CN112386248B - Human body falling detection method, device, equipment and computer readable storage medium - Google Patents
Human body falling detection method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112386248B CN112386248B CN201910743335.5A CN201910743335A CN112386248B CN 112386248 B CN112386248 B CN 112386248B CN 201910743335 A CN201910743335 A CN 201910743335A CN 112386248 B CN112386248 B CN 112386248B
- Authority
- CN
- China
- Prior art keywords
- human body
- trunk
- point cloud
- human
- group
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims description 15
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000007621 cluster analysis Methods 0.000 claims abstract description 23
- 230000010365 information processing Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 25
- 239000013598 vector Substances 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012847 principal component analysis method Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
-
- 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
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
- G01S13/874—Combination of several systems for attitude determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
Abstract
The invention discloses a method, a device, equipment and a computer readable storage medium for detecting human body falling, which relate to the technical field of information processing and are used for solving the problem of high misjudgment rate of human body falling monitoring. The method comprises the following steps: acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body; calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk; and detecting whether the monitored human body falls down according to the posture information. The embodiment of the invention can improve the accuracy of monitoring the falling phenomenon of the human body.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, a device, and a computer readable storage medium for detecting a fall of a human body.
Background
At present, the human body falling detection schemes include the following: through setting up alarm device, utilize video monitoring, utilize wearable equipment to detect etc.. However, these methods are not suitable for sudden situations, or involve privacy problems, or the wearable device cannot be worn due to problems such as skin sensitivity, etc., and there are obstacles in practical application, so that the misjudgment rate of monitoring the falling of the human body is high.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a computer readable storage medium for detecting human body falling, which are used for solving the problem of high misjudgment rate of human body falling monitoring.
In a first aspect, an embodiment of the present invention provides a method for detecting a fall of a human body, including:
acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk;
and detecting whether the monitored human body falls down according to the posture information.
The calculating, based on the point cloud group of the human trunk, the posture information of the human trunk in the target time period includes:
based on a principal component analysis method, obtaining physical characteristic parameters of the point cloud group of the human trunk;
determining the extending direction of the human trunk according to the physical characteristic parameters;
and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Wherein, the determining the extending direction of the human body trunk according to the physical characteristic parameter comprises:
calculating the mass center of the human body trunk group according to the physical characteristic parameters;
calculating a covariance matrix according to the centroid;
calculating eigenvalues and eigenvectors of the covariance matrix;
and taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk.
Wherein, the angle between the extending direction and the zenith direction is used as the inclination angle of the human trunk, and the method comprises the following steps:
the angle between the extension direction and zenith direction is calculated using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein the pose information further comprises at least one angular velocity of the human torso;
the calculating the posture information of the human trunk in the target time period further comprises:
acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period;
using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
Wherein, according to the gesture information, detecting whether the monitored human body falls down includes:
detecting that the monitored human body falls when the minimum value in the at least one inclined angle is larger than a first preset value; or alternatively
And detecting that the monitored human body falls when the maximum value of the at least one angular velocity is larger than a second preset value.
The step of obtaining the point cloud data of the monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body comprises the following steps:
acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data;
and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
In a second aspect, an embodiment of the present invention provides a device for detecting a fall of a human body, including:
the first acquisition module is used for acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
the computing module is used for computing the posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, and the posture information at least comprises at least one inclination angle of the human body trunk;
And the detection module is used for detecting whether the monitored human body falls down according to the gesture information.
Wherein the computing module comprises:
the first acquisition submodule is used for acquiring physical characteristic parameters of the point cloud group of the human trunk based on a principal component analysis method;
the first determining submodule is used for determining the extending direction of the human trunk according to the physical characteristic parameters;
and the second determining submodule is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human body trunk.
Wherein the first determination submodule includes:
a first calculation unit for calculating a centroid of the human body trunk group;
a second calculation unit for calculating a covariance matrix based on the centroid;
a third calculation unit for calculating eigenvalues and eigenvectors of the covariance matrix;
a first determining unit, configured to use a direction indicated by a feature vector corresponding to a maximum feature value as an extending direction of the human trunk;
and the second determining unit is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human body trunk.
The second determining unit is specifically configured to calculate an included angle between the extending direction and the zenith direction by using the following formula:
Wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein the pose information further comprises at least one angular velocity of the human torso; the apparatus further comprises: the second acquisition module is used for acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period; a third acquisition module for using the quotient of the obtained difference and the time length between the first moment and the second moment as the angular velocity of the human torso at the first moment.
