CN116509382A - Human body activity intelligent detection method and health monitoring system based on millimeter wave radar - Google Patents
Human body activity intelligent detection method and health monitoring system based on millimeter wave radar Download PDFInfo
- Publication number
- CN116509382A CN116509382A CN202310801059.XA CN202310801059A CN116509382A CN 116509382 A CN116509382 A CN 116509382A CN 202310801059 A CN202310801059 A CN 202310801059A CN 116509382 A CN116509382 A CN 116509382A
- Authority
- CN
- China
- Prior art keywords
- module
- health
- millimeter wave
- wave radar
- human body
- 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
- 230000036541 health Effects 0.000 title claims abstract description 113
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 230000037081 physical activity Effects 0.000 title claims abstract description 28
- 238000010586 diagram Methods 0.000 claims abstract description 73
- 230000004927 fusion Effects 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000000694 effects Effects 0.000 claims description 33
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 239000000779 smoke Substances 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000009545 invasion Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 210000001015 abdomen Anatomy 0.000 claims description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 2
- 230000033001 locomotion Effects 0.000 abstract description 7
- 230000006399 behavior Effects 0.000 abstract description 4
- 230000015654 memory Effects 0.000 description 15
- 239000007789 gas Substances 0.000 description 12
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 7
- 239000008280 blood Substances 0.000 description 7
- 210000004369 blood Anatomy 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 239000001301 oxygen Substances 0.000 description 7
- 229910052760 oxygen Inorganic materials 0.000 description 7
- 230000009471 action Effects 0.000 description 5
- 230000009429 distress Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000005189 cardiac health Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1112—Global tracking of patients, e.g. by using GPS
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/08—Elderly
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Cardiology (AREA)
- Radar, Positioning & Navigation (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a human body activity intelligent detection method and a health monitoring system based on millimeter wave radar, wherein the method comprises the steps of controlling the millimeter wave radar to emit continuous frequency modulation millimeter wave radar signals to a target human body, collecting echo signals, and obtaining a distance-speed diagram and a micro Doppler diagram according to the echo signals; the distance-speed diagram and the micro Doppler diagram are spliced and fused to obtain a fusion diagram; and extracting the characteristics of the fusion graph by using an LSTM network, transmitting the characteristics output by the LSTM network to a full-connection layer network for characteristic classification, and obtaining the target human body activity state. By fusing the distance-speed diagram and the micro Doppler diagram, a plurality of pieces of information with different dimensions can be fused together to provide more comprehensive and rich characteristic information, so that the motion characteristics and the behavior patterns of a target human body can be better captured, and the accuracy of prediction is improved.
Description
Technical Field
The invention relates to the technical field of the Internet of things, in particular to a human body activity intelligent detection method and a health monitoring system based on millimeter wave radar.
Background
The millimeter wave radar technology is used as a wireless sensing technology, has the characteristics of non-contact, real-time and high precision, provides an innovative solution for the monitoring of the elderly, can judge the falling event in real time by detecting the activity state change of the elderly, and sends an emergency notification by being connected to an alarm system or mobile equipment, so that families or nursing staff can take actions rapidly, and the safety of the elderly is ensured. However, the existing human body activity state detection method based on millimeter wave radar signals has the problems of misjudgment and the like caused by insufficient utilization of acquired information and lower algorithm accuracy, and frequent false alarms are caused, so that user experience is greatly influenced.
Disclosure of Invention
In view of the above, the embodiment of the invention provides an intelligent human activity detection method and a health monitoring system based on millimeter wave radar, which are used for solving the problem of misjudgment caused by low activity detection accuracy of old people in the prior art.
In a first aspect, an embodiment of the present invention provides a human body activity intelligent detection method based on a millimeter wave radar, where the method sets the millimeter wave radar at a position at a preset height from the ground, and the method includes:
Controlling the millimeter wave radar to emit continuous frequency modulation millimeter wave radar signals to a target human body and collecting first echo signals;
clutter removal processing is carried out on the first echo signal to obtain a second echo signal;
acquiring a distance-speed diagram according to the second echo signal;
acquiring a micro Doppler image according to the second echo signal;
performing stitching and fusion on the distance-velocity map and the micro Doppler map, and obtaining a fusion map comprises: preprocessing the range-velocity map and the micro-Doppler map so that the range-velocity map and the micro-Doppler map have the same size and characteristic representation; wherein the preprocessing includes any one or more of image resizing, image cropping, image normalization.
The RGB channels of the preprocessed distance-speed diagram and the RGB channels of the preprocessed micro Doppler diagram are spliced to obtain a fusion diagram, the fusion diagram comprises six channels, the first channel to the third channel are RGB channels of the distance-speed diagram, and the fourth channel to the sixth channel are RGB channels of the micro Doppler diagram;
and extracting the characteristics of the fusion map by using an LSTM network, transmitting the characteristics output by the LSTM network to a full-connection layer network for characteristic classification, and obtaining a target human body activity state, wherein the target human body activity state comprises any one or more of stillness, falling, standing, sitting down, walking and waving hands.
Preferably, the clutter removal processing for the first echo signal to obtain a second echo signal includes:
and removing clutter signals from the first echo signals by using a high-pass filter to obtain second echo signals, wherein the clutter signals comprise reflected signals of walls and household devices in a detection environment and noise of a radar.
Preferably, the acquiring a distance-velocity map according to the second echo signal includes:
performing fast Fourier transform on the second echo signal in a fast time domain to obtain an echo spectrum signal;
and performing fast Fourier transform on the echo frequency spectrum signals in a slow time domain to acquire the distance-speed diagram.
