CN115359624A - Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection - Google Patents
Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection Download PDFInfo
- Publication number
- CN115359624A CN115359624A CN202211301350.2A CN202211301350A CN115359624A CN 115359624 A CN115359624 A CN 115359624A CN 202211301350 A CN202211301350 A CN 202211301350A CN 115359624 A CN115359624 A CN 115359624A
- Authority
- CN
- China
- Prior art keywords
- detection
- retention
- state
- falling
- entering
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 144
- 230000014759 maintenance of location Effects 0.000 claims abstract description 74
- 238000006073 displacement reaction Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 5
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 abstract description 18
- 230000008447 perception Effects 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0461—Sensor means for detecting integrated or attached to an item closely associated with the person but not worn by the person, e.g. chair, walking stick, bed sensor
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0492—Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection, which relates to the technical field of millimeter wave radar application and human behavior perception, and comprises the following steps: according to the point cloud data returned by the millimeter wave radar, state quantity information such as the number of current targets, the height of the mass center of the targets, the speed, the displacement and the like is obtained after processing, the state of the personnel is judged at present, and an alarm is given when falling behaviors and detention behaviors are detected. The priority of falling detection is higher than that of retention detection, and retention judgment is performed again under the condition that falling judgment is not met. If the retention detection process satisfies the fall discrimination condition, the retention detection is released and the fall detection is started. In addition, the breathing heartbeat information returned by the radar module is combined to carry out auxiliary judgment, and the human body target and other interference targets are distinguished according to the vital signs.
Description
Technical Field
The invention relates to the technical field of millimeter wave radar application and human behavior perception, in particular to a millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection.
Background
With the aggravation of the aging degree of China, the problem of nursing the aged has become an important social problem. Falls, as the second most significant factor in mortality in accidental and unintended injuries, are a major problem facing elderly care. The old people often cannot be found in time after falling down, so that the old people are easy to have certain influence on the physical health and mental state. The toilet is used as a place where falling easily occurs, and meanwhile, the toilet has strong privacy, so that the toilet is easy to fall unconsciously.
The existing common methods for detecting falls include wearable devices, cameras, wifi, millimeter wave radar, and the like. The wearable device is low in cost, but the sensors are required to be worn on key parts of a human body, so that the wearable device is inconvenient to use and is easy to forget to wear; the detection precision based on the camera is high, the non-contact detection is realized, the calculation cost is high, and the privacy is exposed; the method based on wifi is low in cost and easy to deploy, but is easily interfered by other external signals; the method based on the millimeter wave radar belongs to non-contact detection, and has the advantages of no privacy disclosure, high transmission rate, strong anti-interference performance, high detection precision and lower cost.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection, which can detect fall behaviors and retention behaviors in a detection area and give an alarm when an abnormal state occurs. The specific method comprises the following steps:
and according to the point cloud returned by the millimeter wave radar, state quantity information such as the number of the current targets, the height of the mass center of the targets, the speed, the displacement and the like is obtained after processing and is used as a judgment condition of the personnel state. The judgment conditions of the falling state are that the number of people is equal to 1, the height of the mass center is less than 0.5m, and the speed is less than 0.8m/s, and the judgment conditions of the staying state are that the number of people is equal to 1, the speed is less than 0.8m/s, and the displacement from the initial position is less than 1m.
The priority of falling detection is higher than that of retention detection, and retention judgment is performed under the condition that falling judgment is not met; and if the retention detection process meets the falling judgment condition, releasing the retention detection and starting falling detection. In addition, the breathing heartbeat information returned by the radar module is combined to carry out auxiliary judgment, and the human body target and other interference targets are distinguished according to the vital signs.
The fall behavior detection process comprises the following steps:
firstly, judging whether the judgment condition of falling is met, and if so, judging whether the falling detection stage is entered for the first time.
If the current frame is the first frame entering the falling detection, recording the starting time of the falling detection, and then entering the judgment of the next frame; if the previous frame has entered fall detection, it is determined whether the time to enter the fall detection state exceeds 20s.
If the time for entering the falling detection state is less than 20s, directly returning to enter the judgment of the next frame; if the current state of entering fall detection has exceeded 20s, the fall state is entered. Since the priority of the fall detection is higher than that of the stay detection, the stay detection is released when the fall state is confirmed.
And judging whether the current falling detection time exceeds 30s, if so, sending a falling alarm and entering the judgment of the next frame, and if not, directly entering the next frame.
The retention behavior detection process is as follows:
firstly, judging whether the number of people is equal to 1 and the speed is less than 0.8m/s, and if the number of people is not equal to 1, removing the retention detection; if the conditions are met, whether the detention detection stage is entered for the first time is judged.
If the current frame is the first frame entering the retention detection, recording the starting time and the initial position of the retention detection, and then entering the next frame; if the previous frame has entered the retention detection, it is determined whether the displacement between the current position and the initial position is greater than 1m.
If the displacement is larger than 1m, the retention detection is removed and the next frame is directly entered; and if the displacement is not more than 1m, judging whether the time of entering the detention detection state currently exceeds 30min.
If the time for entering the retention detection state exceeds 30min, entering the retention state, sending a retention alarm, and entering the next frame judgment; otherwise, the next frame is directly entered.
The beneficial effects of the invention are as follows:
1. the invention is used for detecting the falling behavior and the retention behavior based on the millimeter wave radar, and has the advantages of non-contact detection, no privacy disclosure, high transmission rate, strong anti-interference performance, high detection precision and lower cost.
2. And judging the current state of the target based on state quantity analysis, and the method is a detection mode based on results. Because the invention mainly detects the behavior that people can not climb up again within a period of time after falling over the ground, the invention does not need to care about the falling process, but extracts the state quantity of the fallen human body for judgment, avoids the problem that the feature setting is difficult to cover different falling actions when detecting the falling process, and has smaller calculated quantity.
3. Except for speed, displacement cooperative judgment with an initial position is introduced during stagnation detection, so that the condition of slow movement can be effectively screened out, and misinformation is avoided.
4. Setting the priority of falling detection to be higher than that of retention detection, entering the judgment of retention again under the condition that the falling judgment is not satisfied, and if the condition that the falling judgment is satisfied in the retention detection process, releasing the retention detection and starting the falling detection. The condition that the consequence caused by falling behavior is generally far greater than that of retention behavior is considered, and the condition that the falling report is missed due to overlong retention time threshold can be effectively avoided.
5. And the breathing heartbeat information returned by the radar module is combined to carry out auxiliary judgment, and the human body target and other interference targets are distinguished according to the vital signs, so that misinformation is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is an overall flow chart of the detection algorithm of the present invention.
Fig. 2 is a flow chart of fall detection according to the present invention.
Fig. 3 is a flow chart of retention behavior detection according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
the invention provides a millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection, and the overall flow chart of the algorithm is shown in figure 1.
Firstly, initializing parameters, and then processing point cloud data returned by the millimeter wave radar to obtain state quantity information such as the number of current targets, the height of the mass center of the targets, the speed, the displacement and the like as personnel state discrimination conditions. The tumble state is determined by the number of people being 1, the height of the center of mass being less than 0.5m, and the velocity being less than 0.8m/s, and the stagnation state is determined by the number of people being 1, the velocity being less than 0.8m/s, and the displacement from the initial position being less than 1m. The priority of falling detection is higher than that of retention detection, and retention judgment is performed under the condition that falling judgment is not met; if the retention detection process satisfies the fall discrimination condition, the retention detection is released and the fall detection is started. And if the maintaining time meeting the falling or detention judging condition exceeds a set time threshold, giving an alarm.
In the embodiment of the invention, flags are respectively set for fall detection and detention detection, wherein fallDetSign represents a fall detection state, fallDetSign = 0 represents that the current state is a tracking state, fallDetSign = 1 represents that the current state of fall detection is entered, and fallDetSign = 2 represents that the current time of fall detection exceeds a preset threshold value, and the current state is judged to be a fall state; similarly, the stayDetSign indicates a retention detection state, and when stayDetSign = 0, it indicates that the current state is the tracking state, when stayDetSign = 1, it indicates that the current state is the retention detection state, and when stayDetSign = 2, it indicates that the current time for entering the retention detection exceeds a preset threshold, and it is determined that the state is the retention state.