The detection module is specifically configured to detect that the monitored human body falls when a minimum value in the at least one inclination angle is greater than a first preset value; or detecting that the monitored person falls when the maximum value of the at least one angular velocity is greater than a second preset value.
Wherein, the first acquisition module includes:
the first acquisition sub-module is used for acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment and acquiring a candidate group with the most reflection points from the point cloud data;
And the second acquisition submodule is used for taking the group with the maximum reflection intensity in the candidate groups as the point cloud group of the human trunk.
In a third aspect, an embodiment of the present invention further provides a device for detecting a fall of a human body, including: a collector, a processor, and a detector;
the collector is used for acquiring point cloud data of the monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body;
the processor is used for calculating the posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, and the posture information at least comprises at least one inclination angle of the human body trunk;
and the detector is used for detecting whether the monitored human body falls down according to the gesture information.
Wherein the processor is further configured to:
based on a principal component analysis method, obtaining physical characteristic parameters of the point cloud group of the human trunk;
determining the extending direction of the human trunk according to the physical characteristic parameters;
and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Wherein the processor is further configured to:
Calculating the mass center of the human body trunk group according to the physical characteristic parameters;
calculating a covariance matrix according to the centroid;
calculating eigenvalues and eigenvectors of the covariance matrix;
and taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk.
Wherein the processor is further configured to:
the angle between the extension direction and zenith direction is calculated using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein the pose information further comprises at least one angular velocity of the human torso; wherein the processor is further configured to:
acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period;
using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
Wherein the detector is further configured to:
detecting that the monitored human body falls when the minimum value in the at least one inclination angle is larger than a first preset value; or alternatively
And detecting that the monitored human body falls when the maximum value of the at least one angular velocity is larger than a second preset value.
Wherein, the collector is further used for:
acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data;
and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
In a fourth aspect, an embodiment of the present invention provides an information processing apparatus including: a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor; the processor is configured to read a program in a memory to implement the steps in the method according to the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the method according to the first aspect.
In the embodiment of the invention, clustering analysis is carried out on the obtained point cloud data of the monitored human body to obtain a point cloud group of the human body trunk. Based on the point cloud group of the human body trunk, calculating the posture information of the human body trunk in a target time period, and detecting whether the monitored human body falls down according to the posture information. Because the human body posture information has good stability and better distinguishing capability on falling behaviors and other common misjudgment behaviors, the accuracy of monitoring the falling phenomenon of the human body can be improved by utilizing the scheme of the embodiment of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
Fig. 1 is a flowchart of a method for detecting a fall of a human body according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a cluster analysis result in an embodiment of the invention;
fig. 3 is a second flowchart of a method for detecting a human fall according to an embodiment of the present invention;
fig. 4 is a third flowchart of a method for detecting a fall of a human body according to an embodiment of the present invention;
fig. 5 is a block diagram of a human body fall detection device according to an embodiment of the present invention;
fig. 6 is a second block diagram of the human body fall detection device according to the embodiment of the present invention;
fig. 7 is a third block diagram of the human body fall detection device according to the embodiment of the present invention;
fig. 8 is a block diagram of an information processing apparatus provided by an embodiment of the present invention;
fig. 9 is a system frame diagram provided by an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting a human fall according to an embodiment of the present invention, as shown in fig. 1, including the following steps:
and 101, acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body.
In this step, first, point cloud data of a monitored human body is acquired using a millimeter wave radar device, and a candidate group having the most reflection points is acquired from the point cloud data. And then, taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
When the scheme of the embodiment of the invention is utilized, the millimeter wave radar data with low power consumption does not have identity identification information, so that the privacy of a user can be better protected. Wherein the monitored person may be, for example, a person. The data output by the millimeter wave radar is point cloud data of a human body of a monitored object, and the information of each point comprises [ space three-dimensional information, reflection intensity information and speed information ].
And performing cluster analysis on the point cloud data to divide the point cloud data into a plurality of groups. The cluster analysis may be implemented based on spatial three-dimensional information alone, or may incorporate reflection intensity information or velocity information. In order to improve accuracy, in practical application, clustering analysis can be performed only based on the classification result of the spatial three-dimensional information. The method of cluster analysis can adopt any cluster analysis method.
