CN117908018A - Method, system, equipment and storage medium for warning waving hand - Google Patents
Method, system, equipment and storage medium for warning waving hand Download PDFInfo
- Publication number
- CN117908018A CN117908018A CN202410312918.3A CN202410312918A CN117908018A CN 117908018 A CN117908018 A CN 117908018A CN 202410312918 A CN202410312918 A CN 202410312918A CN 117908018 A CN117908018 A CN 117908018A
- Authority
- CN
- China
- Prior art keywords
- target
- tracks
- point cloud
- data
- radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 230000009471 action Effects 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000001228 spectrum Methods 0.000 claims description 16
- 238000009825 accumulation Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 238000011084 recovery Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000474 nursing effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
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
- G01S13/886—Radar or analogous systems specially adapted for specific applications for alarm systems
-
- 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
- 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
- G01S7/417—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 involving the use of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a method, a system, equipment and a storage medium for warning a waving hand, which relate to the technical field of action monitoring, and the method comprises the following steps: transmitting and collecting returned radar baseband data through a millimeter wave radar; processing the radar baseband data to obtain target point cloud data, and performing track tracking on the target point cloud data to generate a plurality of target tracks; and carrying out hand waving action recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to alarm if the hand waving action exists in the recognition result. The invention solves the technical problem of insufficient alarm accuracy caused by false alarm and missing alarm of active alarm in the prior art, and achieves the technical effect of improving the monitoring accuracy and applicability of active recovery alarm.
Description
Technical Field
The invention relates to the technical field of action monitoring, in particular to a method, a system, equipment and a storage medium for hand waving warning.
Background
The millimeter wave radar can be used for detecting vital signs such as human respiratory heart rate to whether fall or other abnormal conditions appear in the monitoring user, but its monitoring accuracy is lower, has the condition of missing report. In the prior art, the means of alarming through telephone alarming, voice recognition and the like are adopted to perfect the mode of active alarming of a user, but the technical problems of inconvenience or inaccuracy exist.
Disclosure of Invention
The application provides a method, a system, equipment and a storage medium for hand waving warning, which are used for solving the technical problems of inaccurate active warning monitoring and missing report in the prior art.
In a first aspect of the present application, there is provided a hand waving warning method, the method comprising:
transmitting and collecting returned radar baseband data through a millimeter wave radar;
Processing radar baseband data to obtain target point cloud data, and tracking tracks of the target point cloud data to generate a plurality of target tracks;
and carrying out hand waving action recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to give an alarm if the hand waving action exists in the recognition result.
In a second aspect of the present application, there is provided a hand swing warning system, the system comprising:
the radar data acquisition module is used for transmitting and acquiring returned radar baseband data through the millimeter wave radar;
the radar data processing module is used for processing the radar baseband data to obtain target point cloud data, and tracking the target point cloud data to generate a plurality of target tracks;
and the hand waving recognition alarm module is used for carrying out hand waving recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to alarm if the hand waving is in the recognition result.
In a third aspect of the present application, there is provided a computer device comprising a memory and a processor, the memory having stored therein a computer program which when executed by the processor performs the steps of the method of the first aspect.
In a fourth aspect of the present application, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of the first aspect.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
According to the technical scheme, through the millimeter wave radar, returned radar baseband data are transmitted and collected, the radar baseband data are processed to obtain target point cloud data, track tracking is conducted on the target point cloud data to generate a plurality of target tracks, hand waving action recognition is conducted on the plurality of target tracks to obtain recognition results, and if the hand waving action exists in the recognition results, an alarm signal is generated to give an alarm. According to the application, the radar baseband data are collected, processed and clustered to generate the track formed by the hand waving of the user, the hand waving action recognition is carried out according to the track, and when the user carries out alarm indication through waving, the alarm can be accurately recognized, so that the technical effects of improving the alarm accuracy and convenience are achieved, and meanwhile, the omission of alarm monitoring of the user is reduced.
Drawings
FIG. 1 is a schematic flow chart of a method for warning a waving hand;
FIG. 2 is a schematic diagram of a method for acquiring radar baseband data in a waving warning method according to the present application;
FIG. 3 is a schematic diagram of performing distance-dimensional fast Fourier transform, doppler-dimensional Fourier transform and incoherent accumulation on radar baseband data in a waving warning method provided by the application;
FIG. 4 is a schematic diagram of target detection in a waving warning method provided by the application;
FIG. 5 is a schematic diagram of a hand waving alarm system according to the present application;
fig. 6 is a schematic structural diagram of an exemplary computer device according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a charging information acquisition module 11, a basic power distribution module 12, a real-time charging information acquisition module 13, a power distribution optimization module 14, a continuous power distribution module 15, a computer device 300, a memory 301, a processor 302, a communication interface 303 and a bus architecture 304.
Detailed Description
The application provides a method, a system, equipment and a storage medium for alarming when waving hands, which are used for solving the technical problems of inaccurate and inconvenient active alarming monitoring, missing reporting and the like in the prior art.
Example 1
As shown in fig. 1, the present application provides a method for warning a waving hand, which includes:
S101: transmitting and collecting returned radar baseband data through a millimeter wave radar;
In the embodiment of the application, the millimeter wave radar has the advantages of non-contact and privacy, so the millimeter wave radar is commonly used for detecting the respiratory heart rate of a human body to judge whether the human body falls down, and is widely applied to the fields of nursing homes, hospitals and the like. However, millimeter wave radar has low accuracy in detecting vital signs, and is prone to false negatives of falling events. For this situation, an active alerting method is needed, such as telephone alerting, voice recognition, etc., but this part of the users has a certain obstacle to the use and description of the telephone, so that the accuracy and convenience of the active alerting for falling is low.
In the embodiment of the application, the accuracy and the convenience of the active alarm are improved by waving the hand to actively alarm.
Alternatively, other limb actions can be adopted to carry out active alarm, and radar data are collected through the millimeter wave radar to carry out processing and active alarm identification.
And transmitting radar signals through monitoring equipment provided with millimeter wave radar, and collecting and processing the returned radar baseband data to be used as basic data for recovery alarm identification.
The monitoring device is preferably mounted by non-contact means, for example, it may be located on the user's bedside, ceiling or wall to transmit and collect radar signals back to the user's arm, facilitating the user's hand swing warning.
The monitoring equipment is also internally provided with a module for processing and identifying radar signals so as to execute the steps of the method provided by the embodiment of the application.
Step S101 in the method provided by the embodiment of the present application includes:
collecting a returned radar echo signal;
And amplifying, mixing, low-pass filtering and digital sampling the radar echo signals to obtain the radar baseband data.
In the embodiment of the application, after the millimeter wave radar transmits radar signals and is blocked and reflected by the arm of a user to return, the returned radar echo signals are collected.
Certain noise signals exist in the radar echo signals, and the processes such as noise filtering, amplification and the like are needed to be carried out so as to improve the accuracy of signal processing and waving identification.
Illustratively, radar echo signals are amplified, mixed, low pass filtered, digitally sampled, etc., to obtain radar baseband data.
In one possible embodiment, as shown in fig. 2, the millimeter wave radar adopts a TD-MIMO signal transmission mode, and transmits a chirped continuous wave signal (chirp signal), the radar signal is transmitted by a transmitting antenna, and the transmitted electromagnetic wave signal encounters an obstacle, such as the user's arm reflects back, and the time elapsesAnd after receiving echo signals, the receiving antenna filters noise influence through a low-noise amplifier, mixes with one path of transmitting signals, obtains intermediate frequency signals (IF signals) after passing through a low-pass filter, and digitally samples the intermediate frequency signals to obtain adc signals, namely radar baseband data.
Wherein the frequency of the intermediate frequency signalThe method comprises the following steps: /(I)Where k is the signal chirp rate,/>Is the target delay, and delay/>And the target distance d has the following relation: /(I)Where d is the target distance and c is the speed of light. Therefore, the distance between the target and the radar can be obtained by the frequency of the intermediate frequency signal: /(I)。
S102: processing radar baseband data to obtain target point cloud data, and tracking tracks of the target point cloud data to generate a plurality of target tracks;
in the embodiment of the application, based on the radar baseband data obtained by acquisition processing, the target point cloud data is further processed to obtain, and track tracking is carried out on the target point cloud data to identify the track of the radar signal point formed by the arm swing of the target user, so that the hand swing action is identified.
Step S102 in the method provided by the embodiment of the present application includes:
Performing distance-dimension fast Fourier transform and Doppler-dimension Fourier transform on the radar baseband data to obtain distance-Doppler spectrums of all target units;
Performing incoherent accumulation on the distance-Doppler spectrum, performing two-dimensional constant false alarm detection on an incoherent accumulation result by adopting a preset threshold parameter, and extracting to obtain a target monitoring unit corresponding to a target monitoring object on the distance-Doppler spectrum;
Performing azimuth-elevation combined angle measurement on the target monitoring unit to obtain a target azimuth angle, a target pitch angle and a target speed;
According to the target azimuth angle, the target pitch angle and the target speed, combining a target distance unit of the target monitoring unit in the distance-Doppler spectrum to obtain target point cloud data of the target monitoring unit;
and tracking the track according to the target point cloud data to obtain a plurality of target tracks.
In the embodiment of the application, after the radar baseband data is acquired and processed, the radar baseband data is subjected to distance-dimension fast Fourier transform and Doppler-dimension Fourier transform to obtain a distance-Doppler spectrum comprising all target units.
Further, incoherent accumulation is carried out on the distance-Doppler spectrum, a preset threshold parameter is adopted to carry out two-dimensional constant false alarm detection on the incoherent accumulation result, and a target monitoring unit corresponding to the target monitoring object on the distance-Doppler spectrum is obtained through extraction. The target monitoring object is a user arm, and the preset threshold parameter is set according to the arm swing habit distance of the user.
Further, azimuth-pitching combined angle measurement is carried out on the target monitoring unit, a target azimuth angle, a target pitch angle and a target speed are obtained, and target point cloud data of the target monitoring unit are obtained by combining the target distance unit of the target monitoring unit in a distance-Doppler spectrum.
And carrying out track tracking based on the target point cloud data, wherein the track tracking comprises the steps of clustering each point cloud into a corresponding clustering center, and then carrying out track tracking into a corresponding arm waving track to obtain a plurality of target tracks.
As shown in fig. 3, in one embodiment, the millimeter wave radar adopts a 3-transmit and 4-receive antenna design, 3 transmitting antennas transmit signals according to a time division multiplexing mode, 4 receiving antennas simultaneously receive signals, each transmitting antenna transmits 32 chips in one frame time, the number of adc sampling points of each chip is 512, I/Q complex sampling is adopted, and the data volume of the adc data received in one frame is. Performing distance dimension FFT (FFT point number is 512) on all chirp signals of a certain antenna of the adc data to obtain a range_FFT result, performing doppler dimension FFT (FFT point number is 32) on the range_FFT to obtain a doppler _FFT result, and performing the 2 times FFT on all antenna data to obtain/>Group RD-map. To improve the target signal-to-noise ratio, the RD-maps of all antennas are non-coherently accumulated to obtain accumulated RD-maps.
Further, as shown in fig. 4, two-dimensional cfar detection (constant false alarm detection) is performed on the accumulated RD-maps by adopting a preset threshold parameter, and the target is detected and extracted through two-dimensional cfar, wherein the target distance unit is rangeBin, the target doppler unit is dopplerBin, and the distance of the target can be calculated as follows:
The movement speed of the target is: /(I) Wherein/>、/>Respectively representing the distance resolution and the speed resolution. And extracting data of all antennas of the target unit on the RD-map, and calculating the azimuth angle and the pitch angle of the target by using an azimuth-pitch combined angle measuring method, so that the spatial position (x, y, z) of the target and the moving speed of the target can be determined.
In this way, spatial information and speed of all points, namely all target monitoring units, in the current frame are obtained, and target point cloud data are formed.
The step of tracking the track according to the target point cloud data to obtain a plurality of target tracks further comprises:
deleting a point with the speed of 0 from the target point cloud data to obtain target dynamic point cloud data;
And tracking tracks according to the target dynamic point cloud data to obtain a plurality of target tracks.
In the embodiment of the application, based on the speeds of all points in the target point cloud data, the points with the speed of 0 are screened out and deleted, and the target dynamic point cloud is obtained.
Since the radar point cloud data of the millimeter wave radar for monitoring and collecting the arm should be mobile when the user swings his hand, if the speed of a certain point is 0, the probability is noise data, so deletion is required, and the point cloud data with the speed is reserved.
And tracking the track based on the target dynamic point cloud data to obtain the track formed by the current arm swing of the user.
The step of tracking tracks according to the target dynamic point cloud data to obtain a plurality of target tracks includes:
Clustering a plurality of dynamic points in the dynamic point cloud data to obtain K clustering centers, wherein K is an integer greater than 1;
and carrying out track association according to the K clustering centers to obtain the target tracks.
And clustering a plurality of dynamic points in the dynamic point cloud data to obtain K clustering centers.
Illustratively, K cluster centers are obtained by calculating distances of a plurality of dynamic points, and the dynamic points with closer distances are grouped into one type, and each cluster center comprises a plurality of dynamic points with closer distances. K is an integer greater than 1.
In one embodiment, the dynamic points with the distance smaller than the preset distance threshold are clustered into a cluster center, and the preset distance threshold can be set according to the radar data acquisition processing experience of the user, for example, the distribution distance of the point cloud formed according to the size of the arm of the user.
Further, track association is carried out according to the K clustering centers, a plurality of target tracks are obtained, the clustering centers are associated to tracks formed by waving the arms of the nearest users, and recognition of waving actions is carried out.
The step of performing track association according to the K cluster centers to obtain the multiple target tracks in the method provided by the embodiment of the present application includes:
Acquiring a track data space, wherein the track data space comprises a plurality of existing tracks;
And inputting the K clustering centers into the track data space, carrying out nearest neighbor association according to a preset association distance threshold value to obtain a plurality of associated tracks, and generating new generated tracks in the track data space by the clustering centers without associated tracks to obtain a plurality of target tracks.
In the embodiment of the application, clustering is performed according to point cloud data formed by waving in the historical time of the user, a plurality of existing tracks are formed, and a track data space is constructed and used as a historical track database. Each existing track comprises track information formed by dynamic point clouds formed by a user waving an arm.
Inputting K clustering centers into a track data space, carrying out nearest neighbor association according to the distances between the dynamic point positions in the K clustering centers and a plurality of existing tracks and a preset association distance threshold, and selecting the existing tracks with the nearest distance of each clustering center to obtain a plurality of association tracks.
If no existing track exists in a preset association distance threshold value of one cluster center, generating a new generated track in a track data space directly according to the cluster center without the associated track, and obtaining a plurality of target tracks based on a plurality of associated tracks and a plurality of generated tracks. The total of the plurality of associated tracks and the plurality of generated tracks is K.
And reserving all clustering centers associated with all tracks and all dynamic point clouds forming the clustering centers in the track association process.
The preset association distance threshold may be set according to the average distance of the tracks generated by the user during different waving actions.
S103: and carrying out hand waving action recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to give an alarm if the hand waving action exists in the recognition result.
The radar baseband data are acquired through acquisition and processing, processing analysis and clustering are carried out, the track of the object movement in the space is currently detected and is used as a plurality of target tracks, and the plurality of target tracks are further required to be identified to judge whether the hand waving warning is carried out for the user.
In the embodiment of the application, the hand waving action recognition is carried out on a plurality of target tracks, the recognition result is obtained, and if the hand waving action exists in the recognition result, an alarm signal is generated to give an alarm so as to inform related personnel, such as nursing personnel or security personnel.
Step S103 in the method provided by the embodiment of the present application includes:
Acquiring all dynamic point clouds in a multi-frame clustering center accumulated in the multiple target tracks according to the time span, and acquiring multiple accumulated track point clouds;
And carrying out waving action recognition according to the quantity and distribution of the dynamic point clouds in the accumulated track point clouds and the change values of the speed, the distance, the azimuth angle and the pitch angle of the dynamic point clouds in each frame of clustering center, and obtaining the recognition result.
In the embodiment of the application, all dynamic point clouds in a multi-frame clustering center accumulated in a plurality of target tracks in a multi-frame are acquired according to the time span, and a plurality of accumulated track point clouds are acquired.
Wherein multiple target tracks may also be updated over multiple frames, yielding more tracks.
And analyzing whether the waving action of the user exists or not according to the quantity and distribution of the dynamic point clouds in the accumulated track point clouds and the change values of the speed, the distance, the azimuth angle and the pitch angle of the dynamic point clouds in each frame of clustering center as characteristic data.
The method comprises the steps of taking the change values of the speed, the distance, the azimuth angle and the pitch angle of dynamic point clouds in a plurality of accumulated track point clouds obtained by millimeter wave radar monitoring, collecting and processing in historical time as input training data, taking whether a waving action exists as output training data, constructing a model for training, forming a two-classification problem, and carrying out classification recognition on whether the waving action exists by training to convergence.
Optionally, other machine learning means or other methods in the prior art can be used for carrying out the hand waving action recognition.
And (3) through carrying out the recognition of the waving action, obtaining a recognition result, and generating an alarm signal to alarm if the waving action exists in the recognition result. And when the hand waving action does not exist in the identification result, continuing to monitor, so as to avoid false alarm.
In summary, the embodiment of the application has at least the following technical effects:
According to the technical scheme, through the millimeter wave radar, returned radar baseband data are transmitted and collected, the radar baseband data are processed to obtain target point cloud data, track tracking is conducted on the target point cloud data to generate a plurality of target tracks, hand waving action recognition is conducted on the plurality of target tracks to obtain recognition results, and if the hand waving action exists in the recognition results, an alarm signal is generated to give an alarm. According to the method, the radar baseband data are collected and processed to obtain the target point cloud data, the track tracking is carried out on the target point cloud data, the track formed by the hand waving of the user is generated, the waving action recognition is carried out according to the track, and when the user carries out alarm indication through waving, the identification alarm can be accurately carried out, so that the technical effects of improving the alarm accuracy and convenience are achieved, and meanwhile, the missing report of the alarm monitoring of the user is reduced.
Example two
Based on the same inventive concept as one of the hand waving alarm methods in the foregoing embodiments, as shown in fig. 5, the present application provides a hand waving alarm system, and the specific description of one of the hand waving alarm methods in the first embodiment is also applicable to the hand waving alarm system, where the system includes:
The radar data acquisition module 11 is used for transmitting and acquiring returned radar baseband data through a millimeter wave radar;
the radar data processing module 12 is used for processing the radar baseband data to obtain target point cloud data, and performing track tracking on the target point cloud data to generate a plurality of target tracks;
The waving recognition alarm module 13 is configured to recognize waving motions of the plurality of target tracks, obtain a recognition result, and if the recognition result includes waving motions, generate an alarm signal to alarm.
Further, the radar data acquisition module 11 is further configured to implement the following functions:
collecting a returned radar echo signal;
And amplifying, mixing, low-pass filtering and digital sampling the radar echo signals to obtain the radar baseband data.
Further, the radar data processing module 12 is further configured to implement the following functions:
Performing distance-dimension fast Fourier transform and Doppler-dimension Fourier transform on the radar baseband data to obtain distance-Doppler spectrums of all target units;
Performing incoherent accumulation on the distance-Doppler spectrum, performing two-dimensional constant false alarm detection on an incoherent accumulation result by adopting a preset threshold parameter, and extracting to obtain a target monitoring unit corresponding to a target monitoring object on the distance-Doppler spectrum;
Performing azimuth-elevation combined angle measurement on the target monitoring unit to obtain a target azimuth angle, a target pitch angle and a target speed;
According to the target azimuth angle, the target pitch angle and the target speed, combining a target distance unit of the target monitoring unit in the distance-Doppler spectrum to obtain target point cloud data of the target monitoring unit;
and tracking the track according to the target point cloud data to obtain a plurality of target tracks.
Track tracking is performed according to the target point cloud data to obtain a plurality of target tracks, including:
deleting a point with the speed of 0 from the target point cloud data to obtain target dynamic point cloud data;
And tracking tracks according to the target dynamic point cloud data to obtain a plurality of target tracks.
Track tracking is performed according to the target dynamic point cloud data to obtain a plurality of target tracks, wherein the track tracking comprises the following steps:
Clustering a plurality of dynamic points in the dynamic point cloud data to obtain K clustering centers, wherein K is an integer greater than 1;
and carrying out track association according to the K clustering centers to obtain the target tracks.
And performing track association according to the K clustering centers, wherein the track association comprises the following steps:
Acquiring a track data space, wherein the track data space comprises a plurality of existing tracks;
And inputting the K clustering centers into the track data space, carrying out nearest neighbor association according to a preset association distance threshold value to obtain a plurality of associated tracks, and generating new generated tracks in the track data space by the clustering centers without associated tracks to obtain a plurality of target tracks.
Further, the hand waving recognition alarm module is further used for realizing the following functions:
Acquiring all dynamic point clouds in a multi-frame clustering center accumulated in the multiple target tracks according to the time span, and acquiring multiple accumulated track point clouds;
And carrying out waving action recognition according to the quantity and distribution of the dynamic point clouds in the accumulated track point clouds and the change values of the speed, the distance, the azimuth angle and the pitch angle of the dynamic point clouds in each frame of clustering center, and obtaining the recognition result.
Example III
As shown in fig. 6, based on the same inventive concept as one of the hand waving alert methods in the previous embodiments, the present application further provides a computer device 300, where the computer device 300 includes a memory 301 and a processor 302, and the memory 301 stores a computer program, where the computer program implements steps of one of the methods in the embodiments when executed by the processor 302.
The computer device 300 includes: a processor 302, a communication interface 303, a memory 301. Optionally, the computer device 300 may also include a bus architecture 304. Wherein the communication interface 303, the processor 302 and the memory 301 may be interconnected by a bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry Standard architecture, EISA) bus, among others. The bus architecture 304 may be divided into address buses, data buses, control buses, and the like. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.
Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits for controlling the execution of the programs of the present application.
The communication interface 303, uses any transceiver-like means for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), wired access network, etc.
The memory 301 may be, but is not limited to, ROM or other type of static storage device, RAM or other type of dynamic storage device, which may store static information and instructions, or may be an electrically erasable programmable read-only memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY, EEPROM), a compact disk read-only memory (compact discread only memory, CD ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through bus architecture 304. The memory may also be integrated with the processor.
The memory 301 is used for storing computer-executable instructions for executing the inventive arrangements, and is controlled by the processor 302 for execution. The processor 302 is configured to execute computer-executable instructions stored in the memory 301, thereby implementing a hand waving warning method provided in the foregoing embodiment of the present application.
Example IV
Based on the same inventive concept as the hand waving warning method in the previous embodiments, the present application also provides a computer readable storage medium, in which a computer program is stored, which when executed by a processor, implements the steps of the method in the first embodiment.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (10)
1. A method for alerting a person to waving a hand, the method comprising:
transmitting and collecting returned radar baseband data through a millimeter wave radar;
Processing radar baseband data to obtain target point cloud data, and tracking tracks of the target point cloud data to generate a plurality of target tracks;
and carrying out hand waving action recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to give an alarm if the hand waving action exists in the recognition result.
2. The method of claim 1, wherein the acquiring the returned radar baseband data comprises:
collecting a returned radar echo signal;
And amplifying, mixing, low-pass filtering and digital sampling the radar echo signals to obtain the radar baseband data.
3. The method of claim 1, wherein processing the radar baseband data to obtain target point cloud data and track the target point cloud data comprises:
Performing distance-dimension fast Fourier transform and Doppler-dimension Fourier transform on the radar baseband data to obtain distance-Doppler spectrums of all target units;
Performing incoherent accumulation on the distance-Doppler spectrum, performing two-dimensional constant false alarm detection on an incoherent accumulation result by adopting a preset threshold parameter, and extracting to obtain a target monitoring unit corresponding to a target monitoring object on the distance-Doppler spectrum;
Performing azimuth-elevation combined angle measurement on the target monitoring unit to obtain a target azimuth angle, a target pitch angle and a target speed;
According to the target azimuth angle, the target pitch angle and the target speed, combining a target distance unit of the target monitoring unit in the distance-Doppler spectrum to obtain target point cloud data of the target monitoring unit;
and tracking the track according to the target point cloud data to obtain a plurality of target tracks.
4. A method according to claim 3, wherein tracking tracks according to the target point cloud data to obtain a plurality of target tracks comprises:
deleting a point with the speed of 0 from the target point cloud data to obtain target dynamic point cloud data;
And tracking tracks according to the target dynamic point cloud data to obtain a plurality of target tracks.
5. The method of claim 4, wherein tracking tracks based on the target dynamic point cloud data to obtain a plurality of target tracks, comprising:
Clustering a plurality of dynamic points in the dynamic point cloud data to obtain K clustering centers, wherein K is an integer greater than 1;
and carrying out track association according to the K clustering centers to obtain the target tracks.
6. The method of claim 5, wherein said performing track association according to said K cluster centers comprises:
Acquiring a track data space, wherein the track data space comprises a plurality of existing tracks;
And inputting the K clustering centers into the track data space, carrying out nearest neighbor association according to a preset association distance threshold value to obtain a plurality of associated tracks, and generating new generated tracks in the track data space by the clustering centers without associated tracks to obtain a plurality of target tracks.
7. The method of claim 6, wherein said performing a hand swing identification of said plurality of target tracks comprises:
Acquiring all dynamic point clouds in a multi-frame clustering center accumulated in the multiple target tracks according to the time span, and acquiring multiple accumulated track point clouds;
And carrying out waving action recognition according to the quantity and distribution of the dynamic point clouds in the accumulated track point clouds and the change values of the speed, the distance, the azimuth angle and the pitch angle of the dynamic point clouds in each frame of clustering center, and obtaining the recognition result.
8. A hand waving alert system, the system comprising:
the radar data acquisition module is used for transmitting and acquiring returned radar baseband data through the millimeter wave radar;
the radar data processing module is used for processing the radar baseband data to obtain target point cloud data, and tracking the target point cloud data to generate a plurality of target tracks;
and the hand waving recognition alarm module is used for carrying out hand waving recognition on the plurality of target tracks to obtain a recognition result, and generating an alarm signal to alarm if the hand waving is in the recognition result.
9. A computer device, characterized in that it comprises a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, implements the steps of the method according to any of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410312918.3A CN117908018A (en) | 2024-03-19 | 2024-03-19 | Method, system, equipment and storage medium for warning waving hand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410312918.3A CN117908018A (en) | 2024-03-19 | 2024-03-19 | Method, system, equipment and storage medium for warning waving hand |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117908018A true CN117908018A (en) | 2024-04-19 |
Family
ID=90697258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410312918.3A Pending CN117908018A (en) | 2024-03-19 | 2024-03-19 | Method, system, equipment and storage medium for warning waving hand |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117908018A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107430189A (en) * | 2015-02-27 | 2017-12-01 | 德州仪器公司 | Recognized using the gesture of frequency modulated continuous wave radar |
| CN111650582A (en) * | 2020-07-27 | 2020-09-11 | 四川长虹电器股份有限公司 | Gesture recognition method based on MIMO millimeter wave radar |
| US20210173046A1 (en) * | 2015-07-17 | 2021-06-10 | Sai Deepika Regani | Method, apparatus, and system for wireless motion recognition |
| US20220252712A1 (en) * | 2019-07-05 | 2022-08-11 | Gree Electric Appliances, Inc. Of Zhuhai | Human Detection Method and Device, Electronic Apparatus and Storage Medium |
| CN115345908A (en) * | 2022-10-18 | 2022-11-15 | 四川启睿克科技有限公司 | Human body posture recognition method based on millimeter wave radar |
| CN115422962A (en) * | 2021-05-12 | 2022-12-02 | 北京算丰征途科技有限公司 | Gesture and gesture recognition method and device based on millimeter wave radar and deep learning algorithm |
| CN115542308A (en) * | 2022-12-05 | 2022-12-30 | 德心智能科技(常州)有限公司 | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar |
| US20230067322A1 (en) * | 2020-04-30 | 2023-03-02 | Huawei Technologies Co., Ltd. | Gesture recognition method and related apparatus |
| CN115877344A (en) * | 2023-02-21 | 2023-03-31 | 南京理工大学 | Radar detection method and system for integrated processing of broadband detection, tracking and identification |
| CN116106855A (en) * | 2023-04-13 | 2023-05-12 | 中国科学技术大学 | Tumble detection method and tumble detection device |
| CN116186580A (en) * | 2022-12-28 | 2023-05-30 | 浙江大学 | Millimeter wave radar point cloud signal gesture recognition method based on manual characteristics |
| CN116593978A (en) * | 2023-03-31 | 2023-08-15 | 厦门精益远达智能科技有限公司 | Gesture detection method, system and storage medium based on point cloud |
| CN116942142A (en) * | 2023-06-08 | 2023-10-27 | 人工智能与数字经济广东省实验室(广州) | Personnel intelligent monitoring method based on millimeter wave radar and related equipment |
| CN117630860A (en) * | 2023-12-25 | 2024-03-01 | 无锡威孚高科技集团股份有限公司 | Gesture recognition method of millimeter wave radar |
| CN117647797A (en) * | 2023-10-20 | 2024-03-05 | 森思泰克河北科技有限公司 | Method and device for correcting short-distance speed of radar, radar and storage medium |
-
2024
- 2024-03-19 CN CN202410312918.3A patent/CN117908018A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107430189A (en) * | 2015-02-27 | 2017-12-01 | 德州仪器公司 | Recognized using the gesture of frequency modulated continuous wave radar |
| US20210173046A1 (en) * | 2015-07-17 | 2021-06-10 | Sai Deepika Regani | Method, apparatus, and system for wireless motion recognition |
| US20220252712A1 (en) * | 2019-07-05 | 2022-08-11 | Gree Electric Appliances, Inc. Of Zhuhai | Human Detection Method and Device, Electronic Apparatus and Storage Medium |
| US20230067322A1 (en) * | 2020-04-30 | 2023-03-02 | Huawei Technologies Co., Ltd. | Gesture recognition method and related apparatus |
| CN111650582A (en) * | 2020-07-27 | 2020-09-11 | 四川长虹电器股份有限公司 | Gesture recognition method based on MIMO millimeter wave radar |
| CN115422962A (en) * | 2021-05-12 | 2022-12-02 | 北京算丰征途科技有限公司 | Gesture and gesture recognition method and device based on millimeter wave radar and deep learning algorithm |
| CN115345908A (en) * | 2022-10-18 | 2022-11-15 | 四川启睿克科技有限公司 | Human body posture recognition method based on millimeter wave radar |
| CN115542308A (en) * | 2022-12-05 | 2022-12-30 | 德心智能科技(常州)有限公司 | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar |
| CN116186580A (en) * | 2022-12-28 | 2023-05-30 | 浙江大学 | Millimeter wave radar point cloud signal gesture recognition method based on manual characteristics |
| CN115877344A (en) * | 2023-02-21 | 2023-03-31 | 南京理工大学 | Radar detection method and system for integrated processing of broadband detection, tracking and identification |
| CN116593978A (en) * | 2023-03-31 | 2023-08-15 | 厦门精益远达智能科技有限公司 | Gesture detection method, system and storage medium based on point cloud |
| CN116106855A (en) * | 2023-04-13 | 2023-05-12 | 中国科学技术大学 | Tumble detection method and tumble detection device |
| CN116942142A (en) * | 2023-06-08 | 2023-10-27 | 人工智能与数字经济广东省实验室(广州) | Personnel intelligent monitoring method based on millimeter wave radar and related equipment |
| CN117647797A (en) * | 2023-10-20 | 2024-03-05 | 森思泰克河北科技有限公司 | Method and device for correcting short-distance speed of radar, radar and storage medium |
| CN117630860A (en) * | 2023-12-25 | 2024-03-01 | 无锡威孚高科技集团股份有限公司 | Gesture recognition method of millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220252712A1 (en) | Human Detection Method and Device, Electronic Apparatus and Storage Medium | |
| CN112401856B (en) | Nursing home monitoring method and system based on millimeter wave radar | |
| CN109275095B (en) | Bluetooth-based indoor positioning system, positioning equipment and positioning method | |
| KR101334190B1 (en) | Method for producing at least information for track fusion and association for radar target tracking, and storage medium thereof | |
| JP2020071226A (en) | Fall detection method and apparatus | |
| CN112184626A (en) | Gesture recognition method, device, equipment and computer readable medium | |
| WO2021248472A1 (en) | Target tracking method and apparatus based on ultra-wideband radar, device, and storage medium | |
| CN114942434B (en) | Fall gesture recognition method and system based on millimeter wave Lei Dadian cloud | |
| CN111142102B (en) | Respiratory data calculation method and related equipment | |
| CN111629339B (en) | User close contact tracking system based on radio frequency technology | |
| CN115542308B (en) | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar | |
| CN110837079B (en) | Target detection method and device based on radar | |
| CN112198507B (en) | Method and device for detecting human body falling features | |
| CN116027324A (en) | Fall detection method and device based on millimeter wave radar and millimeter wave radar equipment | |
| CN114509749A (en) | Indoor positioning detection system and method | |
| CN113854990A (en) | Heartbeat detection method and device | |
| CN113030948A (en) | Fall detection system and method based on target following millimeter wave radar | |
| CN116942142A (en) | Personnel intelligent monitoring method based on millimeter wave radar and related equipment | |
| CN113885022A (en) | Fall detection method and radar equipment | |
| CN115755015A (en) | Method, device, equipment and medium for detecting living body in cabin | |
| CN115291184A (en) | Attitude monitoring method combining millimeter wave radar and deep learning | |
| JP3567906B2 (en) | Radar signal processor | |
| Xie et al. | Lightweight midrange arm-gesture recognition system from mmwave radar point clouds | |
| CN113729674A (en) | Respiration detection method and device | |
| CN117784124A (en) | Millimeter wave radar falling monitoring method and device in multi-person scene |
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 |