A fall behavior detection flow is shown in fig. 2, and the specific steps are as follows:
step S1, in an initialization stage, setting both the fallDetSign and the stayDetSign as 0;
s2, judging whether a judgment condition for falling is met, and if so, judging whether to enter a falling detection stage for the first time according to the value of fallDetSign;
step S301, if fallDetSign = 0, it is indicated that the frame is the first frame entering the fall detection, at this time, the value of fallDetSign is set to 1, the start time of the fall detection is recorded, and then the judgment of the next frame is entered;
step S302, if fallDetSign is not equal to 0, the previous frame is indicated to have entered the fall detection, and whether the time for entering the fall detection state exceeds 20S is judged at the moment;
step S401, if the time for entering the falling detection state is less than 20S, directly returning to enter the judgment of the next frame;
step S402, if the time for entering the falling detection state currently exceeds 20S, the falling state is entered, and the fallDetSign is set to be 2. Because the priority of the falling detection is higher than that of the retention detection, if the falling state is confirmed, the retention detection is released, and the stayDetSign is set to be 0;
and S5, judging whether the current time for falling detection exceeds 30S, if so, sending a falling alarm and entering the judgment of the next frame, otherwise, directly entering the next frame.
The retention behavior detection flowchart is shown in fig. 3, and the specific steps are as follows:
step S1, judging whether the number of people is equal to 1 and the speed is less than 0.8 m/S;
step S201, if the condition of step S1 is not satisfied, making stayDetSign = 0, and canceling the retention detection;
step S202, if the condition is met, judging whether to enter a retention detection stage for the first time according to the value of the stayDetSign;
step S301, if the stayDetSign = 0, it indicates that the frame is the first frame entering the retention detection, at this time, the stayDetSign is set to 1, the start time and the initial position of the retention detection are recorded, and then the next frame is entered;
step S302, if the stayDetSign is not equal to 0, the previous frame is proved to have entered into the retention detection, and at this time, whether the displacement between the current position and the initial position is larger than 1m or not is judged;
step S401, if the displacement is larger than 1m, making stayDetSign = 0, releasing the retention detection and directly entering the next frame;
step S402, if the displacement is not more than 1m, judging whether the time of entering the retention detection state currently exceeds 30min;
step S5, if the time for entering the retention detection state exceeds 30min, entering the retention state, setting the stayDetSign to be 2, sending a retention alarm, and entering the next frame for judgment; otherwise, the next frame is directly entered.
In an embodiment of the present invention, the displacement is calculated as follows: setting an initial Position 0: (x 0 , y 0 , z 0 ) Current Position (Position) ((ii))x, y, z) Calculated by the method of Euclidean distance, displacement =。
The invention utilizes the millimeter wave radar to detect the falling and detention behaviors, and has the advantages of non-contact, no privacy disclosure, high transmission rate, strong anti-interference performance, high detection precision and lower cost. By adopting a detection mode based on results, the falling process does not need to be concerned, but the state quantity of the fallen human body is extracted for judgment, so that the problem that different falling actions are difficult to cover by setting features during the falling process is avoided, and the calculated quantity is reduced. The displacement information of the initial position is cooperatively judged during the retention detection, so that the condition of slow movement can be effectively screened out, and misinformation is avoided. The falling detection priority is set to be higher than the retention detection priority, the effect caused by falling is considered to be generally far greater than the retention behavior, and the condition that the falling is missed due to the fact that the retention time threshold is too long can be effectively avoided. In addition, the breathing heartbeat information returned by the millimeter wave radar is combined to perform auxiliary judgment, a human body target and other interference targets are distinguished according to the vital signs, and false alarm is reduced.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (4)
1. A millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection is characterized in that whether a fall behavior and a detention behavior occur in a detection area or not is judged according to the state quantity analysis, and an alarm is given when an abnormal state occurs;