The torso is the largest reflector in each part of the human body, so its corresponding point cloud group should have two features: (1) the most reflection points and (2) the greatest reflection intensity. Based on the principle, firstly, a candidate group with the most reflection points is obtained from the point cloud data, and then, the group with the greatest reflection intensity in the candidate group is used as the point cloud group of the human body trunk.
Fig. 2 is a schematic diagram of a cluster analysis result in an embodiment of the invention.
Step 102, calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk.
In this step, based on principal component analysis (Principal Components Analysis, PCA), physical characteristic parameters of the point cloud group of the human torso are obtained, and then the extending direction of the human torso is determined from the physical characteristic parameters. And then, taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk. The physical characteristic parameters comprise characteristic vectors and characteristic values of a point cloud group of the human trunk.
In practical application, after the point cloud group of the human trunk is determined, PCA is adopted to obtain the physical characteristic parameters of the point cloud group of the human trunk, and the extending direction of the human trunk is determined from three main directions of the physical characteristic parameters. Then, the included angle between the extending direction of the human trunk and the zenith direction is the inclined angle of the human trunk.
The specific calculation flow is as follows:
(1) A centroid of the human torso group is calculated.
A group of point clouds of a human torso, each point cloud represented as: p (P) i ＝<x i ,y i ,z i >The point cloud group is expressed as: p (P) 1 ，P 2 ，……，P N . The centroid m (the average value of the array calculated in the n-dimensional direction) is calculated as follows:
wherein N represents the number of point clouds in the point cloud group.
(2) And calculating a covariance matrix according to the centroid.
Wherein the covariance matrix C is expressed as:
the covariance matrix C represents the interrelationship between the x, y, z coordinate values. If the three coordinate values are independent of each other, the value of the element on the covariance matrix is 0.
(3) And calculating eigenvalues and eigenvectors of the covariance matrix.
Here, the eigenvalue λ can be solved from |c- λe|=0 1 ，λ 2 ，λ 3 Then the characteristic value of the solution is brought back to solve the corresponding characteristic vector epsilon 1 ，ε 2 ，ε 3 。
(4) And taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk.
The magnitude of the characteristic value indicates the degree of expansion and contraction in the corresponding direction, so the maximum characteristic value max (λ 1 ，λ 2 ，λ 3 ) Corresponding feature vector epsilon x Representing the extension direction of the human torso, while the smaller two eigenvalues correspond to the cross-sectional direction of the human torso.
(5) And taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Feature vector ε x Namely, the main direction is used for calculating the included angle between the main direction and the zenith direction v (0, 1) to obtain the inclination angle of the body, and the formula is as follows:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
And step 103, detecting whether the monitored human body falls down or not according to the gesture information.
Here, the monitored fall of the human body is detected in case that a minimum value of the at least one inclination angle is larger than a first preset value. The first preset value can be set arbitrarily.
Because the human body posture information has good stability and better distinguishing capability on falling behaviors and other common misjudgment behaviors, the accuracy of monitoring the falling phenomenon of the human body can be improved by utilizing the scheme of the embodiment of the invention.
Referring to fig. 3, fig. 3 is a flowchart of a method for detecting a human fall according to an embodiment of the present invention, as shown in fig. 3, including the following steps:
step 301, obtaining point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body.
Step 302, calculating at least one inclination angle of the human body trunk in a target time period based on the point cloud group of the human body trunk.
Wherein steps 301-302 may be referred to the description of steps 101-102.
In the embodiment of the invention, the angular velocity of the human trunk can effectively distinguish falling from lying rest, so that the angular velocity of the human trunk can be adopted for gesture information to further improve the judgment accuracy. Thus, on the basis of the calculation of the at least one inclination angle, the posture information further comprises at least one angular velocity of the human torso. After step 302, the method according to an embodiment of the present invention further comprises:
step 303, obtaining the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period.
Step 304 of using the quotient of the obtained difference and the time length between the first moment and the second moment as the angular velocity of the human torso at the first moment. The time length between the first time and the second time can be arbitrarily set, for example, to 1s.
Specifically, the method for calculating the angular velocity of the human trunk comprises the following steps:
calculating t 1 Inclination angle theta of human trunk at moment 1 Calculate the next time t 2 Inclination angle theta of human trunk 2 Then calculate t based on the next formula 2 Human body trunk angular velocity omega at moment 1 ：
ω 1 ＝(θ 2 -θ 1 )/(t 2 -t 1 )
Wherein the time interval t 2 -t 1 May be set to 1 second.
Step 305, detecting whether the monitored human body falls.
In this embodiment, whether the monitored human body falls is detected based on the posture information.
Specifically, detecting that the monitored human body falls under the condition that the minimum value in the at least one inclined angle is larger than a first preset value; or detecting that the monitored human body falls under the condition that the maximum value of the at least one angular velocity is larger than a second preset value. The first preset value and the second preset value can be set arbitrarily.
In the embodiment of the invention, the local change of the millimeter wave radar data is strong, and the local change of the data can be caused by the instantaneous and fine breathing activity. For example, the signal reflected by the head may have only 1 point, and the source of the signal reflected by the head in two adjacent frames of images may be shifted from the forehead of the first frame to the cheek of the second frame. For the feature that millimeter wave radar data has a large variation, the overall information (more information at more points) should be utilized as much as possible, and the influence of local instability is reduced by utilizing the overall stability. The height information is only based on the height information in the three-dimensional coordinates of the point cloud, and the inclination angle information utilizes the three-dimensional information and the intensity information, so that the three-dimensional information and the intensity information have higher stability. The inclination angle of the human trunk has higher stability, and can more accurately reflect the posture of the human body. In addition, the inclination angle relative height information of the human trunk can effectively distinguish common misjudgment actions such as shoelace tying, sitting and the like, so that the accuracy of falling judgment is effectively improved. In the embodiment of the invention, the monitored human body does not need to wear any equipment, so that the user experience is better. Meanwhile, the embodiment of the invention can automatically identify time and send out an alarm, so that the user does not need to send out help, and the problem that the user loses the help calling capability due to falling is avoided.
On the basis of the embodiment, when the human body falls, prompt information, such as an alarm, can be output. And when the inclination angle of the human trunk obtained at the third moment is smaller than a third preset value, canceling outputting the prompt information, such as canceling an alarm. The third preset value may be set arbitrarily.
Referring to fig. 4, fig. 4 is a flowchart of a method for detecting a human fall according to an embodiment of the present invention. In fig. 4, the human body posture is monitored in real time. When the inclination angle of the human trunk is larger than theta 1 In this case, the falling phenomenon can be initially screened. And then, continuing the subsequent judgment to determine whether the falling phenomenon really occurs.
The falling phenomenon can be determined to occur when any one of the following conditions is satisfied:
(1) A certain period of time t before the current moment 1 In the human body, the maximum value of the angular velocity of the human body trunk is larger than omega 1 ；
(2) A certain period of time t before the current moment 2 In the human body trunk, the minimum value of the inclination angle is larger than theta 2 。
If it is determined that a fall has occurred, an alarm may be issued. Then, when the inclination angle of the human trunk is smaller than theta 3 And when the alarm is canceled.
Referring to fig. 5, fig. 5 is a block diagram of a human body falling detection device according to an embodiment of the present invention, and as shown in fig. 5, the device may include:
The first obtaining module 501 is configured to obtain point cloud data of a monitored human body by using millimeter wave radar equipment, and perform cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk;
a calculating module 502, configured to calculate pose information of the human torso in a target time period based on a point cloud group of the human torso, where the pose information includes at least one inclination angle of the human torso;
and the detection module 503 is configured to detect whether the monitored human body falls according to the gesture information.
Wherein the computing module 502 includes:
the first acquisition submodule is used for acquiring physical characteristic parameters of the point cloud group of the human trunk based on a principal component analysis method; the first determining submodule is used for determining the extending direction of the human trunk according to the physical characteristic parameters; and the second determining submodule is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human body trunk.
Wherein the first determination submodule includes: a first calculation unit for calculating a centroid of the human body trunk group; a second calculation unit for calculating a covariance matrix based on the centroid; a third calculation unit for calculating eigenvalues and eigenvectors of the covariance matrix; a first determining unit, configured to use a direction indicated by a feature vector corresponding to a maximum feature value as an extending direction of the human trunk; and the second determining unit is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human body trunk.
