CN114942434A - Fall attitude identification method and system based on millimeter wave radar point cloud - Google Patents
Fall attitude identification method and system based on millimeter wave radar point cloud Download PDFInfo
- Publication number
- CN114942434A CN114942434A CN202210441714.0A CN202210441714A CN114942434A CN 114942434 A CN114942434 A CN 114942434A CN 202210441714 A CN202210441714 A CN 202210441714A CN 114942434 A CN114942434 A CN 114942434A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- millimeter wave
- wave radar
- target
- person
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000005484 gravity Effects 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 230000036544 posture Effects 0.000 abstract description 25
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000009434 installation Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 208000012260 Accidental injury Diseases 0.000 description 1
- 208000001132 Osteoporosis Diseases 0.000 description 1
- 206010034719 Personality change Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/411—Identification of targets based on measurements of radar reflectivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The invention discloses a method and a system for recognizing falling postures based on millimeter wave radar point clouds, which are characterized in that a target effective point cloud set is obtained by collecting and preprocessing millimeter wave radar point clouds, target point cloud data in the target effective point cloud set are converted into spatial position coordinates of a person to be detected, a three-dimensional Cartesian coordinate system is established according to the spatial position coordinates of the person to be detected, and the barycentric coordinates of the target point cloud data in the target effective point cloud set are calculated by combining the three-dimensional Cartesian coordinate system; identifying the current falling posture of the person to be detected according to the gravity center coordinates; the invention combines the millimeter wave radar technology, furthest ensures the privacy and safety of the person to be detected on the premise of ensuring the accuracy and real-time property of the falling posture identification, and effectively solves the problems of low privacy, low stability, low accuracy, low comfort and the like of the existing falling detection method.
Description
Technical Field
The invention relates to the technical field of fall detection, in particular to a fall attitude identification method and system based on millimeter wave radar point cloud.
Background
The fall is the fourth leading cause of our country's death by accidental injury, and for the elderly over 65 years old, falls are the first and are very common in the elderly population. China has entered the aging society, 1.5 hundred million old people aged 65 years and over are available, and 30-40% of old people aged 65 years have experience of falling down. With the increase of age, most old people have the phenomena of osteoporosis and brittle bones, and if the old people fall down and are not cured in time, the consequences are disastrous. Therefore, the need for a reliable early warning method for the fall of the old people becomes urgent.
In the related art, there are a human body fall detection system based on visual identification, a system for acquiring channel state information CSI to identify human body behaviors and fall detection based on WIFI equipment, and a method based on wearable equipment and sensors, but the fall detection systems all have defects of different degrees: the privacy is not guaranteed, the method is easily influenced by environmental factors, the accuracy is not high, and the comfort is low.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method and a system for recognizing falling postures based on millimeter wave radar point cloud.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
on one hand, the method for recognizing the falling attitude based on the millimeter wave radar point cloud comprises the following steps:
s1, collecting millimeter wave radar point clouds and preprocessing the millimeter wave radar point clouds to obtain a target effective point cloud set;
s2, converting the target point cloud data in the target effective point cloud set into spatial position coordinates of a person to be detected, and constructing a three-dimensional Cartesian coordinate system according to the spatial position coordinates of the person to be detected;
s3, calculating the barycentric coordinates of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
and S4, identifying the current falling posture of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
Preferably, step S1 specifically includes the following sub-steps:
s11, collecting the millimeter wave radar point cloud, judging whether frame data are missing in the millimeter wave radar point cloud or not, if so, filling the missing data with data, and entering the step S12; otherwise, go to step S12;
s12, judging whether the number of point clouds in each frame of data of the millimeter wave radar point clouds meets the preset point cloud detection number, and fusing not less than one frame of millimeter wave radar point cloud data to obtain a millimeter wave radar point cloud data set if the number of point clouds in each frame of data of the millimeter wave radar point clouds meets the preset point cloud detection number; otherwise, returning to the step S11;
and S13, clustering the millimeter wave radar point cloud data set by using a density-based noise application space clustering method to obtain a target effective point cloud set.
Preferably, step S13 specifically includes the following sub-steps:
a1, calculating the Euclidean distance between each point cloud and other point clouds in the millimeter wave radar point cloud data set, wherein the calculation formula is as follows:
wherein dist (.) is Euclidean distance, X is millimeter wave radar point cloud data set, and Y is the ith point X in the millimeter wave radar point cloud data set i Subset of (a), y i For the ith data in subset Y, N p The number of point clouds in each frame of millimeter wave radar point cloud data, N is the fused millimeter wave radar point cloud data, (n.N) p ) The total number of the target point clouds is obtained;
a2, constructing a k-distance set of each point cloud in the millimeter wave radar point cloud data set according to the Euclidean distance;
a3, constructing a k-distance curve graph according to the k-distance set of each point cloud, and determining the radius of a neighborhood by a curve inflection point;
a4, determining the number of each point in the millimeter wave radar point cloud data set in the neighborhood radius, calculating the expectation of each number, and taking the expectation as the optimal value of the number of data points in the neighborhood radius in the cluster to obtain a target effective point cloud set, wherein the expected calculation formula is represented as:
wherein p is i MinPts is the mathematical expectation for the number of points in the neighborhood radius ε of the ith data.
Preferably, step S2 is specifically:
converting each point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be measured according to a mapping relation from a spatial polar coordinate to a standard spatial coordinate, and constructing a three-dimensional Cartesian coordinate system by taking a millimeter wave radar device as a coordinate origin according to the spatial position coordinate of the person to be measured, wherein the mapping relation from the spatial polar coordinate to the standard spatial coordinate is expressed as follows:
wherein f is a mapping relation;
is emptyInter-polar coordinates, (x, y, z) are standard spatial coordinates, cos (.) is a cosine function, sin (.) is a sine function, and s is a radial distance.
Preferably, step S4 specifically includes the following substeps:
s41, detecting the current posture, judging whether the current posture meets the preset condition, and if so, entering the step S42; otherwise, deleting the group of data and recalculating the current posture;
s42, calculating the current gravity center vertical velocity component according to the gravity center coordinates of each target point cloud data, judging whether the gravity center vertical velocity component meets a first preset threshold value, if so, determining that the current person to be detected has a vertical direction movement trend, and entering the step S43; otherwise, the current person to be tested is considered to have no falling tendency;
s43, calculating the actual height among the target point cloud data according to the target point cloud data to obtain the gravity center height of the current person to be measured, wherein the calculation formula is as follows:
wherein h is g Is the gravity center height of the current person to be measured, H is the radar mounting height, z i As the target point cloud height, N p The number of point clouds in the millimeter wave radar point cloud data of each frame is n, and the number of the fused millimeter wave radar point cloud data frames is n;
s44, judging whether the gravity center height of the current person to be tested meets a second preset threshold, if so, determining that the current person to be tested has a lying posture trend, and entering the step S45; otherwise, the current person to be tested is considered to have no falling tendency;
s45, calculating a maximum width ratio according to the target effective point cloud set, judging whether the maximum width ratio meets a third preset threshold value, if so, determining that the current person to be tested has a lying posture, and entering S46; otherwise, the current person to be tested is considered to have no falling tendency;
s46, judging whether the height of the target point of the current person to be tested meets a preset fourth preset threshold value or not, and if so, determining that the current person to be tested falls down; otherwise, the current person to be tested is considered to have no falling tendency.
Preferably, the preset condition in step S41 is expressed as:
S t ＝S t-1 ＝S t-2 ＝…＝S t-n
wherein S is t And n is the fused millimeter wave radar point cloud data for the human body posture detected at the moment t.
Preferably, the calculation formula of the current barycentric vertical velocity component in step S42 is expressed as:
wherein, V z For the vertical velocity component of the current center of gravity, V is the radial velocity, N p The number of point clouds in each frame of millimeter wave radar point cloud data is shown, n is the fused millimeter wave radar point cloud data, and sin theta is the sine value of the pitch angle of the target point cloud.
Preferably, the calculation of the maximum width ratio in step S45 includes the steps of:
b1, performing secondary clustering on the target effective point cloud sets to obtain target effective point cloud sets subjected to secondary clustering;
b2, converting the point cloud data in the target effective point cloud set after the secondary clustering processing into a data set under a three-dimensional Cartesian coordinate system, and obtaining the area of each point cloud; wherein the area of each point cloud satisfies
B3, calculating the maximum width ratio of the target effective point cloud set after the secondary clustering according to the area where each point cloud is located, and expressing the maximum width ratio as follows:
wherein R is h Max (. eta.) is a function of the maximum width ratio, x max ，x min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the x-axis coordinate after the secondary clustering processing; y is max ,y min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the y-axis coordinate after the secondary clustering processing; z is a radical of max ,z min Respectively is the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the z-axis coordinate after the secondary clustering processing.
In a second aspect, a fall gesture recognition system based on millimeter wave radar point cloud includes:
the target effective point cloud set building module is used for collecting millimeter wave radar point clouds and carrying out pretreatment to obtain a target effective point cloud set;
the coordinate system building module is used for converting each target point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be detected and building a three-dimensional Cartesian coordinate system according to the spatial position coordinate of the person to be detected;
the gravity center coordinate calculation module is used for calculating the gravity center coordinate of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
and the falling attitude identification module is used for identifying the current falling attitude of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
In a third aspect, an electronic device includes:
a memory for storing a computer program;
a processor for implementing any of the steps of the method for recognizing a fall gesture based on a millimeter wave radar point cloud when executing the computer program.
The invention has the following beneficial effects:
acquiring millimeter wave radar point clouds, preprocessing the millimeter wave radar point clouds to obtain a target effective point cloud set, converting each target point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be detected, constructing a three-dimensional Cartesian coordinate system according to the spatial position coordinate of the person to be detected, and calculating the gravity center coordinate of each target point cloud data in the target effective point cloud set by combining the three-dimensional Cartesian coordinate system; identifying the current falling posture of the person to be detected according to the gravity center coordinates; by the millimeter wave radar technology, the accuracy of falling posture identification is ensured, the privacy safety of the personnel to be detected is ensured to the maximum extent, and the problems of low privacy, low stability, low accuracy, low comfort and the like of the existing falling detection method are effectively solved; the falling early warning system can be applied to old people care institutions, hotels or families, and effectively reduces risks caused by falling accidents.
Drawings
Fig. 1 is a flowchart illustrating steps of a fall gesture recognition method based on millimeter wave radar point cloud according to the present invention;
fig. 2 is a schematic view of a millimeter wave radar in an embodiment of the present invention, in which fig. 2(a) is a front view of the radar and fig. 2(b) is a side view of the radar;
FIG. 3 is a flowchart illustrating steps S1 according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the sub-step of step S13 according to an embodiment of the present invention;
FIG. 5 is a coordinate system of a millimeter wave radar apparatus according to an embodiment of the present invention;
FIG. 6 is a millimeter wave radar point cloud data diagram under a three-dimensional Cartesian coordinate system according to an embodiment of the invention;
FIG. 7 is a flowchart illustrating the substeps of step S4 according to an embodiment of the present invention;
fig. 8 is a flowchart illustrating the steps of calculating the maximum width ratio in step S45 according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
On one hand, as shown in fig. 1, an embodiment of the present invention provides a method for recognizing a fall gesture based on millimeter wave radar point cloud, including the following steps:
s1, collecting millimeter wave radar point clouds and preprocessing the millimeter wave radar point clouds to obtain a target effective point cloud set;
in the embodiment of the invention, the length-width ratio (X) of the rectangular structure of the room is determined 0 :Y 0 ) Selecting proper installation height H, direction and pitch angle to enable the working blind area of the millimeter wave radar device to tend to be in a smaller range; more specifically, in the embodiment of the invention, the length and the width of the room are similar, the installation mode adopts a side installation mode as shown in figure 2, the installation height is 1.7m, and the installation pitch angle is 0 degree.
As shown in fig. 3, preferably, step S1 specifically includes the following sub-steps:
s11, collecting the millimeter wave radar point cloud, judging whether frame data are missing in the millimeter wave radar point cloud or not, if so, filling the missing data with data, and entering the step S12; otherwise, go to step S12;
in the embodiment of the invention, point cloud data is sent by a millimeter wave radar device in frames, and the method for acquiring each frame of millimeter wave radar point cloud data comprises the following steps: firstly, a millimeter wave radar device generates a chirp signal through a synthesizer and transmits the chirp signal through a transmitting antenna, a receiving antenna captures a reflected chirp of an object in a scanning area to the chirp signal, and then a mixer combines signals of the transmitting antenna and the receiving antenna together to generate an intermediate frequency signal;
performing Fourier transform on the intermediate frequency signal along a distance dimension and performing Fourier transform along a Doppler dimension to obtain a Range-Doppler Matrix (RDM), performing cell average constant false alarm detection along the Doppler dimension in the RDM, performing cell average constant false alarm detection along the distance dimension, and performing Fourier transform between space dimensions, namely receiving antennas, on the detected cell to realize the arrival angle estimation of the cell; and (3) obtaining the representation (r, phi, theta and V) of the points of the detected cells according to the distance, the speed and the angle of the detected cells, wherein r is the distance between the target point cloud and the origin of coordinates, phi is an azimuth angle, theta is a pitch angle, and V is the radial speed of the points, and the representation of the points of all the cells forms millimeter wave radar point cloud data. Each time, a complete frame period is formed by the process of obtaining millimeter wave radar point cloud data through linear frequency modulation pulse signal transmitting, receiving and signal processing. And continuously transmitting linear frequency modulation signals by the radar to obtain millimeter wave radar point cloud continuous data frames.
In the embodiment of the invention, it is assumed that a frame of millimeter wave radar point cloud continuous data comprises N p Each target point contains 5 fields of (r, phi, theta, V) four-dimensional information and signal-to-noise ratio (SNR), and if the length of each field is l bytes, the length of each frame of millimeter wave radar data should be:
L＝5·N p ·l
length l of point cloud data frame of millimeter wave radar 0 <And L, considering that the data frame has a missing data phenomenon, and filling data in the missing position on the premise of ensuring that the data is not misplaced.
S12, judging whether the number of point clouds in each frame of data of the millimeter wave radar point clouds meets the preset point cloud detection number, and if so, fusing at least one frame of millimeter wave radar point cloud data to obtain a millimeter wave radar point cloud data set; otherwise, returning to the step S11;
in the embodiment of the invention, the length l of each frame of millimeter wave radar point cloud data frame is counted 0 When the number N of point clouds in each frame of millimeter wave radar point cloud data p If the detection precision can not be ensured when the preset point cloud detection number M is not reached, N frames of millimeter wave radar point cloud data are fused to improve the identification accuracy, and the total number of the target point clouds is (n.N) p ) The millimeter wave radar point cloud data set M.
And S13, clustering the millimeter wave radar point cloud data set by using a density-based noise application space clustering method to obtain a target effective point cloud set.
In the embodiment of the invention, the clustering method adopts density-based noise application space clustering (DBSCAN). Compared with a k-means clustering method, the DBSCAN clustering method does not need to set the cluster number in advance, the cluster number can not be determined in the millimeter wave radar point cloud data generally, the density outlier detection is very accurate, the outlier in the millimeter wave radar point cloud data can be identified accurately, and the effects of clustering and noise point removal can be realized; two main parameters were set in the cluster analysis: epsilon (Epsilon) is used to define the neighborhood search radius around a point, the DBSCAN clustering method finds clusters by examining the Epsilon neighborhood of each object in the valid point cloud dataset X, and if the Epsilon neighborhood of a point contains at least MinPts neighbors, the DBSCAN identifies the point as a core point. MinPts is the minimum number of neighbors required for the core point, the epsilon neighborhood of the core point in the cluster must contain at least MinPts neighbors, and the epsilon neighborhood of the boundary point may contain fewer neighbors than MinPts.
As shown in fig. 4, preferably, step S13 specifically includes the following sub-steps:
a1, calculating the Euclidean distance between each point cloud and other point clouds in the millimeter wave radar point cloud data set, wherein the calculation formula is as follows:
wherein dist is Euclidean distance, X is millimeter wave radar point cloud data set, and Y is the ith point X in the millimeter wave radar point cloud data set X i Subset of (a), y i For the ith data in subset Y, N p The number of point clouds in each frame of millimeter wave radar point cloud data, N is the fused millimeter wave radar point cloud data, (n.N) p ) The total number of the target point clouds is obtained;
in the embodiment of the invention, the target effective point cloud data set
For any point X in X i Calculating a point x i Removing point X to set X i Subset of the latter
The euclidean distance between all points in (a).
A2, constructing a k-distance set of each point cloud in the millimeter wave radar point cloud data set according to the Euclidean distance;
in the embodiment of the invention, the obtained distances are sorted from small to large, and the rows are supposed to be arrangedThe set of distances after the sequence is
Wherein d is k Is a point x i To the k-th nearest element between all points in the set Y, then called d k Is k-distance (k-distance). For all points X in the target valid point cloud data set X i K-distances are calculated by an Euclidean distance calculation formula, and finally k-distance sets of all points are obtained
A3, constructing a k-distance curve graph according to the k-distance set of each point cloud, and determining a neighborhood radius by a curve inflection point;
in the embodiment of the invention, the set E is sorted in an ascending order and a k-distance graph (k-distance graph) is drawn, and the k-distance value corresponding to the inflection point position (knee) of the curve is determined as the value of the neighborhood radius epsilon by observing the k-distance graph, because the neighborhood of the inflection point is the area where the points in the data set start to gradually reduce to the abnormal value (noise) area.
A4, determining the number of each point in the millimeter wave radar point cloud data set in the neighborhood radius, calculating the expectation of each number, and taking the expectation as the optimal value of the number of data points in the neighborhood radius in the cluster to obtain a target effective point cloud set, wherein the expected calculation formula is represented as:
wherein p is i MinPts is the mathematical expectation for the number of points in the neighborhood radius ε of the ith point data, where the MinPts parameter is set to 50 and the ε parameter is set to 0.5.
In the embodiment of the invention, under the condition that the neighborhood radius epsilon is determined, the number of points in the epsilon neighborhood of each point in the data set is counted, then the mathematical expectation is calculated on the number of points in the epsilon neighborhood of each point in the whole data set X to obtain MinPts, and the MinPts at the moment is the optimal value of the number of the data points in the epsilon neighborhood of the core object in each cluster.
S2, converting the target point cloud data in the target effective point cloud set into spatial position coordinates of a person to be detected, and constructing a three-dimensional Cartesian coordinate system according to the spatial position coordinates of the person to be detected;
preferably, step S2 is specifically:
converting each point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be measured according to a mapping relation from a spatial polar coordinate to a standard spatial coordinate, and constructing a three-dimensional Cartesian coordinate system by taking a millimeter wave radar device as a coordinate origin according to the spatial position coordinate of the person to be measured, wherein the mapping relation from the spatial polar coordinate to the standard spatial coordinate is expressed as follows:
wherein f is a mapping relation;
for spatial polar coordinates, (x, y, z) are standard spatial coordinates, cos (. lam.) is a cosine function, sin (. lam.) is a sine function, and s is the radial distance.
As shown in fig. 5, it is a coordinate system of the millimeter wave radar apparatus according to the embodiment of the present invention; fig. 6 shows millimeter wave radar point cloud data in a three-dimensional cartesian coordinate system according to an embodiment of the present invention.
S3, calculating the barycentric coordinates of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
preferably, step S3 is specifically:
according to a three-dimensional Cartesian coordinate system, calculating barycentric coordinates of each target point cloud data in a target effective point cloud set, wherein the calculation formula of the barycentric coordinates is as follows:
wherein x is g X-axis coordinate, x, being the coordinate of the center of gravity of the object i Is the x-axis coordinate of the ith point in the target effective point cloud set M, N p The number of the point clouds in each frame of millimeter wave radar point cloud data is shown, and n is the fused millimeter wave radar point cloud data.
Wherein, the calculation method of the y-axis coordinate and the z-axis coordinate is the same as the above.
And S4, identifying the current falling posture of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
As shown in fig. 7, preferably, step S4 specifically includes the following sub-steps:
s41, detecting the current posture, judging whether the current posture meets the preset condition, and if so, entering the step S42; otherwise, deleting the group of data and recalculating the current posture;
preferably, the preset condition in step S41 is represented as:
S t ＝S t-1 ＝S t-2 ＝…＝S t-n
wherein S is t And n is the fused millimeter wave radar point cloud data for the human body posture detected at the moment t.
The condition shows that the attitude result of the frame detection at the current moment is the same as the attitude detection result of the previous (n · s) frame, so that misjudgments of a transition frame, namely a millimeter wave radar point cloud data frame in the attitude change process can be eliminated.
S42, calculating the current gravity center vertical velocity component according to the gravity center coordinates of each target point cloud data, judging whether the gravity center vertical velocity component meets a first preset threshold value, if so, determining that the current person to be detected has a vertical direction movement trend, and entering the step S43; otherwise, the current person to be tested is considered to have no falling tendency;
preferably, the calculation formula of the current barycentric vertical velocity component in step S42 is expressed as:
wherein, V z For the vertical velocity component of the current center of gravity, V is the radial velocity, N p For each frame of millimeter wave radar pointsThe number of cloud points in the cloud data, n is the fused millimeter wave radar point cloud data, and sin theta is the sine value of the pitch angle of the target point cloud.
In the embodiment of the invention, if the height of the gravity center of the human body is lowered to the lowest point within 1 second, the current detected object is considered to have the risk of falling, namely, when the velocity component V in the vertical direction of the point cloud is formed z >V max In which V is max The maximum velocity threshold value of the velocity component of the point cloud in the vertical direction is used, and the gravity center height needs to be further judged in order to avoid misjudgment of normal activities.
S43, calculating the actual height among the target point cloud data according to the target point cloud data to obtain the gravity center height of the current person to be measured, wherein the calculation formula is as follows:
wherein h is g Is the gravity center height of the current person to be measured, H is the radar mounting height, z i As the target point cloud height, N p The number of point clouds in the millimeter wave radar point cloud data of each frame is n, and the number of the fused millimeter wave radar point cloud data frames is n;
s44, judging whether the gravity center height of the current person to be tested meets a second preset threshold, if so, determining that the current person to be tested has a lying posture trend, and entering the step S45; otherwise, the current person to be tested is considered to have no falling tendency;
in the embodiment of the invention, when the height h of the gravity center is g Satisfies the condition h g <C center H, wherein C center And if the gravity center height threshold coefficient is obtained, the detected target is considered to be at a lower height currently, and the detected target is marked as a suspected lying down posture. In order to distinguish the squat action of the detected target, the z-axis coordinate value range of the target point cloud needs to be further detected.
S45, calculating a maximum width ratio according to the target effective point cloud set, judging whether the maximum width ratio meets a third preset threshold value, if so, determining that the current person to be tested has a lying posture, and entering the step S46; otherwise, the current person to be tested is considered to have no falling tendency;
as shown in fig. 8, the calculation method of the maximum width ratio in step S45 includes the steps of:
b1, performing secondary clustering on the target effective point cloud sets to obtain target effective point cloud sets subjected to secondary clustering;
b2, converting the point cloud data in the target effective point cloud set after the secondary clustering treatment into a data set under a three-dimensional Cartesian coordinate system, and obtaining the area of each point cloud;
in the embodiment of the present invention, in order to describe the current posture corresponding to the millimeter wave radar more accurately, the present embodiment performs secondary DBSCAN clustering analysis on the target effective point cloud set to obtain a target effective point cloud set after secondary DBSCAN clustering, and converts the target effective point cloud set into an area S where a point cloud is located in a spatial coordinate system L, so that any point cloud P (x, y, z) in the target effective point cloud set after secondary DBSCAN clustering satisfies:
wherein x is max ，x min Respectively representing the maximum value and the minimum value of point clouds in the target effective point cloud set after the secondary DBSCAN clustering on the x-axis coordinate; y is max ，y min Respectively representing the maximum value and the minimum value of point cloud coordinates of a target effective point cloud set after secondary DBSCAN clustering on the y axis; z is a radical of formula max ，z min The maximum value and the minimum value of the point cloud in the target effective point cloud set after the secondary DBSCAN clustering on the z-axis coordinate are respectively.
B3, calculating the maximum width ratio of the target effective point cloud set after the secondary clustering according to the area where each point cloud is located, and expressing the maximum width ratio as follows:
wherein R is h Max (. eta.) is a function of the maximum width ratio, x max ，x min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the x-axis coordinate after the secondary clustering processing; y is max ,y min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the y-axis coordinate after the secondary clustering processing; z is a radical of max ,z min Respectively is the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the z-axis coordinate after the secondary clustering processing.
In the embodiment of the invention, the maximum aspect ratio R of the concentrated point clouds of the target effective point clouds after secondary DBSCAN clustering h <C lie In which C is lie Marking a threshold coefficient for the lying posture of the point cloud in the target effective point cloud after the secondary DBSCAN clustering, and considering that the target to be measured is in the lying posture; in order to avoid misjudgment of normal sleeping behavior, whether the target point cloud is in contact with the ground or not needs to be further detected.
S46, judging whether the height of the target point of the current person to be tested meets a preset fourth preset threshold value, and if so, determining that the current person to be tested falls down; otherwise, the current person to be tested is considered to have no falling tendency.
In the embodiment of the present invention, it is determined whether the actual height of the target point is smaller than a fourth preset threshold, that is: h is i <C low Number of points N of H z In which C is low Marking a threshold coefficient for the effective target point cloud near the ground, and counting the number N of the target point clouds meeting the condition z >C point ·(n·N p ) In which C is point Marking a quantity threshold coefficient for the target point cloud, and determining that the target to be detected is in contact with the ground, namely that the current posture of the target to be detected is judged to fall down; actual height h of each point i The calculation formula is as follows: h is i ＝H+z i (ii) a The fourth preset threshold may include a height threshold (where the height threshold is different from the height threshold of the gravity center point; usually, the height threshold is higher than the height threshold of the gravity center point) or the number of point clouds under the height threshold, which can be used to determine the number of point clouds at a lower height, where the number of point clouds at a lower height is less in a normal standing situation and the number of point clouds at a lower height is more in a falling state.
In a second aspect, an embodiment of the present invention provides a system for recognizing a fall gesture based on millimeter wave radar point cloud, including:
the target effective point cloud set building module is used for collecting millimeter wave radar point clouds and carrying out pretreatment to obtain a target effective point cloud set;
the coordinate system building module is used for converting each target point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be detected and building a three-dimensional Cartesian coordinate system according to the spatial position coordinate of the person to be detected;
the gravity center coordinate calculation module is used for calculating the gravity center coordinate of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
and the falling attitude identification module is used for identifying the current falling attitude of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
The system for recognizing the falling attitude based on the millimeter wave radar point cloud provided by the embodiment of the invention has all the beneficial effects of the method for recognizing the falling attitude based on the millimeter wave radar point cloud.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
a memory for storing a computer program;
a processor for implementing any of the steps of the method for recognizing a fall gesture based on a millimeter wave radar point cloud when executing the computer program.
The electronic equipment provided by the embodiment of the invention has all the beneficial effects of the fall attitude identification method based on the millimeter wave radar point cloud.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (10)
1. A fall attitude identification method based on millimeter wave radar point cloud is characterized by comprising the following steps:
s1, collecting millimeter wave radar point clouds and preprocessing the millimeter wave radar point clouds to obtain a target effective point cloud set;
s2, converting the target point cloud data in the target effective point cloud set into spatial position coordinates of a person to be detected, and constructing a three-dimensional Cartesian coordinate system according to the spatial position coordinates of the person to be detected;
s3, calculating the barycentric coordinates of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
and S4, identifying the current falling posture of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
2. The method for recognizing the fall gesture based on the millimeter wave radar point cloud of claim 1, wherein step S1 specifically comprises the following steps:
s11, collecting the millimeter wave radar point cloud, judging whether frame data are missing in the millimeter wave radar point cloud or not, if yes, filling the missing data with data, and entering the step S12; otherwise, go to step S12;
s12, judging whether the number of point clouds in each frame of data of the millimeter wave radar point clouds meets the preset point cloud detection number, and if so, fusing at least one frame of millimeter wave radar point cloud data to obtain a millimeter wave radar point cloud data set; otherwise, returning to the step S11;
and S13, clustering the millimeter wave radar point cloud data set by using a density-based noise application space clustering method to obtain a target effective point cloud set.
3. The fall posture identification method based on the millimeter wave radar point cloud of claim 2, wherein the step S13 specifically comprises the following sub-steps:
a1, calculating the Euclidean distance between each point cloud and other point clouds in the millimeter wave radar point cloud data set, wherein the calculation formula is as follows:
wherein dist (.) is Euclidean distance, X is millimeter wave radar point cloud data set, and Y is the ith point X in the millimeter wave radar point cloud data set i Subset of (a), y i For the ith data in subset Y, N p The number of point clouds in each frame of millimeter wave radar point cloud data, N is the fused millimeter wave radar point cloud data, (n.N) p ) The total number of the target point clouds is obtained;
a2, constructing a k-distance set of each point cloud in the millimeter wave radar point cloud data set according to Euclidean distances;
a3, constructing a k-distance curve graph according to the k-distance set of each point cloud, and determining the radius of a neighborhood by a curve inflection point;
a4, determining the number of each point in the millimeter wave radar point cloud data set in the neighborhood radius, calculating the expectation of each number, and taking the expectation as the optimal value of the number of data points in the neighborhood radius in the cluster to obtain a target effective point cloud set, wherein the expected calculation formula is represented as:
wherein p is i MinPts is the mathematical expectation for the number of points in the neighborhood radius ε of the ith data.
4. The method for recognizing the fall gesture based on the millimeter wave radar point cloud of claim 1, wherein the step S2 specifically comprises:
converting each point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be measured according to a mapping relation from a spatial polar coordinate to a standard spatial coordinate, and constructing a three-dimensional Cartesian coordinate system by taking a millimeter wave radar device as a coordinate origin according to the spatial position coordinate of the person to be measured, wherein the mapping relation from the spatial polar coordinate to the standard spatial coordinate is expressed as follows:
wherein f is a mapping relation;
for spatial polar coordinates, (x, y, z) are standard spatial coordinates, cos (.) is a cosine function, sin (.) is a sine function, and s is a radial distance.
5. The method for recognizing the falling posture based on the millimeter wave radar point cloud as claimed in claim 1, wherein the step S4 specifically comprises the following sub-steps:
s41, detecting the current posture, judging whether the current posture meets the preset condition, and if so, entering the step S42; otherwise, deleting the group of data and recalculating the current posture;
s42, calculating the current gravity center vertical velocity component according to the gravity center coordinates of each target point cloud data, judging whether the gravity center vertical velocity component meets a first preset threshold value, if so, determining that the current person to be detected has a vertical direction movement trend, and entering the step S43; otherwise, the current person to be tested is considered to have no falling tendency;
s43, calculating the actual height among the target point cloud data according to the target point cloud data to obtain the gravity center height of the current person to be measured, wherein the calculation formula is as follows:
wherein h is g Is the gravity center height of the current person to be measured, H is the radar mounting height, z i As the target point cloud height, N p The number of point clouds in the millimeter wave radar point cloud data of each frame is n, and the number of the fused millimeter wave radar point cloud data frames is n;
s44, judging whether the gravity center height of the current person to be tested meets a second preset threshold, if so, determining that the current person to be tested has a lying posture trend, and entering the step S45; otherwise, the current person to be tested is considered to have no falling tendency;
s45, calculating a maximum width ratio according to the target effective point cloud set, judging whether the maximum width ratio meets a third preset threshold value, if so, determining that the current person to be tested has a lying posture, and entering the step S46; otherwise, the current person to be tested is considered to have no falling tendency;
s46, judging whether the height of the target point of the current person to be tested meets a preset fourth preset threshold value or not, and if so, determining that the current person to be tested falls down; otherwise, the current person to be tested is considered to have no falling tendency.
6. The method for recognizing the falling posture based on the millimeter wave radar point cloud as claimed in claim 5, wherein the preset conditions in the step S41 are as follows:
S t ＝S t-1 ＝S t-2 ＝…＝S t-n
wherein S is t And n is the fused millimeter wave radar point cloud data for the human body posture detected at the moment t.
7. The method for recognizing the falling posture based on the millimeter wave radar point cloud as claimed in claim 5, wherein the calculation formula of the vertical velocity component of the current gravity center in the step S42 is as follows:
wherein, V z For the vertical velocity component of the current center of gravity, V is the radial velocity, N p And n is the point cloud number in each frame of millimeter wave radar point cloud data, n is the fused millimeter wave radar point cloud data, and sin theta is the sine value of the target point cloud pitch angle.
8. The method for recognizing the falling posture based on the millimeter wave radar point cloud as claimed in claim 5, wherein the calculation manner of the maximum width ratio in the step S45 comprises the following steps:
b1, performing secondary clustering on the target effective point cloud sets to obtain target effective point cloud sets subjected to secondary clustering;
b2, converting the point cloud data in the target effective point cloud set after the secondary clustering processing into a data set under a three-dimensional Cartesian coordinate system, and obtaining the area of each point cloud;
b3, calculating the maximum width ratio of the target effective point cloud set after the secondary clustering according to the area where each point cloud is located, and expressing the maximum width ratio as follows:
wherein R is h Max (. eta.) is a function of the maximum width ratio, x max ，x min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the x-axis coordinate after the secondary clustering processing; y is max ,y min Respectively obtaining the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the y-axis coordinate after the secondary clustering processing; z is a radical of max ,z min Respectively is the maximum value and the minimum value of each point cloud in the target effective point cloud set M' on the z-axis coordinate after the secondary clustering processing.
9. A fall attitude identification system based on millimeter wave radar point cloud is characterized by comprising:
the target effective point cloud set building module is used for collecting millimeter wave radar point clouds and carrying out pretreatment to obtain a target effective point cloud set;
the coordinate system building module is used for converting each target point cloud data in the target effective point cloud set into a spatial position coordinate of a person to be detected and building a three-dimensional Cartesian coordinate system according to the spatial position coordinate of the person to be detected;
the gravity center coordinate calculation module is used for calculating the gravity center coordinate of each target point cloud data in the target effective point cloud set according to the three-dimensional Cartesian coordinate system;
and the falling attitude identification module is used for identifying the current falling attitude of the person to be detected according to the barycentric coordinates of each target point cloud data and the target effective point cloud set.
10. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for fall gesture recognition based on millimeter wave radar point clouds of any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210441714.0A CN114942434B (en) | 2022-04-25 | 2022-04-25 | Fall gesture recognition method and system based on millimeter wave Lei Dadian cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210441714.0A CN114942434B (en) | 2022-04-25 | 2022-04-25 | Fall gesture recognition method and system based on millimeter wave Lei Dadian cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114942434A true CN114942434A (en) | 2022-08-26 |
| CN114942434B CN114942434B (en) | 2024-02-02 |
Family
ID=82906289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210441714.0A Active CN114942434B (en) | 2022-04-25 | 2022-04-25 | Fall gesture recognition method and system based on millimeter wave Lei Dadian cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114942434B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115291184A (en) * | 2022-10-08 | 2022-11-04 | 四川启睿克科技有限公司 | Attitude monitoring method combining millimeter wave radar and deep learning |
| CN115439484A (en) * | 2022-11-10 | 2022-12-06 | 苏州挚途科技有限公司 | Detection method and device based on 4D point cloud, storage medium and processor |
| CN115601925A (en) * | 2022-11-17 | 2023-01-13 | 中南民族大学（Cn） | Fall detection system |
| CN115661935A (en) * | 2022-10-31 | 2023-01-31 | 海信集团控股股份有限公司 | Method and equipment for determining human body action accuracy |
| CN117173793A (en) * | 2023-11-02 | 2023-12-05 | 浙江大华技术股份有限公司 | Target gesture detection method, computer device and storage medium |
| CN117636404A (en) * | 2024-01-26 | 2024-03-01 | 贵州信邦富顿科技有限公司 | Fall detection method and system based on non-wearable equipment |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109581361A (en) * | 2018-11-22 | 2019-04-05 | 九牧厨卫股份有限公司 | A kind of detection method, detection device, terminal and detection system |
| US20190108740A1 (en) * | 2017-10-06 | 2019-04-11 | Tellus You Care, Inc. | Non-contact activity sensing network for elderly care |
| CN111047827A (en) * | 2019-12-03 | 2020-04-21 | 北京深测科技有限公司 | Intelligent monitoring method and system for environment-assisted life |
| CN111145264A (en) * | 2019-11-12 | 2020-05-12 | 深圳前海达闼云端智能科技有限公司 | Calibration method and device for multiple sensors and computing equipment |
| US20200301019A1 (en) * | 2019-03-22 | 2020-09-24 | Toyota Jidosha Kabushiki Kaisha | Object recognition device and vehicle control system |
| CN111931733A (en) * | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN112036269A (en) * | 2020-08-17 | 2020-12-04 | 文思海辉元辉科技(无锡)有限公司 | Fall detection method and device, computer equipment and storage medium |
| US20210018608A1 (en) * | 2019-07-16 | 2021-01-21 | Bodidata, Inc. | Systems and methods for improved radar scanning coverage and efficiency |
| CN112346055A (en) * | 2020-10-23 | 2021-02-09 | 无锡威孚高科技集团股份有限公司 | Fall detection method and device based on millimeter wave radar and millimeter wave radar equipment |
| CN112386248A (en) * | 2019-08-13 | 2021-02-23 | 中国移动通信有限公司研究院 | Method, device and equipment for detecting human body falling and computer readable storage medium |
| CN112526513A (en) * | 2021-02-10 | 2021-03-19 | 北方工业大学 | Millimeter wave radar environment map construction method and device based on clustering algorithm |
| CN112782664A (en) * | 2021-02-22 | 2021-05-11 | 西南交通大学 | Toilet fall detection method based on millimeter wave radar |
| CN113128379A (en) * | 2021-04-06 | 2021-07-16 | 深圳市真元天芮智能软件有限公司 | Human body falling detection method, computer readable storage medium and electronic device |
| CN113311428A (en) * | 2021-05-25 | 2021-08-27 | 山西大学 | Intelligent human body falling monitoring system based on millimeter wave radar and identification method |
| US11114206B2 (en) * | 2017-10-06 | 2021-09-07 | Tellus You Care, Inc. | Vital signs with non-contact activity sensing network for elderly care |
| CN113963192A (en) * | 2021-09-22 | 2022-01-21 | 森思泰克河北科技有限公司 | Fall detection method and device and electronic equipment |
-
2022
- 2022-04-25 CN CN202210441714.0A patent/CN114942434B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11114206B2 (en) * | 2017-10-06 | 2021-09-07 | Tellus You Care, Inc. | Vital signs with non-contact activity sensing network for elderly care |
| US20190108740A1 (en) * | 2017-10-06 | 2019-04-11 | Tellus You Care, Inc. | Non-contact activity sensing network for elderly care |
| CN109581361A (en) * | 2018-11-22 | 2019-04-05 | 九牧厨卫股份有限公司 | A kind of detection method, detection device, terminal and detection system |
| US20200301019A1 (en) * | 2019-03-22 | 2020-09-24 | Toyota Jidosha Kabushiki Kaisha | Object recognition device and vehicle control system |
| US20210018608A1 (en) * | 2019-07-16 | 2021-01-21 | Bodidata, Inc. | Systems and methods for improved radar scanning coverage and efficiency |
| CN112386248A (en) * | 2019-08-13 | 2021-02-23 | 中国移动通信有限公司研究院 | Method, device and equipment for detecting human body falling and computer readable storage medium |
| CN111145264A (en) * | 2019-11-12 | 2020-05-12 | 深圳前海达闼云端智能科技有限公司 | Calibration method and device for multiple sensors and computing equipment |
| CN111047827A (en) * | 2019-12-03 | 2020-04-21 | 北京深测科技有限公司 | Intelligent monitoring method and system for environment-assisted life |
| CN112036269A (en) * | 2020-08-17 | 2020-12-04 | 文思海辉元辉科技(无锡)有限公司 | Fall detection method and device, computer equipment and storage medium |
| CN111931733A (en) * | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN112346055A (en) * | 2020-10-23 | 2021-02-09 | 无锡威孚高科技集团股份有限公司 | Fall detection method and device based on millimeter wave radar and millimeter wave radar equipment |
| CN112526513A (en) * | 2021-02-10 | 2021-03-19 | 北方工业大学 | Millimeter wave radar environment map construction method and device based on clustering algorithm |
| CN112782664A (en) * | 2021-02-22 | 2021-05-11 | 西南交通大学 | Toilet fall detection method based on millimeter wave radar |
| CN113128379A (en) * | 2021-04-06 | 2021-07-16 | 深圳市真元天芮智能软件有限公司 | Human body falling detection method, computer readable storage medium and electronic device |
| CN113311428A (en) * | 2021-05-25 | 2021-08-27 | 山西大学 | Intelligent human body falling monitoring system based on millimeter wave radar and identification method |
| CN113963192A (en) * | 2021-09-22 | 2022-01-21 | 森思泰克河北科技有限公司 | Fall detection method and device and electronic equipment |
Non-Patent Citations (8)
| Title |
|---|
| 刘石雨: ""一种实时多传感器跌倒检测系统"", 《软件导刊》, vol. 20, no. 2, pages 165 - 169 * |
| 吕富强: ""基于密度噪声应用空间聚类算法的机载激光雷达建筑物点云提取与单体化"", vol. 22, no. 9, pages 3446 - 3452 * |
| 吕富强: "《基于密度噪声应用空间聚类算法的机载激光雷达建筑物点云提取与单体化》", vol. 22, no. 9, pages 3446 - 3452 * |
| 李克强: "《电动汽车工程手册 第六卷 智能网联》", 机械工业出版社, pages: 104 - 108 * |
| 王智: ""基于激光雷达的室内跌倒检测系统设计与实践"", 《声电技术》, vol. 45, no. 11, pages 51 - 54 * |
| 瞿畅: ""基于Kinect体感传感器的老年人跌倒自动检测"", 《传感技术学报》, vol. 29, no. 3, pages 378 - 384 * |
| 许志猛: ""基于空间聚类的FMCW雷达双人行为识别方法"", 《福州大学学报》, vol. 48, no. 4, pages 445 - 449 * |
| 谢辉: ""基于KCF的多条件综合判断行人跌倒检测方法"", 《物联技术》, no. 9, pages 27 - 31 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115291184A (en) * | 2022-10-08 | 2022-11-04 | 四川启睿克科技有限公司 | Attitude monitoring method combining millimeter wave radar and deep learning |
| CN115661935A (en) * | 2022-10-31 | 2023-01-31 | 海信集团控股股份有限公司 | Method and equipment for determining human body action accuracy |
| CN115439484A (en) * | 2022-11-10 | 2022-12-06 | 苏州挚途科技有限公司 | Detection method and device based on 4D point cloud, storage medium and processor |
| CN115601925A (en) * | 2022-11-17 | 2023-01-13 | 中南民族大学（Cn） | Fall detection system |
| CN117173793A (en) * | 2023-11-02 | 2023-12-05 | 浙江大华技术股份有限公司 | Target gesture detection method, computer device and storage medium |
| 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 |
| CN117636404A (en) * | 2024-01-26 | 2024-03-01 | 贵州信邦富顿科技有限公司 | Fall detection method and system based on non-wearable equipment |
| CN117636404B (en) * | 2024-01-26 | 2024-04-16 | 贵州信邦富顿科技有限公司 | Fall detection method and system based on non-wearable equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114942434B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114942434A (en) | Fall attitude identification method and system based on millimeter wave radar point cloud | |
| CN110456320B (en) | Ultra-wideband radar identity recognition method based on free space gait time sequence characteristics | |
| CN106559749B (en) | Multi-target passive positioning method based on radio frequency tomography | |
| CN103559508B (en) | A kind of based on continuous Adaboost video vehicle detection method | |
| US6735550B1 (en) | Feature classification for time series data | |
| CN112184626A (en) | Gesture recognition method, device, equipment and computer readable medium | |
| CN113311428B (en) | Human body falling intelligent monitoring system and falling identification method based on millimeter wave radar | |
| CN112394334A (en) | Radar reflection point clustering device and method and electronic equipment | |
| CN112926541A (en) | Sleeping post detection method and device and related equipment | |
| CN112782664A (en) | Toilet fall detection method based on millimeter wave radar | |
| CN114814832A (en) | Millimeter wave radar-based real-time monitoring system and method for human body falling behavior | |
| CN115205891A (en) | Personnel behavior recognition model training method, behavior recognition method and device | |
| CN110599800A (en) | Parking lot parking space state monitoring system and monitoring method | |
| CN111507361B (en) | Action recognition device, method and system based on microwave radar | |
| CN115542308A (en) | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar | |
| CN112198507B (en) | Method and device for detecting human body falling features | |
| CN116704366A (en) | Storm drop zone identification early warning method and device based on transform deep learning model | |
| CN116257651A (en) | Intelligent monitoring system for abnormal sound of through channel cab apron | |
| CN116520315A (en) | Target recognition system, target recognition method and target recognition device | |
| Yip et al. | Efficient and effective tropical cyclone eye fix using genetic algorithms | |
| CN114577224A (en) | Object positioning method and device, electronic equipment and storage medium | |
| CN111239717B (en) | Water surface obstacle detection method based on X-band radar | |
| CN113869183A (en) | Fall detection method and device | |
| CN117281498B (en) | Health risk early warning method and equipment based on millimeter wave radar | |
| CN115457351B (en) | Multi-source information fusion uncertainty judging method |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231013 Address after: 610000 Chengdu, Sichuan Province, China (Sichuan) Free Trade Pilot Zone Applicant after: Sichuan Bawei Jiuzhang Technology Co.,Ltd. Address before: 610031 north section of two ring road, Sichuan, Chengdu Applicant before: SOUTHWEST JIAOTONG University Applicant before: Sichuan Bawei Jiuzhang Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |