In one embodiment of the present application, p is 0 for a set duration, e.g., the set duration is extended to 1 × 1/0.01 for 100 seconds.
The set duration varies with the detection frequency, and decreases when the detection frequency increases, whereas increases when the detection frequency decreases.
In another specific embodiment of the present application, the height change value h +0.1 and the fall acceleration α +0.1 are added, wherein the step size of both characteristic parameters is 0.1.
Detailed description of the invention
The invention discloses a human body falling detection self-adaptive device based on a UWB radar, which is applied to one or two human body falling detection self-adaptive systems in specific embodiments and comprises a radar transmitting and receiving device and a robot device, wherein the radar transmitting and receiving device is used for transmitting and receiving UWB radar waves, calculating according to the time interval between the transmitted radar waves and the received radar waves, comparing with a human body falling characteristic parameter set value, and judging whether a human body falls or not according to a comparison result.
When the human body is detected to fall down, the robot device is controlled to send a confirmation instruction, and the detected person confirms whether the human body falls down or not to form a closed loop; when the detected person confirms that the person falls down, the alarm is given, and when the person confirms that the person does not fall down, the parameters are dynamically corrected, so that the false alarm probability is reduced.
The embodiments of the present invention are preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (11)
1. The utility model provides a human body falls down and detects adaptive system based on UWB radar which characterized in that: the method comprises the following steps:
s1, detecting human body characteristics;
s2, establishing a universal human body falling characteristic library, and setting human body falling characteristic parameters, wherein the human body falling characteristic parameters comprise a height change value h, a falling acceleration alpha, a falling height d, a falling keeping time length t and a falling model reliability p;
s3, establishing a private feature library according to the height of the human body;
s4, detecting the state of the detected person in real time;
s5, judging whether the detected person falls down or not according to the detection result, if not, turning to S4, and if so, entering the next step;
s6, sending tumbling information to the detected person;
s7, receiving feedback information of the detected person;
s8, judging whether the feedback information is a fall or not, if so, turning to S10, and if not, entering the next step;
s9, correcting the characteristic parameters of human body tumble, and turning to S4;
and S10, warning of falling.
2. The human fall detection adaptive system of claim 1, characterized in that: in step S1, the distance between the object and the radar observation point is calculated based on the time interval T between the detection of the radar transmission wave and the detection of the reflection wave reflected from the human body.
3. The human fall detection adaptive system of claim 1, characterized in that: in step S2, a general human body fall characteristic library is established in a dynamic manner, that is, a corresponding initial fall model is set according to the initial installation height of the radar transmitting device and different human body heights.
4. The human fall detection adaptive system of claim 1, characterized in that: in step S2, a threshold value is set for each human body fall characteristic parameter.
5. The human fall detection adaptive system of claim 4, characterized in that: after a fall, the height change value is calculated by the following formula:
Wherein alpha represents the acceleration of the fall, t represents the initial value of the holding time of the fall, HtallIndicating the height of the human body.
6. The human fall detection adaptive system of claim 4, characterized in that: the height after fall value d is calculated according to the following formula:
d＝H-(W×Htall)+q；
wherein H represents the distance between the radar wave transmitting point and the ground; w represents the human shoulder width coefficient, HtallAnd q is an error correction value.
7. The human fall detection adaptive system of claim 1, characterized in that: the method from human body characteristic detection to human body tumble characteristic parameter correction comprises the following steps:
a1, setting initial value h of height change0Initial value of acceleration alpha0Initial height value d after falling0Initial value t of tumble holding time0；
A2, setting the initial value of the falling model credibility p as 1;
a3, detecting the detected person in real time, and calculating the characteristic parameters of the detected person;
a4, comparing the detected data with a set value;
a5, judging whether the detected person falls down or not according to the comparison result, if not, turning to A3, and if so, entering the next step;
a6, sending fall information to the detected person;
a7, judging whether the feedback information of the detected person is a fall, if so, turning to A14, and if not, entering the next step;
a8, p is p-m, and the reliability p value of the falling model is corrected;
a9, starting timing;
a10, when the timing duration is equal to the set timing duration, judging whether the height after falling is less than or equal to the set value, if so, turning to A14, and if not, entering the next step;
a11, judging whether the p value is equal to zero, if not, turning to A13, and if so, entering the next step;
a12, increasing the height change value h-h + n, or/and increasing the acceleration set value alpha-alpha + i, or/and increasing the fall holding time t-t + j, or/and reducing the height after the fall, or/and prolonging the set time, turning to A2;
a13, ending the process, and turning to A3;
a14, warning of falling;
wherein m, n, i, j represent the respective step sizes.