The second determining unit is specifically configured to calculate an included angle between the extending direction and the zenith direction by using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein the pose information further comprises at least one angular velocity of the human torso; as shown in fig. 6, the apparatus further includes: a second obtaining module 504, configured to obtain a difference between the inclination angle of the first time and the inclination angle of the second time in the target period; a third obtaining module 505, configured to use a quotient of the obtained difference and a time length between the first time and the second time as an angular velocity of the human torso at the first time.
The detection module is specifically configured to detect that the monitored human body falls when a minimum value in the at least one inclination angle is greater than a first preset value; or detecting that the monitored person falls when the maximum value of the at least one angular velocity is greater than a second preset value.
Wherein the first obtaining module 501 includes: the first acquisition sub-module is used for acquiring point cloud data of the monitored human body by millimeter wave radar equipment and acquiring a candidate group with the most reflection points from the point cloud data; and the second acquisition submodule is used for taking the group with the maximum reflection intensity in the candidate groups as the point cloud group of the human trunk.
Because the principle of solving the problem of the device is similar to that of the method for detecting the human body falling in the embodiment of the invention, the implementation of the device can be referred to as the implementation of the method, and the implementation principle and the technical effect are similar, and the embodiment is not repeated here.
Referring to fig. 7, fig. 7 is a block diagram of a human body falling detection device according to an embodiment of the present invention, and as shown in fig. 7, the device may include: collector 701, processor 702 and detector 703.
The collector 701 is configured to obtain point cloud data of a monitored human body, and perform cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
the processor 702 is configured to calculate pose information of the human torso in a target time period based on a point cloud group of the human torso, where the pose information includes at least one tilt angle of the human torso;
the detector 703 is configured to detect whether the monitored human body falls according to the gesture information.
The processor 701 is further configured to obtain physical characteristic parameters of the point cloud group of the human torso based on a principal component analysis method; determining the extending direction of the human trunk according to the physical characteristic parameters; and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Wherein the processor 701 is further configured to calculate a centroid of the human torso group; calculating a covariance matrix according to the centroid; calculating eigenvalues and eigenvectors of the covariance matrix; taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk; and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Wherein the processor 701 is further configured to calculate an angle between the extending direction and the zenith direction by using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein, the gesture information further comprises at least one angular velocity of the human torso; the processor 701 is further configured to obtain a difference between the tilt angle at the first time and the tilt angle at the second time in the target time period; using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
Wherein the detector 703 is further configured to detect that the monitored human body falls when the minimum value of the at least one inclination angle is greater than a first preset value; or detecting that the monitored person falls when the maximum value of the at least one angular velocity is greater than a second preset value.
The collector 701 is further configured to obtain point cloud data of the monitored human body by using millimeter wave radar equipment, and obtain a candidate group with the most reflection points from the point cloud data; and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
Because the principle of solving the problem of the device is similar to that of the method for detecting the human body falling in the embodiment of the invention, the implementation of the device can be referred to as the implementation of the method, and the implementation principle and the technical effect are similar, and the embodiment is not repeated here.
As shown in fig. 8, an information processing apparatus of an embodiment of the present invention includes: processor 800, for reading the program in memory 820, performs the following processes:
acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk;
and detecting whether the monitored human body falls down according to the posture information.
A transceiver 810 for receiving and transmitting data under the control of the processor 800.
Wherein in fig. 8, a bus architecture may comprise any number of interconnected buses and bridges, and in particular, one or more processors represented by processor 800 and various circuits of memory represented by memory 820, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. Transceiver 810 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 may store data used by the processor 800 in performing operations.
The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 may store data used by the processor 800 in performing operations.
The processor 800 is further configured to read the computer program, and perform the following steps:
acquiring a candidate group with the most reflection points from the point cloud data;
And taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
Based on a principal component analysis method, obtaining physical characteristic parameters of the point cloud group of the human trunk;
determining the extending direction of the human trunk according to the physical characteristic parameters;
and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
The processor 800 is further configured to read the computer program, and perform the following steps:
calculating the mass center of the human body trunk group;
calculating a covariance matrix according to the centroid;
calculating eigenvalues and eigenvectors of the covariance matrix;
taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk;
and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
The processor 800 is further configured to read the computer program, and perform the following steps:
the angle between the extension direction and zenith direction is calculated using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
The pose information further includes at least one angular velocity of the human torso; the processor 800 is further configured to read the computer program, and perform the following steps:
acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period;
using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
The processor 800 is further configured to read the computer program, and perform the following steps:
detecting that the monitored human body falls when the minimum value in the at least one inclination angle is larger than a first preset value; or alternatively
And detecting that the monitored human body falls when the maximum value of the at least one angular velocity is larger than a second preset value.
The processor 800 is further configured to read the computer program, and perform the following steps:
acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data;
and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
Referring to fig. 9, fig. 9 is a system frame diagram provided by an embodiment of the present invention, as shown in fig. 9, the system may include: a perception module 901, an intelligent analysis module 902, a business management module 903.
The sensing module 901 may be, for example, a low-power consumption millimeter wave radar device, and is configured to obtain point cloud data of a monitored human body.
The intelligent analysis module 902 may include: a human body posture characteristic analysis sub-module and a human body falling judgment sub-module. The human body posture feature analysis sub-module is used for calculating human body posture features based on millimeter wave radar data. And the human body falling judgment sub-module is used for judging the falling state based on the gesture characteristics. In the embodiment of the invention, the human body trunk part and the four limbs part are segmented based on cluster analysis, the human body inclination angle and the angular velocity are calculated by adopting physical characteristic parameters of the human body trunk, and then the falling state is judged based on the information. The intelligent analysis module can be deployed in customized computing equipment, idle computing resources (such as intelligent home gateway) in a home, or a cloud platform, and the analysis result is sent to a service platform.
The service platform module 903 includes: the message forwarding sub-module, the equipment management sub-module and the user management sub-module realize the functions of data management, equipment management, user management and the like. The message forwarding sub-module is used for being responsible for forwarding the message. The result of the data analysis is received from the intelligent analysis module, can be stored into a database through the equipment management submodule, and provides services such as user management, data inquiry, event pushing and the like for the guardian/organization terminal through the user management submodule.
Furthermore, a computer-readable storage medium of an embodiment of the present invention stores a computer program executable by a processor to implement the steps of:
acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk;
and detecting whether the monitored human body falls down according to the posture information.
The calculating, based on the point cloud group of the human trunk, the posture information of the human trunk in the target time period includes:
based on a principal component analysis method, obtaining physical characteristic parameters of the point cloud group of the human trunk;
determining the extending direction of the human trunk according to the physical characteristic parameters;
and taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk.
Wherein, the determining the extending direction of the human body trunk according to the physical characteristic parameter comprises:
calculating the mass center of the human body trunk group according to the physical characteristic parameters;
Calculating a covariance matrix according to the centroid;
calculating eigenvalues and eigenvectors of the covariance matrix;
and taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk.
Wherein, the angle between the extending direction and the zenith direction is used as the inclination angle of the human trunk, and the method comprises the following steps:
the angle between the extension direction and zenith direction is calculated using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
Wherein the pose information further comprises at least one angular velocity of the human torso;
the calculating the posture information of the human trunk in the target time period further comprises:
acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period;
using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
Wherein, according to the gesture information, detecting whether the monitored human body falls down includes:
Detecting that the monitored human body falls when the minimum value in the at least one inclined angle is larger than a first preset value; or alternatively
And detecting that the monitored human body falls when the maximum value of the at least one angular velocity is larger than a second preset value.
The step of obtaining the point cloud data of the monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body comprises the following steps:
acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data;
and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may be physically included separately, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform part of the steps of the transceiving method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (8)
1. A method for detecting a fall of a person, comprising:
acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
calculating posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, wherein the posture information at least comprises at least one inclination angle of the human body trunk;
detecting whether the monitored human body falls down according to the gesture information;
the calculating, based on the point cloud group of the human trunk, the posture information of the human trunk in the target time period includes:
based on a principal component analysis method, obtaining physical characteristic parameters of the point cloud group of the human trunk;
determining the extending direction of the human trunk according to the physical characteristic parameters;
taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk;
wherein, the determining the extending direction of the human body trunk according to the physical characteristic parameter comprises:
calculating the mass center of the human body trunk group according to the physical characteristic parameters;
calculating a covariance matrix according to the centroid;
Calculating eigenvalues and eigenvectors of the covariance matrix;
taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk;
the step of obtaining the point cloud data of the monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body comprises the following steps:
acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data;
and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
2. The method according to claim 1, wherein said setting the angle between the extending direction and the zenith direction as the inclination angle of the human torso comprises:
the angle between the extension direction and zenith direction is calculated using the following formula:
wherein ω represents the included angle, dot represents the point multiplication operation, ε x The feature vector corresponding to the largest feature value is represented, v represents the zenith direction, |epsilon x V represents epsilon respectively x And v.
3. The method of claim 1, wherein the pose information further comprises at least one angular velocity of the human torso;
The calculating the posture information of the human trunk in the target time period further comprises:
acquiring the difference between the inclination angle of the first moment and the inclination angle of the second moment in the target time period;
using the quotient of the obtained difference and the length of time between the first moment and the second moment as the angular velocity of the human torso at the first moment.
4. A method according to claim 3, wherein detecting whether the monitored person falls based on the gesture information comprises:
detecting that the monitored human body falls when the minimum value in the at least one inclination angle is larger than a first preset value; or alternatively
And detecting that the monitored human body falls when the maximum value of the at least one angular velocity is larger than a second preset value.
5. A human fall detection device, comprising:
the first acquisition module is used for acquiring point cloud data of a monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of a human body trunk of the monitored human body;
the computing module is used for computing the posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, and the posture information at least comprises at least one inclination angle of the human body trunk;
The detection module is used for detecting whether the monitored human body falls down according to the gesture information;
wherein the computing module comprises:
the first acquisition submodule is used for acquiring physical characteristic parameters of the point cloud group of the human trunk based on a principal component analysis method; the first determining submodule is used for determining the extending direction of the human trunk according to the physical characteristic parameters; the second determining submodule is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk;
wherein the first determination submodule includes: a first calculation unit for calculating a centroid of the human body trunk group; a second calculation unit for calculating a covariance matrix based on the centroid; a third calculation unit for calculating eigenvalues and eigenvectors of the covariance matrix; a first determining unit, configured to use a direction indicated by a feature vector corresponding to a maximum feature value as an extending direction of the human trunk; the second determining unit is used for taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk;
wherein, the first acquisition module includes: the first acquisition sub-module is used for acquiring point cloud data of the monitored human body by millimeter wave radar equipment and acquiring a candidate group with the most reflection points from the point cloud data; and the second acquisition submodule is used for taking the group with the maximum reflection intensity in the candidate groups as the point cloud group of the human trunk.
6. A human fall detection device, comprising: a collector, a processor, and a detector;
the collector is used for acquiring point cloud data of the monitored human body, and performing cluster analysis on the point cloud data to obtain a point cloud group of the human body trunk of the monitored human body;
the processor is used for calculating the posture information of the human body trunk in a target time period based on the point cloud group of the human body trunk, and the posture information at least comprises at least one inclination angle of the human body trunk;
the detector is used for detecting whether the monitored human body falls down according to the gesture information;
the processor is further used for obtaining physical characteristic parameters of the point cloud group of the human trunk based on a principal component analysis method; determining the extending direction of the human trunk according to the physical characteristic parameters; taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk;
wherein the processor is further configured to calculate a centroid of the human torso group; calculating a covariance matrix according to the centroid; calculating eigenvalues and eigenvectors of the covariance matrix; taking the direction indicated by the feature vector corresponding to the maximum feature value as the extending direction of the human trunk; taking the included angle between the extending direction and the zenith direction as the inclination angle of the human trunk;
The collector is used for acquiring point cloud data of the monitored human body by utilizing millimeter wave radar equipment, and acquiring a candidate group with the most reflection points from the point cloud data; and taking the group with the maximum reflection intensity in the candidate groups as a point cloud group of the human trunk.