setting marks for fall detection and retention detection respectively, wherein fallDetSign represents a fall detection state, when fallDetSign = 0, the fall detection state is currently indicated, when fallDetSign = 1, the fall detection state is currently entered, and when fallDetSign = 2, the fall detection time currently exceeds a preset threshold value, the fall detection state is judged; similarly, the stayDetSign represents a retention detection state, when the stayDetSign = 0, the current state is a tracking state, when the stayDetSign = 1, the current state is a retention detection state, when the stayDetSign = 2, the current time for entering the retention detection exceeds a preset threshold value, and the state is judged to be a retention state;
the fall behavior detection process comprises the following specific steps:
step S1, in an initialization stage, setting both the fallDetSign and the stayDetSign as 0;
s2, judging whether a judgment condition for falling is met, and if so, judging whether to enter a falling detection stage for the first time according to the value of fallDetSign;
step S301, if fallDetSign = 0, it is indicated that the current frame is the first frame entering the fall detection, at this time, the value of fallDetSign is set to 1, the start time of the fall detection is recorded, and then the judgment of the next frame is entered;
step S302, if fallDetSign is not equal to 0, the previous frame is indicated to have entered the falling detection, and at this time, whether the time for entering the falling detection state exceeds 20S is judged;
step S401, if the time for entering the falling detection state is less than 20S, directly returning to enter the judgment of the next frame;
step S402, if the time for entering the falling detection state currently exceeds 20S, entering the falling state, and setting the fallDetSign to be 2; because the priority of the falling detection is higher than that of the retention detection, if the falling state is confirmed, the retention detection is released, and the stayDetSign is set to be 0;
s5, judging whether the time for entering falling detection currently exceeds 30S, if so, sending a falling alarm and entering the judgment of the next frame, otherwise, directly entering the next frame;
the specific steps of the retention behavior detection process are as follows:
step S1, judging whether the number of people is equal to 1 and the speed is less than 0.8 m/S;
step S201, if the condition of step S1 is not satisfied, making stayDetSign = 0, and canceling the retention detection;
step S202, if the condition is met, judging whether to enter a retention detection stage for the first time according to the value of the stayDetSign;
step S301, if the stayDetSign = 0, it is indicated that the frame is the first frame entering the retention detection, at this time, the stayDetSign is set to 1, the start time and the initial position of the retention detection are recorded, and then the next frame is entered;
step S302, if the stayDetSign is not equal to 0, the previous frame is indicated to enter the retention detection, and at the moment, whether the displacement between the current position and the initial position is more than 1m is judged;
step S401, if the displacement is larger than 1m, making the stayDetSign = 0, removing the retention detection and directly entering the next frame;
step S402, if the displacement is not more than 1m, judging whether the time of entering the retention detection state currently exceeds 30min;
step S5, if the time for entering the retention detection state exceeds 30min, entering the retention state, setting the stayDetSign to be 2, sending a retention alarm, and entering the next frame for judgment; otherwise, the next frame is directly entered.
2. The millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection as claimed in claim 1, wherein the current number of targets, the height of the center of mass of the targets, the speed and the displacement state quantity are obtained as personnel state discrimination conditions after processing according to the point cloud returned by the millimeter wave radar.
3. The millimeter wave radar fall and retention behavior detection method based on state quantity analysis as claimed in claim 2, wherein: the judgment conditions of the falling state are that the number of people is equal to 1, the height of the mass center is less than 0.5m, and the speed is less than 0.8m/s, and the judgment conditions of the staying state are that the number of people is equal to 1, the speed is less than 0.8m/s, and the displacement from the initial position is less than 1m; the priority of falling detection is higher than that of retention detection, and retention judgment is performed under the condition that falling judgment is not met; and if the retention detection process meets the falling judgment condition, releasing the retention detection and starting falling detection.
4. The millimeter wave radar fall detection algorithm based on state quantity analysis and vital sign detection as claimed in claim 1, wherein the vital sign detection is performed using respiration heartbeat data to distinguish human body from other interfering targets.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211301350.2A CN115359624A (en) | 2022-10-24 | 2022-10-24 | Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211301350.2A CN115359624A (en) | 2022-10-24 | 2022-10-24 | Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115359624A true CN115359624A (en) | 2022-11-18 |
Family
ID=84008487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211301350.2A Pending CN115359624A (en) | 2022-10-24 | 2022-10-24 | Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115359624A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740621A (en) * | 2016-01-29 | 2016-07-06 | 江阴中科今朝科技有限公司 | Moving monitoring and intelligent aged nursing health cloud platform of human body behavior data |
CN111166342A (en) * | 2020-01-07 | 2020-05-19 | 四川宇然智荟科技有限公司 | Millimeter wave radar and camera fused fall detection device and detection method thereof |
CN112669570A (en) * | 2021-01-06 | 2021-04-16 | 常州百芝龙智慧科技有限公司 | Habit-based self-learning whole-house abnormity monitoring equipment |
CN115089135A (en) * | 2022-04-25 | 2022-09-23 | 无锡博奥玛雅医学科技有限公司 | Millimeter wave radar-based elderly health state detection method and system |
-
2022
- 2022-10-24 CN CN202211301350.2A patent/CN115359624A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740621A (en) * | 2016-01-29 | 2016-07-06 | 江阴中科今朝科技有限公司 | Moving monitoring and intelligent aged nursing health cloud platform of human body behavior data |
CN111166342A (en) * | 2020-01-07 | 2020-05-19 | 四川宇然智荟科技有限公司 | Millimeter wave radar and camera fused fall detection device and detection method thereof |
CN112669570A (en) * | 2021-01-06 | 2021-04-16 | 常州百芝龙智慧科技有限公司 | Habit-based self-learning whole-house abnormity monitoring equipment |
CN115089135A (en) * | 2022-04-25 | 2022-09-23 | 无锡博奥玛雅医学科技有限公司 | Millimeter wave radar-based elderly health state detection method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111887861B (en) | Millimeter wave radar-based integrated monitoring method for indoor personnel safety | |
CN110807377B (en) | Target tracking and intrusion detection method, device and storage medium | |
JP6762344B2 (en) | Methods and systems to track the position of the face and alert the user | |
JP5301973B2 (en) | Crime prevention device and program | |
JP2007272488A (en) | Image processor, monitor camera and image monitoring system | |
CN112623919B (en) | Escalator intelligent monitoring management system based on computer vision | |
Khawandi et al. | Implementation of a monitoring system for fall detection in elderly healthcare | |
Wen et al. | We help you watch your steps: Unobtrusive alertness system for pedestrian mobile phone users | |
CN113947867B (en) | Method, system, electronic device and storage medium for detecting abnormal target behavior | |
CN114446026B (en) | Article forgetting reminding method, corresponding electronic equipment and device | |
CN114469076A (en) | Identity feature fused old solitary people falling identification method and system | |
CN112327288A (en) | Radar human body action recognition method and device, electronic equipment and storage medium | |
CN107105092A (en) | A kind of human body tumble recognition methods based on dynamic time warping | |
KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
CN110633652A (en) | Unexpected situation determination method and device and electronic equipment | |
CN114469074A (en) | Fall early warning method, system, equipment and computer storage medium | |
CN114333235A (en) | Human body multi-feature fusion falling detection method | |
CN115359624A (en) | Millimeter wave radar fall detection algorithm based on state quantity analysis and sign detection | |
CN107944346B (en) | Abnormal condition monitoring method and monitoring equipment based on image processing | |
CN113793475A (en) | System and method for detecting falling of old people in key area | |
CN109199357B (en) | Help seeking method based on wearable device, wearable device and storage medium | |
CN114121270A (en) | Disease risk grade prediction method and device | |
CN113671489B (en) | State reminding method and device, electronic equipment and computer readable storage medium | |
CN115204240A (en) | Fall detection method and device based on millimeter wave radar and FPGA | |
CN112447023A (en) | Abnormal condition reminding method and device and storage device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221118 |