8. The human fall detection adaptive system of claim 7, characterized in that: in step a3, the feedback information of the detected person includes at least one of the detected person replying to confirm the fall, clicking the robot screen to confirm the fall button, and not responding for a set time.
9. The human fall detection adaptive system of claim 7, characterized in that: in step a5, when the real-time detection parameters simultaneously satisfy: real-time altitude change is greater than or equal to altitude change set value hsReal-time acceleration is more than or equal to the acceleration set value alpha, and real-time height is less than or equal to the height set value d after fallingsAnd when the real-time falling holding time length is more than or equal to the set value t of the falling holding time length, judging that the falling is carried out.
10. The human fall detection adaptive system of claim 7, characterized in that: in step a10, the set time length varies with the detection frequency, and when the detection frequency increases, the set time length decreases, whereas when the detection frequency decreases, the set time length increases, and when the fall model confidence level p is 1, the set time length is extended.
11. A human body fall detection self-adaptive device based on UWB radar, which applies the human body fall detection self-adaptive system of any one of claims 1-10, and is characterized in that: the robot comprises a radar transmitting and receiving device and a robot device, wherein the radar transmitting and receiving device is used for transmitting UWB radar waves and calculating and obtaining whether the human body falls down or not according to the time interval of the transmitted and received radar waves; when the human body is detected to fall down, the robot is controlled to send a confirmation instruction, and the detected person confirms whether the human body falls down or not to form a closed loop; when the detected person confirms that the person falls, an alarm is given, and when the person confirms that the person does not fall, the parameters are corrected to reduce false alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910918192.7A CN110703241A (en) | 2019-09-26 | 2019-09-26 | Human body falling detection self-adaptive system and device based on UWB radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910918192.7A CN110703241A (en) | 2019-09-26 | 2019-09-26 | Human body falling detection self-adaptive system and device based on UWB radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110703241A true CN110703241A (en) | 2020-01-17 |
Family
ID=69197522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910918192.7A Pending CN110703241A (en) | 2019-09-26 | 2019-09-26 | Human body falling detection self-adaptive system and device based on UWB radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110703241A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117269957A (en) * | 2023-11-21 | 2023-12-22 | 天津爱仕凯睿科技发展有限公司 | Human body falling detection method and system based on radar detection technology |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130002434A1 (en) * | 2011-06-30 | 2013-01-03 | General Electric Company | Radar based systems and methods for detecting a fallen person |
| CN102982653A (en) * | 2012-11-07 | 2013-03-20 | 中南大学 | Human body falling monitoring method and device based on acceleration and height information |
| CN103577836B (en) * | 2013-09-30 | 2018-01-23 | 吴家宝 | Falling over of human body detection model method for building up and model system |
| CN108806190A (en) * | 2018-06-29 | 2018-11-13 | 张洪平 | A kind of hidden radar tumble alarm method |
| CN108968970A (en) * | 2018-05-24 | 2018-12-11 | 厦门精益远达智能科技有限公司 | A kind of method, apparatus and radar system that Doppler's millimetre-wave radar detection human body is fallen |
| CN109480403A (en) * | 2018-10-12 | 2019-03-19 | 桂林电子科技大学 | A kind of cognition bracelet detection Falls Among Old People and alarm method based on big data |
| CN109765552A (en) * | 2019-02-22 | 2019-05-17 | 弗徕威智能机器人科技（上海）有限公司 | It is a kind of that detection method and system are fallen down based on radar system and robot |
| CN109961058A (en) * | 2019-04-03 | 2019-07-02 | 湖南省顺鸿智能科技有限公司 | A kind of contactless fall detection method and device |
| CN110179471A (en) * | 2019-05-30 | 2019-08-30 | 南方科技大学 | Fall down detection method, device, equipment and storage medium |
-
2019
- 2019-09-26 CN CN201910918192.7A patent/CN110703241A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130002434A1 (en) * | 2011-06-30 | 2013-01-03 | General Electric Company | Radar based systems and methods for detecting a fallen person |
| CN102982653A (en) * | 2012-11-07 | 2013-03-20 | 中南大学 | Human body falling monitoring method and device based on acceleration and height information |
| CN103577836B (en) * | 2013-09-30 | 2018-01-23 | 吴家宝 | Falling over of human body detection model method for building up and model system |
| CN108968970A (en) * | 2018-05-24 | 2018-12-11 | 厦门精益远达智能科技有限公司 | A kind of method, apparatus and radar system that Doppler's millimetre-wave radar detection human body is fallen |
| CN108806190A (en) * | 2018-06-29 | 2018-11-13 | 张洪平 | A kind of hidden radar tumble alarm method |
| CN109480403A (en) * | 2018-10-12 | 2019-03-19 | 桂林电子科技大学 | A kind of cognition bracelet detection Falls Among Old People and alarm method based on big data |
| CN109765552A (en) * | 2019-02-22 | 2019-05-17 | 弗徕威智能机器人科技（上海）有限公司 | It is a kind of that detection method and system are fallen down based on radar system and robot |
| CN109961058A (en) * | 2019-04-03 | 2019-07-02 | 湖南省顺鸿智能科技有限公司 | A kind of contactless fall detection method and device |
| CN110179471A (en) * | 2019-05-30 | 2019-08-30 | 南方科技大学 | Fall down detection method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| BARIS EROL;MOENESS AMIN;ZHICHONG ZHOU;JUN ZHANG: "Range information for reducing fall false alarms in assisted living", 《2016 IEEE RADAR CONFERENCE (RADARCONF)》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117269957A (en) * | 2023-11-21 | 2023-12-22 | 天津爱仕凯睿科技发展有限公司 | Human body falling detection method and system based on radar detection technology |
| CN117269957B (en) * | 2023-11-21 | 2024-02-13 | 天津爱仕凯睿科技发展有限公司 | Human body falling detection method and system based on radar detection technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105662384B (en) | Method and device for monitoring whether human heart rate is normal | |
| US20080258907A1 (en) | Wireless detection and alarm system for monitoring human falls and entries into swimming pools by using three dimensional acceleration and wireless link energy data method and apparatus | |
| US11430323B2 (en) | Detecting device interfering with security device | |
| EP2356639B1 (en) | Method and apparatus for fall detection and alarm | |
| CN104464158B (en) | Fire alarm linkage control method and system | |
| CN111627185A (en) | Fall alarm method and device and fall detection system | |
| CN113034837B (en) | False alarm-prevention smoke sensing detection alarm and alarm control method | |
| CN110703241A (en) | Human body falling detection self-adaptive system and device based on UWB radar | |
| CN108645412A (en) | A kind of adaptive track initiation method of multisensor | |
| EP3418994B1 (en) | System and method for preventing false alarms during alarm sensitivity threshold changes in fire alarm systems | |
| CN113055072B (en) | Method and device for improving communication quality of satellite terminal | |
| CN113947867A (en) | Method, system, electronic device and storage medium for detecting abnormal target behaviors | |
| CN113945915A (en) | Method and device for detecting falling by millimeter wave radar | |
| CN109059991A (en) | Intelligently from mobile device and its method of sensor calibration, computer storage medium | |
| US10033457B2 (en) | Blind spot determination | |
| JPH0916868A (en) | Terminal sensor in monitor system for prevention of disaster | |
| CN104867292A (en) | Intelligent alarm method and device | |
| CN111464388B (en) | Polling frequency self-adaptive communication method, device, equipment and storage medium | |
| US11022707B2 (en) | Method of determining earthquake event and related earthquake detecting system | |
| CN215180009U (en) | Gas monitoring device with humiture is corrected function | |
| CN105959184A (en) | Smart indoor air purification system | |
| WO2019008162A1 (en) | Fall detection system and method | |
| CN111522247B (en) | Abnormality detection method for multiple sensors in intelligent home system | |
| US11043100B2 (en) | Method for detecting fall of a user | |
| CN110524542A (en) | A kind of human-body safety salvage and management system based on robot linkage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |
|
| RJ01 | Rejection of invention patent application after publication |