Preferably, the acquiring a micro doppler plot according to the second echo signal includes:
performing distance fast Fourier transform on the second echo signal to obtain a distance-time diagram;
and carrying out short-time Fourier transform on the distance-time diagram to obtain the micro Doppler diagram.
Preferably, the feature extraction of the fusion map by using an LSTM network, the feature output by the LSTM network is transferred to a full-connection layer network to perform feature classification, and the obtaining the target human activity state further includes:
Dividing the fusion map into sub-images with equal K; the K equally divided sub-images form a continuous image;
sequentially inputting the continuous images into the LSTM network;
and converging the characteristics output by the LSTM network by using a full connection layer, classifying the characteristics by using a Softmax layer, outputting the probability of each classification, and acquiring the target human activity state according to the probability.
In a second aspect, an embodiment of the present invention provides a millimeter wave radar detection module, where the module includes at least a millimeter wave radar unit and a control unit, where the millimeter wave radar unit is configured to transmit a millimeter wave radar signal to a target human body and receive echo information, and perform analog-to-digital conversion on the echo signal and input the echo signal into the control unit; the control unit is used for controlling the millimeter wave radar unit to transmit or receive signals and acquiring the target human activity state according to the human activity intelligent detection method based on the millimeter wave radar according to the first aspect.
In a third aspect, an embodiment of the present invention provides a health care module, where the health care module at least includes a millimeter wave radar detection module as described in the second aspect, and the health care module detects an activity state of an elderly person through the millimeter wave radar detection module, and when detecting that the activity state of the elderly person is a falling state, the health care module alerts and notifies a family member or a caretaker in time.
In a fourth aspect, embodiments of the present invention provide a healthcare system, the system comprising: the health care module, the health monitoring module, the health life module, the health help calling module, the health daemon module, the intelligent main control center module, the intelligent endowment cloud platform and the terminal module according to the third aspect, wherein the health care module, the health monitoring module, the health life module, the health help calling module and the health daemon module are connected with the intelligent main control center module, and the intelligent endowment cloud platform is respectively connected with the intelligent main control center module and the terminal module; the health care module is used for monitoring whether the old people normally move through the millimeter wave radar detection module, and the health life module is used for monitoring whether the old people are in a health state through the intelligent wearing equipment; the healthy living module is used for judging whether the old is in a normal living mode according to water flow detection; the health help calling module is used for calling for help to family members in time through help calling equipment when the old people go out dangerous conditions; the health daemon module is used for acquiring and reporting security information such as stranger invasion, dense smoke alarm, gas leakage and the like; the intelligent main control center module analyzes and processes the data collected by the health care module, the health life module, the health help calling module and the health daemon module or sends the data to the intelligent endowment cloud platform for analysis and processing, and the result is fed back to the terminal module through the intelligent endowment cloud platform.
In summary, the beneficial effects of the invention are as follows:
the human body activity intelligent detection method based on the millimeter wave radar provided by the embodiment of the invention is characterized in that the millimeter wave radar is controlled to emit continuous frequency modulation millimeter wave radar signals to a target human body, echo signals are collected, and a distance-speed diagram and a micro Doppler diagram are obtained according to the echo signals; the distance-speed diagram and the micro Doppler diagram are spliced and fused to obtain a fusion diagram; and extracting the characteristics of the fusion graph by using an LSTM network, transmitting the characteristics output by the LSTM network to a full-connection layer network for characteristic classification, and obtaining the target human body activity state. By fusing the distance-speed diagram and the micro Doppler diagram, a plurality of pieces of information with different dimensions can be fused together to provide more comprehensive and rich characteristic information, so that the motion characteristics and the behavior patterns of a target human body can be better captured, and the accuracy of prediction is improved.
The health monitoring system provided by the embodiment of the invention comprises: the intelligent care cloud platform is connected with the intelligent main control center module respectively, and the intelligent care cloud platform is connected with the terminal module. The system can collect the health state information of the old people in real time and generate an analysis report, so that the activity monitoring, the positioning monitoring, the heart rate monitoring, the emergency help seeking, the water use monitoring and the health monitoring of the old people are realized, help seeking information is sent out and families are informed when abnormal conditions and emergency conditions are met, and the life health safety of the old people can be protected in real time without excessively depending on manpower.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described, and it is within the scope of the present invention to obtain other drawings according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an embodiment of the present invention in which a millimeter wave radar is provided.
Fig. 2 is a schematic flow chart of a human body activity intelligent detection method based on millimeter wave radar according to an embodiment of the invention.
Fig. 3 is a schematic structural diagram of a millimeter wave radar monitoring module according to an embodiment of the present invention.
Fig. 4 is a hardware schematic of a millimeter wave radar unit according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a healthcare system according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an intelligent master control center module according to an embodiment of the invention.
Description of the embodiments
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely configured to illustrate the invention and are not configured to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the invention by showing examples of the invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
Example 1
The embodiment of the invention provides a human body activity intelligent detection method based on millimeter wave radar, which is suitable for application scenes of monitoring daily activities of old people indoors in home, community care centers or old people care centers. The method adopts millimeter wave radar for detection, the millimeter wave radar is arranged at the top of living room, bedroom, bathroom, kitchen and the like or at a position with preset height from the ground of a room, preferably, as shown in fig. 1, the radar is arranged at the height H, the radar projects wave beams from top to bottom, the radius of the maximum coverage area is R, and when a target human body such as the old is movable or stationary in the maximum coverage area, the activity monitoring of the target human body can be realized. Preferably, H is 2.4 to 3 meters.
Referring to fig. 2, the method includes:
s1, controlling the millimeter wave radar to emit continuous frequency modulation millimeter wave radar signals to a target human body and collecting first echo signals;
s2, clutter removal processing is carried out on the first echo signal to obtain a second echo signal;
s3, acquiring a distance-speed diagram according to the second echo signal;
s4, acquiring a micro Doppler image according to the second echo signal;
s5, splicing and fusing the distance-speed diagram and the micro Doppler diagram to obtain a fusion diagram;
and S6, carrying out feature extraction on the fusion map by using an LSTM network, transmitting the features output by the LSTM network to a full-connection layer network for feature classification, and obtaining a target human body activity state, wherein the target human body activity state comprises any one or more of stillness, falling, standing, sitting, walking and waving.
Specifically, the millimeter wave radar is controlled to emit continuous frequency modulation millimeter wave radar signals, the radar signals can generate echo signals (marked as first echo signals) through target human bodies and objects in the surrounding environment, such as walls, furniture, home appliances and the like, in order to enable detection accuracy to be higher, clutter is firstly removed from the first echo signals to obtain purer target human body echo signals when signal processing is carried out, the purer target human body echo signals are marked as second echo signals, the second echo signals are subjected to Fourier transformation in a fast time domain and a slow time domain to obtain a distance-speed diagram and a micro Doppler diagram, in order to obtain multi-dimensional characteristic information, in the embodiment of the invention, the two types of images are subjected to splicing and fusion processing, then time sequence information of the fusion diagram is extracted by utilizing an LSTM network (LSTM is an abbreviation of Long Short Term Memory, namely a long-short-term memory recurrent neural network), and characteristic classification is achieved by utilizing a full-connection layer network, and therefore the activity state of a target human body is obtained.
Preferably, a dataset of human activity states is constructed to train the LSTM network to obtain more accurate results. In one embodiment, a data set of a human body activity state test can use the existing disclosed data set, and can also be acquired and tidied by itself, in the embodiment of the invention, a tester performs actions such as standing, falling, standing, sitting, walking, waving and the like in different environments (such as a living room, a bedroom, a kitchen, a bathroom and the like) for a plurality of times to acquire acquired data to obtain an original data set, images of the original data set are respectively processed into a distance-speed diagram and a micro Doppler diagram with uniform sizes, the distance-speed diagram and the micro Doppler diagram are spliced to obtain a fusion diagram, and the fusion diagram is randomly grouped according to the human body activity state category to obtain N sample subsets. Wherein the number of samples in each sample subset is close and the proportion of samples of each class is the same as in the original data set. And selecting N-1 subsets each time as a training set, and using the rest subset for testing, so as to perform N-fold cross validation, and using the trained LSTM network for detection and analysis of the subsequent target human body activity state. LSTM network training is prior art and will not be described in detail herein.
Preferably, the clutter removal processing for the first echo signal to obtain a second echo signal includes: and removing clutter signals from the first echo signals by using a high-pass filter to obtain second echo signals, wherein the clutter signals comprise reflected signals of walls and household devices in a detection environment and noise of a radar. The high-pass filter may be a butt Wo Sigao pass filter, a gaussian high-pass filter, a moving average filter, or the like, and may be selected according to the actual situation, again without limitation. The high pass filter attenuates or removes energy from the output signal by reducing the amplitude of the low frequency signal. The acquired original echo signals are recorded as first echo signals, static clutter caused by objects such as walls, furniture and household appliances in the first echo signals is filtered by using a high-pass filter, and echo signals subjected to clutter removal processing are recorded as second echo signals.
Preferably, the acquiring a distance-velocity map according to the second echo signal includes:
performing fast Fourier transform on the second echo signal in a fast time domain to obtain an echo spectrum signal;
and performing fast Fourier transform on the echo frequency spectrum signals in a slow time domain to acquire the distance-speed diagram.
Specifically, a second echo signal, i.e. a coherent processing interval, is collected over a certain time. Performing distance compression on the collected second echo signals using a pulse compression technique (e.g., matched filtering) to enhance signal-to-noise ratio and increase distance resolution; performing a Fast Fourier Transform (FFT) on each pulse signal within the coherence processing interval along a distance dimension (fast time domain), which converts the echo signal in the time domain into the frequency domain, and the converted signal is denoted as an echo spectrum signal; after the first FFT, another FFT is performed in the slow time domain, converting the distance-time spectrum into the distance-speed domain. This second FFT is called velocity conversion or doppler processing, so that a distance-velocity map can be obtained showing the distribution of the target body in both the distance and velocity dimensions. The information in the range-velocity map helps to detect moving objects, estimate their velocity, and distinguish them from clutter or stationary objects in the radar scene.
Preferably, the acquiring a micro doppler plot according to the second echo signal includes:
performing distance fast Fourier transform on the second echo signal to obtain a distance-time diagram;
and carrying out short-time Fourier transform on the distance-time diagram to obtain the micro Doppler diagram.
Specifically, the distance fourier transform is mainly used for extracting distance information in the second echo signal, and converting the time domain signal into a distance domain signal, so that the intensity distribution condition of the target human body on different distances can be obtained. After the distance fast Fourier transform is carried out on the second echo signal to obtain a distance-time diagram, short-time Fourier transform is carried out, the short-time Fourier transform is mainly used for analyzing the signal in the time domain, and the time-frequency characteristic of the signal can be obtained by segmenting the signal and carrying out Fourier transform on each time segment. The micro Doppler graph shows the speed distribution of the target human body at different distances and times, thereby providing the motion characteristics of the target human body. It should be noted that when the echo signal is subjected to the distance fourier transform and the short-time fourier transform, the window length, the overlapping proportion and the fourier transform parameters can be selected appropriately according to the actual situation so as to obtain an accurate micro doppler image.
Preferably, the performing stitching and fusion on the distance-velocity map and the micro doppler map, and obtaining a fusion map includes:
preprocessing the range-velocity map and the micro-Doppler map so that the range-velocity map and the micro-Doppler map have the same size and characteristic representation; wherein the preprocessing includes any one or more of image resizing, image cropping, image normalization.
And splicing the RGB channels of the preprocessed distance-speed diagram and the RGB channels of the preprocessed micro Doppler diagram to obtain the fusion diagram, wherein the fusion diagram comprises six channels, the first channel to the third channel are the RGB channels of the distance-speed diagram, and the fourth channel to the sixth channel are the RGB channels of the micro Doppler diagram.
In particular, the range-velocity map and the micro-doppler map are preprocessed to ensure that they have the same size and characteristic representation. The preprocessing comprises the operations of image size adjustment, image clipping, image normalization and the like. One or more of the pretreatment methods may be selected as needed to provide the range-to-velocity map and the micro-doppler map with the same size and numerical range. And splicing the RGB channels of the preprocessed distance-speed diagram and the RGB channels of the preprocessed micro Doppler diagram. Specifically, the red, green and blue channels of the distance-velocity map are spliced together with the red, green and blue channels of the micro-Doppler map to form a fusion map. Thus, the fusion map will include six channels, with the first three channels corresponding to the RGB channels of the distance-velocity map and the last three channels corresponding to the RGB channels of the micro Doppler map; further, the fusion map is visually displayed. The use of an image processing tool or library to display and save the fusion map ensures that the resulting image can reveal both range-velocity information and micro-doppler information. A fusion map of six channels will provide more comprehensive characteristic information including information in the dimensions of distance, velocity, and micro-doppler frequency.
Preferably, the feature extraction of the fusion map by using an LSTM network, the feature output by the LSTM network is transferred to a full-connection layer network to perform feature classification, and the obtaining the target human activity state further includes:
dividing the fusion map into sub-images with equal K; the K equally divided sub-images form a continuous image;
sequentially inputting the continuous images into the LSTM network;
and converging the characteristics output by the LSTM network by using a full connection layer, classifying the characteristics and the probability of each classification by using a Softmax layer, and acquiring the target human body activity state according to the probability.
Specifically, the fusion map is equally divided into sub-images with K equal divisions: the fusion map is divided into K equally divided sub-images, and each sub-image is ensured to have the same size and characteristic representation. The fusion map may be divided into K sub-images using an image processing method. The K sub-images are sequentially formed into a sequence of successive images, forming a successive image. Thus, each sub-image in the successive image represents a feature over a period of time. Successive images are sequentially input into the LSTM network. The LSTM network will time-sequence model the sequence of consecutive images, capturing the time-sequence information in the sequence of images. Output features of the LSTM network are extracted, which capture timing features and context information in the image sequence. Typically, the output of an LSTM network is a sequence of feature vectors, each representing a feature of the input sequence of successive images over a period of time. And inputting the feature vector sequence output by the LSTM network into the full-connection layer network for feature aggregation and processing. The full connectivity layer network may include a plurality of full connectivity layers and activation functions for extracting and combining feature information. Feature classification using Softmax layer: and adding a Softmax layer at the end of the fully connected layer network, which is used for classifying the feature vectors into different human body activity states and outputting probability distribution of each state. According to the probability distribution output by the Softmax layer, the human body activity state with the highest probability is selected as the final classification result.
In summary, according to the human body activity state detection method based on the millimeter wave radar, the distance-speed diagram and the micro Doppler diagram are fused, so that two pieces of information with different dimensions can be fused together, and more comprehensive and rich characteristic information can be provided. The distance-velocity map provides information about the position and velocity of movement of the target body, while the micro-doppler map provides information about the direction and frequency of movement of the target body. By fusing the pair dimension information, the motion characteristics and the behavior patterns of the target human body can be better captured, so that the accuracy of prediction is improved. Each pixel point in the fusion map contains characteristic information of multiple dimensions such as distance, speed, doppler frequency and the like, so that the model can more comprehensively understand and analyze the motion behaviors of a target human body. By comprehensively considering the characteristic information, the prediction model can more accurately judge the activity state of the target human body, such as falling, walking, stillness and the like.
Example two
Based on the above embodiment, as shown in fig. 3, the embodiment of the invention provides a millimeter wave radar detection module, which comprises at least a millimeter wave radar unit and a control unit, wherein the millimeter wave radar unit is used for transmitting millimeter wave radar signals to a target human body and receiving echo information, and the echo signals are input into the control unit after analog-to-digital conversion; the control unit is used for controlling the millimeter wave radar unit to transmit or receive signals and acquiring the target human activity state according to the human activity intelligent detection method based on the millimeter wave radar according to the first embodiment. Fig. 4 is a schematic diagram of hardware of a millimeter wave radar unit used in an embodiment of the present invention.
Example III
Based on the first embodiment and the second embodiment, the embodiment of the present invention provides a health care module, which at least includes a millimeter wave radar detection module as described in the second embodiment, wherein the health care module detects an activity state of an old person through the millimeter wave radar detection module, and when detecting that the activity state of the old person is a falling state, the health care module timely alerts and notifies a family member or a care personnel.
Example IV
Based on the first to third embodiments, referring to fig. 5, an embodiment of the present invention provides a health monitoring system, which includes: the health care module, the health monitoring module, the health life module, the health help calling module, the health daemon module, the intelligent main control center module, the intelligent endowment cloud platform and the terminal module according to the third embodiment, wherein the health care module, the health monitoring module, the health life module, the health help calling module and the health daemon module are connected with the intelligent main control center module, and the intelligent endowment cloud platform is respectively connected with the intelligent main control center module and the terminal module; the health care module is used for monitoring whether the old people normally move through the millimeter wave radar detection module according to the second embodiment, and the health life module is used for monitoring whether the old people are in a health state through the intelligent wearable equipment; the healthy living module is used for judging whether the old is in a normal living mode according to water flow detection; the health help calling module is used for calling for help to family members in time through help calling equipment when the old people go out dangerous conditions; the health daemon module is used for acquiring and reporting security information such as stranger invasion, dense smoke alarm, gas leakage and the like.
As shown in fig. 5, the health care module, the health life module, the health help calling module and the health daemon module are in communication with the intelligent control center module in a wireless or wired manner, these modules send collected information and data such as image data, heart rate data and the like to the intelligent main control center module in a wired or wireless manner, the intelligent main control center module is connected with the intelligent care cloud platform, some simple data processing can be performed in the intelligent main control center module, and corresponding some complex data processing can be sent to the intelligent care cloud platform for processing, and data or instructions obtained after processing by the intelligent care cloud platform are transmitted to the health care module, the health life module, the health care module and the health care daemon module.
In addition, the intelligent pension cloud platform is communicated with the terminal module in a wireless or wired mode. The terminal module can be the terminal equipment of smart mobile phone, panel computer, PC, and intelligent care cloud platform future intelligent master control center module sends to the terminal module from health care module, health detection module, healthy life module, health call for help module and health daemon after the information in the module is handled, and the terminal module can try to look over the condition such as old man's health state, active state, living state and life state, receives unusual alarm information or removes unusual alarm information etc.. In the same way, the terminal module can also feed back information to the intelligent main control center module, and further feeds back the information to the corresponding health care module, the health detection module, the health life module, the health distress module and the health daemon module.
In one embodiment, the health care module may further include an image acquisition unit or a human body presence detection unit in addition to the millimeter wave radar detection module, where the image acquisition unit acquires the activity state of the old through acquiring daily activity pictures of the old by controlling the image acquisition device, monitors whether the old has no activity for a long time, and when the activity state of the old is abnormal or the old has no activity for a long time, sends yellow alarm information to the terminal module, and if the terminal module does not reply in a preset time, automatically dials a telephone of a preset emergency contact person, thereby notifying a family of the old to view the status of the old in time. The image acquisition device may be a monocular camera, a binocular camera or the like. The human body presence detection unit detects whether the old people move or not and monitors the abdomen and chest expansion of the old people caused by breathing by controlling the human body presence sensor, and when the monitoring data is abnormal, for example, the abdomen or chest expansion of the old people is monitored to be different from the normal state, the red alarm is sent to the terminal module and the emergency contact person phone is immediately dialed, so that the family is informed in time to check the body state of the old people.
In one embodiment, the health monitoring module comprises a heart rate monitoring unit and a blood oxygen detecting unit, wherein the heart rate monitoring module monitors the heart rate of the old through controlling the intelligent wearing equipment in real time, monitors the heart rate of the old during exercise and sleeping, reports related data to the intelligent endowment cloud platform, and sends an analysis result of the intelligent endowment cloud platform to the intelligent wearing equipment and the terminal module so as to facilitate the old or the family thereof to check whether the heart rate of the old is normal; the intelligent wearing equipment can be an intelligent bracelet or an intelligent watch, the intelligent bracelet can be used for dual positioning through a GPS satellite and an LBS base station, the position information of the old can be obtained in real time, the heart rate condition of the old in activities such as sports, sleeping, housework and walking is detected in real time, data analysis and health prediction are carried out from the collected heart rate data to an intelligent endowment cloud platform end, if the heart health state of the old is estimated according to the currently collected data and a prediction model, reminding or alarm information is timely sent to the intelligent bracelet or the intelligent watch to remind the old to pay attention once the heart rate of the old is abnormal, and the heart rate data is sent to a terminal module to remind the family to pay attention. The blood oxygen monitoring module monitors the blood oxygen concentration of the old through controlling the blood oxygen measuring instrument, the blood oxygen measuring instrument feeds back the measurement result to the old, meanwhile, the blood oxygen measuring instrument can send relevant data to the intelligent endowment cloud platform, and the analysis result of the intelligent endowment cloud platform is sent to the terminal module so as to facilitate the family to check whether the blood oxygen concentration of the old is normal.
In one embodiment, the healthy living module uploads information such as water consumption and water habit in the old people's home to the intelligent pension cloud platform through recording, the intelligent pension cloud platform judges whether the old people's living is unusual according to current water consumption, and when abnormality occurs, an alarm is sent to the terminal module. The intelligent watch can acquire average daily water consumption of the old people, data of water consumption habits such as water consumption of a water consumption time period and water consumption of each water consumption time period are uploaded to the intelligent endowment cloud platform, the intelligent endowment cloud platform summarizes and analyzes the daily water consumption habits of the old people according to the data and sends the data to the terminal module, so that families can conveniently check the water consumption condition of the old people in real time and check the water consumption analysis report of the old people, when no water is used or the water consumption is abnormal in a preset time period, the water consumption abnormality alarm can be prompted, whether the old people cannot get up or cannot move to cause the water consumption condition is judged, and the families are informed to process in time. Besides detecting water consumption habit, the intelligent water consumption device can also detect whether water consumption is excessive, for example, water leakage or water tap failure and other conditions can cause the water consumption to be excessive, and when the water consumption is excessive, the old is informed by an intelligent bracelet, an intelligent watch, an intelligent mobile phone and the like carried by the old in time, or a terminal module is used for informing families to process.
In one embodiment, the health distress module comprises a one-key alarm unit or a voice alarm unit, wherein the one-key alarm unit is used for sending distress information to families by pressing an alarm when the old falls down or abnormal conditions occur, and the voice alarm unit is used for sending distress information to families by speaking distress instructions to an intelligent voice sound box when the old falls down and cannot be flicked. By way of example, when the old person in the sole falls carelessly and cannot walk, help seeking information can be sent to police or families by pressing alarm equipment such as a key alarm, and under more serious conditions, when the old person cannot play due to falling, help seeking instructions can be sent to the intelligent voice sound box, and the help seeking instructions can be sent to the terminal module to enable the families to know the dangerous condition of the old person, so that help can be timely carried out.
In one embodiment, the health daemon system comprises an infrared detection unit, a door and window detection unit, a smoke detection unit and a gas detection unit, wherein the infrared detection unit is used for sending help seeking information to families when sensing invasion of strangers through an infrared sensor and notifying the families of timely rescue; the door and window detection unit is used for sending help seeking information to family members when strangers want to enter the room through the door and the window, notifying the family members that the old is possibly threatened, and sending alarm signals such as alarm sounds to frighten the strangers; the smoke detection unit is used for sending an alarm to inform the old people and sending help seeking information to the families when the smoke sensor detects dense smoke, and informing the old people that the place is possible or the fire disaster is normally sent to be needed to leave in time; when the old people forget to turn off the gas or the gas and send the gas or the gas to leak, an alarm is sent out to inform the old people of the gas leakage danger and inform the old people of timely leaving when the gas sensor in the gas detection module detects that the gas or the gas content in the air is larger than a certain value, so that safety accidents are avoided, and the safety of the old people is ensured.
In summary, the health monitoring system provided by the embodiment of the invention realizes the functions of activity detection, positioning detection, heart rate detection, residence detection, emergency help seeking, water use detection, health detection and the like of the old in the home life through the health care module, the health monitoring module, the health life module, the health help calling module, the health protection module and the like, and the intelligent main control center module can collect the health state information of the old in real time, generate an analysis report, remind the old of abnormal conditions and physical health conditions, send help seeking information and inform families when encountering abnormal conditions and emergency, and can protect the life health safety of the old in real time without relying on manpower by collecting information from the health care module, the health monitoring module, the health life module, the health help calling module and the health protection module to the intelligent care cloud platform for data analysis processing.
Example five
In addition, fig. 6 shows a schematic hardware structure of the intelligent master control center module according to the embodiment of the invention.
The intelligent centre of control module may comprise a processor 301 and a memory 302 in which computer program instructions are stored.
In particular, the processor 301 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.
Memory 302 may include mass storage for data or instructions. By way of example, and not limitation, memory 302 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 302 may include removable or non-removable (or fixed) media, where appropriate. Memory 302 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In particular embodiments, memory 302 includes Read Only Memory (ROM). The ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these, where appropriate.
In one example, the intelligent hub module may also include a communication interface 303 and a bus 310. As shown in fig. 6, the processor 301, the memory 302, and the communication interface 303 are connected to each other by a bus 310 and perform communication with each other.
The communication interface 303 is mainly used to implement communication between each module, device, unit and/or apparatus in the embodiment of the present invention.
Bus 310 includes hardware, software, or both, coupling the components of the intelligent hub module to each other. By way of example, and not limitation, bus 310 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. Bus 310 may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.
Claims (10)
1. The human body activity intelligent detection method based on the millimeter wave radar is characterized in that the millimeter wave radar is arranged at a position with a preset height from the ground, and the method comprises the following steps:
controlling the millimeter wave radar to emit continuous frequency modulation millimeter wave radar signals to a target human body and collecting first echo signals;
clutter removal processing is carried out on the first echo signal to obtain a second echo signal;
acquiring a distance-speed diagram according to the second echo signal;
acquiring a micro Doppler image according to the second echo signal;
and performing splicing and fusion on the distance-speed diagram and the micro Doppler diagram to obtain a fusion diagram, wherein the method comprises the following steps of: preprocessing the range-velocity map and the micro-Doppler map to enable the range-velocity map and the micro-Doppler map to have the same size and characteristic representation, wherein the preprocessing comprises any one or more of image resizing, image cropping and image normalization; the RGB channels of the preprocessed distance-speed diagram and the RGB channels of the preprocessed micro Doppler diagram are spliced to obtain a fusion diagram, the fusion diagram comprises six channels, the first channel to the third channel are RGB channels of the distance-speed diagram, and the fourth channel to the sixth channel are RGB channels of the micro Doppler diagram;
And extracting the characteristics of the fusion map by using an LSTM network, transmitting the characteristics output by the LSTM network to a full-connection layer network for characteristic classification, and obtaining a target human body activity state, wherein the target human body activity state comprises any one or more of stillness, falling, standing, sitting down, walking and waving hands.
2. The method for intelligent detection of human activity based on millimeter wave radar according to claim 1, wherein the acquiring a distance-velocity map from the second echo signal comprises:
performing fast Fourier transform on the second echo signal in a fast time domain to obtain an echo spectrum signal;
and performing fast Fourier transform on the echo frequency spectrum signals in a slow time domain to acquire the distance-speed diagram.
3. The method for intelligently detecting human body activity based on millimeter wave radar according to claim 1, wherein the step of acquiring a micro doppler map from the second echo signal comprises:
performing distance fast Fourier transform on the second echo signal to obtain a distance-time diagram;
and carrying out short-time Fourier transform on the distance-time diagram to obtain the micro Doppler diagram.
4. The intelligent human body activity detection method based on millimeter wave radar according to any one of claims 1-3, wherein the feature extraction is performed on the fusion map by using an LSTM network, the features output by the LSTM network are transferred to a full-connection layer network for feature classification, and the obtaining the target human body activity state further comprises:
Dividing the fusion map into sub-images with equal K; the K equally divided sub-images form a continuous image;
sequentially inputting the continuous images into the LSTM network;
and converging the characteristics output by the LSTM network by using a full connection layer, classifying the characteristics by using a Softmax layer, outputting the probability of each classification, and acquiring the target human activity state according to the probability.
5. The method for intelligently detecting human activity based on millimeter wave radar according to any one of claims 1 to 3, wherein the performing clutter removal processing on the first echo signal to obtain a second echo signal includes:
and removing clutter signals from the first echo signals by using a high-pass filter to obtain second echo signals, wherein the clutter signals comprise reflected signals of walls and household devices in a detection environment and noise of a radar.
6. The millimeter wave radar detection module is characterized by comprising at least a millimeter wave radar unit and a control unit, wherein the millimeter wave radar unit is used for transmitting millimeter wave radar signals to a target human body and receiving echo information, and the echo signals are input into the control unit after analog-to-digital conversion; the control unit is used for controlling the millimeter wave radar unit to transmit or receive signals and acquiring the target human activity state according to the human activity intelligent detection method based on the millimeter wave radar as claimed in any one of claims 1 to 5.
7. A health care module, characterized in that, health care module includes at least one millimeter wave radar detection module according to claim 6, and health care module passes through the millimeter wave radar detection module detects old man's active state, alerts when detecting that old man's active state is the state of tumbleing.
8. A healthcare system, the system comprising: the health care module, health monitoring module, health life module, health help calling module, health daemon module, intelligent master control center module, intelligent care cloud platform and terminal module of claim 7, wherein the health care module, health monitoring module, health life module, health help calling module, health daemon module are connected with the intelligent master control center module, the intelligent care cloud platform is connected with the intelligent master control center module and the terminal module respectively; the health care module is used for monitoring whether the old people normally move through the millimeter wave radar detection module, and the health life module is used for monitoring whether the old people are in a health state through the intelligent wearing equipment; the healthy living module is used for judging whether the old is in a normal living mode according to water flow detection; the health help calling module is used for calling for help to family members in time through help calling equipment when the old people go out dangerous conditions; the health daemon module is used for acquiring and reporting stranger invasion information, dense smoke alarm information and gas leakage information; the intelligent main control center module analyzes and processes the data collected from the health care module, the health life module, the health help calling module and the health daemon module or sends the data to the intelligent endowment cloud platform for analysis and processing, and the result is fed back to the terminal module through the intelligent endowment cloud platform.
9. The health care system according to claim 8, wherein the health care module comprises an image acquisition unit and/or a human body presence detection unit, wherein the image acquisition unit acquires the activity state of the old people by controlling the image acquisition device, monitors whether the old people are inactive for a long time, and when the old people are inactive for a long time, sends yellow alarm information to the terminal module, and when the terminal module does not reply within a preset time, automatically dials a telephone of a preset emergency contact; the human body presence detection unit detects whether the old people move or not and monitors the abdomen and chest expansion of the old people caused by breathing by controlling the human body presence sensor, and when the monitored data are abnormal, the human body presence detection unit sends a red alarm to the terminal module and immediately dials an emergency contact phone.
10. The healthcare system according to claim 8 or 9, wherein the terminal module comprises any one or more of a smart phone, a tablet computer, and a PC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310801059.XA CN116509382A (en) | 2023-07-03 | 2023-07-03 | Human body activity intelligent detection method and health monitoring system based on millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310801059.XA CN116509382A (en) | 2023-07-03 | 2023-07-03 | Human body activity intelligent detection method and health monitoring system based on millimeter wave radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116509382A true CN116509382A (en) | 2023-08-01 |
Family
ID=87392553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310801059.XA Pending CN116509382A (en) | 2023-07-03 | 2023-07-03 | Human body activity intelligent detection method and health monitoring system based on millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116509382A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003006337A (en) * | 2001-06-26 | 2003-01-10 | Matsushita Electric Works Ltd | Remote supporting system for the aged and person in need of care |
| JP2013020574A (en) * | 2011-07-14 | 2013-01-31 | Cosmo Life Kk | House state confirmation system |
| CN106772373A (en) * | 2016-12-15 | 2017-05-31 | 西安电子科技大学 | For the SAR imaging methods of any ground moving object |
| CN107016818A (en) * | 2017-06-06 | 2017-08-04 | 上海泛亿信息科技有限公司 | A kind of old man's physical condition intelligent and safe monitoring system |
| JP2017224293A (en) * | 2016-06-15 | 2017-12-21 | 志明 陳 | Elderly symptom analysis system based on water consumption |
| CN107656255A (en) * | 2017-10-25 | 2018-02-02 | 中国人民解放军国防科技大学 | Ultra-wideband radar moving target two-dimensional positioning method based on multipath echoes |
| CN110109091A (en) * | 2019-05-23 | 2019-08-09 | 中国人民解放军战略支援部队信息工程大学 | A kind of passive radar method for parameter estimation and device for high-speed target |
| KR102116405B1 (en) * | 2019-01-03 | 2020-06-05 | (주) 모인온 | Intelligent system and method for checking safety of the elderly living alone |
| KR20200139984A (en) * | 2019-06-05 | 2020-12-15 | 주식회사 에이치앤디에스 | Management system for elderly people living alone based on ultra-wideband impluse-radio |
| WO2022117120A1 (en) * | 2021-04-22 | 2022-06-09 | 青岛海尔空调器有限总公司 | Bathroom safety control system and air conditioner |
| CN114895275A (en) * | 2022-05-20 | 2022-08-12 | 中国人民解放军国防科技大学 | Radar micro-motion gesture recognition method based on efficient multi-dimensional attention neural network |
| CN115761736A (en) * | 2022-11-29 | 2023-03-07 | 长安大学 | Underground cavity intelligent detection method and system based on multi-dimensional ground penetrating radar image |
-
2023
- 2023-07-03 CN CN202310801059.XA patent/CN116509382A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003006337A (en) * | 2001-06-26 | 2003-01-10 | Matsushita Electric Works Ltd | Remote supporting system for the aged and person in need of care |
| JP2013020574A (en) * | 2011-07-14 | 2013-01-31 | Cosmo Life Kk | House state confirmation system |
| JP2017224293A (en) * | 2016-06-15 | 2017-12-21 | 志明 陳 | Elderly symptom analysis system based on water consumption |
| CN106772373A (en) * | 2016-12-15 | 2017-05-31 | 西安电子科技大学 | For the SAR imaging methods of any ground moving object |
| CN107016818A (en) * | 2017-06-06 | 2017-08-04 | 上海泛亿信息科技有限公司 | A kind of old man's physical condition intelligent and safe monitoring system |
| CN107656255A (en) * | 2017-10-25 | 2018-02-02 | 中国人民解放军国防科技大学 | Ultra-wideband radar moving target two-dimensional positioning method based on multipath echoes |
| KR102116405B1 (en) * | 2019-01-03 | 2020-06-05 | (주) 모인온 | Intelligent system and method for checking safety of the elderly living alone |
| CN110109091A (en) * | 2019-05-23 | 2019-08-09 | 中国人民解放军战略支援部队信息工程大学 | A kind of passive radar method for parameter estimation and device for high-speed target |
| KR20200139984A (en) * | 2019-06-05 | 2020-12-15 | 주식회사 에이치앤디에스 | Management system for elderly people living alone based on ultra-wideband impluse-radio |
| WO2022117120A1 (en) * | 2021-04-22 | 2022-06-09 | 青岛海尔空调器有限总公司 | Bathroom safety control system and air conditioner |
| CN114895275A (en) * | 2022-05-20 | 2022-08-12 | 中国人民解放军国防科技大学 | Radar micro-motion gesture recognition method based on efficient multi-dimensional attention neural network |
| CN115761736A (en) * | 2022-11-29 | 2023-03-07 | 长安大学 | Underground cavity intelligent detection method and system based on multi-dimensional ground penetrating radar image |
Non-Patent Citations (2)
| Title |
|---|
| 许向阳等: "FMCW毫米波雷达跌倒检测算法研究", 软件工程, vol. 26, no. 5, pages 6 - 10 * |
| 郑志远: "基于FMCW雷达的人体跌倒检测方法研究", 中国优秀硕士学位论文全文数据库 信息科技辑(月刊), no. 02, pages 136 - 1640 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734055B (en) | Abnormal person detection method, device and system | |
| US10485452B2 (en) | Fall detection systems and methods | |
| CN110192862B (en) | Radar-based non-contact human body respiration detection method and device | |
| Maitre et al. | Fall detection with UWB radars and CNN-LSTM architecture | |
| Gjoreski et al. | Accelerometer placement for posture recognition and fall detection | |
| Tabar et al. | Smart home care network using sensor fusion and distributed vision-based reasoning | |
| Chaudhuri et al. | Fall detection devices and their use with older adults: a systematic review | |
| JP5991388B2 (en) | Safety monitoring device | |
| US9710761B2 (en) | Method and apparatus for detection and prediction of events based on changes in behavior | |
| CN109765539A (en) | Indoor user behavior monitoring method and apparatus, electrical equipment and home furnishing monitoring system | |
| CN113925475B (en) | Non-contact human health monitoring system and monitoring method | |
| CN110197732B (en) | Remote health monitoring system, method and equipment based on multiple sensors | |
| CN106652346A (en) | Home-based care monitoring system for old people | |
| CN113397520B (en) | Information detection method and device for indoor object, storage medium and processor | |
| WO2015077829A1 (en) | System for monitoring subject movement | |
| CN110675596B (en) | Fall detection method applied to wearable terminal | |
| US9852620B1 (en) | System and method for detecting sound and performing an action on the detected sound | |
| CN107909771A (en) | A kind of personnel's tumble alarm system and its implementation based on wireless sensor network | |
| CN110210739B (en) | Nuclear radiation detection method and system based on artificial intelligence | |
| CN114446026B (en) | Article forgetting reminding method, corresponding electronic equipment and device | |
| KR20150114373A (en) | Appartus and method for monitoring security using variation of correlation coefficient pattern in sound field spectra | |
| CN109561855A (en) | Equipment, system and method for fall detection | |
| Diep et al. | A classifier based approach to real-time fall detection using low-cost wearable sensors | |
| CN116509382A (en) | Human body activity intelligent detection method and health monitoring system based on millimeter wave radar | |
| Guo et al. | Emergency semantic feature vector extraction from WiFi signals for in-home monitoring of elderly |
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 |