7. An information processing apparatus comprising: a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor; it is characterized in that the method comprises the steps of,
the processor being configured to read a program in a memory to implement the steps in the method according to any one of claims 1 to 4.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910743335.5A CN112386248B (en) | 2019-08-13 | 2019-08-13 | Human body falling detection method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910743335.5A CN112386248B (en) | 2019-08-13 | 2019-08-13 | Human body falling detection method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112386248A CN112386248A (en) | 2021-02-23 |
| CN112386248B true CN112386248B (en) | 2024-01-23 |
Family
ID=74602515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910743335.5A Active CN112386248B (en) | 2019-08-13 | 2019-08-13 | Human body falling detection method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112386248B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI774444B (en) * | 2021-06-28 | 2022-08-11 | 萬旭電業股份有限公司 | Millimeter wave radar apparatus detecting fall posture |
| US20230008729A1 (en) * | 2021-07-11 | 2023-01-12 | Wanshih Electronic Co., Ltd. | Millimeter wave radar apparatus determining fall posture |
| CN114942434B (en) * | 2022-04-25 | 2024-02-02 | 四川八维九章科技有限公司 | Fall gesture recognition method and system based on millimeter wave Lei Dadian cloud |
| CN114720977B (en) * | 2022-06-10 | 2022-09-20 | 长沙莫之比智能科技有限公司 | Object falling detection method and device, millimeter wave radar and storage medium |
| CN116338684A (en) * | 2023-05-29 | 2023-06-27 | 长沙莫之比智能科技有限公司 | Human body falling detection method and system based on millimeter wave radar and deep learning |
| CN117173793B (en) * | 2023-11-02 | 2024-03-01 | 浙江大华技术股份有限公司 | Target gesture detection method, computer device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007151948A (en) * | 2005-12-07 | 2007-06-21 | Kansai Electric Power Co Inc:The | Method and device for determining falling down |
| CN105979203A (en) * | 2016-04-29 | 2016-09-28 | 中国石油大学(北京) | Multi-camera cooperative monitoring method and device |
| CN113076781A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信有限公司研究院 | Method, device and equipment for detecting falling and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4749907B2 (en) * | 2006-03-27 | 2011-08-17 | Ｏｋｉセミコンダクタ株式会社 | Fall detection device |
| US10293205B2 (en) * | 2014-01-27 | 2019-05-21 | The Regents Of The University Of Michigan | IMU system for assessing head and torso orientation during physical motion |
| WO2019070570A1 (en) * | 2017-10-06 | 2019-04-11 | Tellus You Care, Inc. | Non-contact activity sensing network for elderly care |
-
2019
- 2019-08-13 CN CN201910743335.5A patent/CN112386248B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007151948A (en) * | 2005-12-07 | 2007-06-21 | Kansai Electric Power Co Inc:The | Method and device for determining falling down |
| CN105979203A (en) * | 2016-04-29 | 2016-09-28 | 中国石油大学(北京) | Multi-camera cooperative monitoring method and device |
| CN113076781A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信有限公司研究院 | Method, device and equipment for detecting falling and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112386248A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112386248B (en) | Human body falling detection method, device, equipment and computer readable storage medium | |
| US11308334B2 (en) | Method and apparatus for integration of detected object identifiers and semantic scene graph networks for captured visual scene behavior estimation | |
| JP2020071226A (en) | Fall detection method and apparatus | |
| EP3215914B1 (en) | Improved calibration for eye tracking systems | |
| Chandra et al. | IoT based fall detection and ambient assisted system for the elderly | |
| US8705795B2 (en) | Information processing apparatus, information processing method, and program | |
| JP5693162B2 (en) | Image processing system, imaging apparatus, image processing apparatus, control method therefor, and program | |
| EP2923304A1 (en) | Method and system for counting people using depth sensor | |
| Sun et al. | Privacy-preserving fall detection with deep learning on mmWave radar signal | |
| US20220156959A1 (en) | Image processing device, image processing method, and recording medium in which program is stored | |
| JP6977787B2 (en) | Sensor information integration system, sensor information integration method and program | |
| JP2019087231A (en) | System and method for tracking face position and alerting user | |
| CN110362492A (en) | Intelligent algorithm test method, device, server, terminal and storage medium | |
| Chen et al. | SWIM: Speed-aware WiFi-based passive indoor localization for mobile ship environment | |
| CN105593903A (en) | Living body determination devices and methods | |
| Yang et al. | Perceiving the slightest tag motion beyond localization | |
| US20140086448A1 (en) | Appearance Model Based Automatic Detection in Sensor Images | |
| US10878228B2 (en) | Position estimation system | |
| CN112863124A (en) | Fall detection and assistance | |
| US11887331B2 (en) | Information processing apparatus, control method, and non-transitory storage medium | |
| JP2018142137A (en) | Information processing device, information processing method and program | |
| KR101886856B1 (en) | System and method for data combining based on result of non-rigid object tracking on multi-sensor seeker | |
| Brent et al. | Cooperative place recognition in robotic swarms | |
| JP7483140B2 (en) | Image processing system, imaging device, terminal device, and image processing method | |
| JP7218416B2 (en) | Information processing device, information processing system, information processing method and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |