CN117784124A - Millimeter wave radar falling monitoring method and device in multi-person scene - Google Patents
Millimeter wave radar falling monitoring method and device in multi-person scene Download PDFInfo
- Publication number
- CN117784124A CN117784124A CN202311836517.XA CN202311836517A CN117784124A CN 117784124 A CN117784124 A CN 117784124A CN 202311836517 A CN202311836517 A CN 202311836517A CN 117784124 A CN117784124 A CN 117784124A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- millimeter wave
- monitoring
- target
- wave 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012806 monitoring device Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 2
- 230000003111 delayed effect Effects 0.000 claims description 2
- 238000002592 echocardiography Methods 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a millimeter wave radar falling monitoring method and a monitoring device under a multi-person scene, wherein the monitoring method comprises the following steps: 1. monitoring human body actions by utilizing millimeter wave radar to emit frequency modulation continuous waves, and generating point cloud information by carrying out signal processing and data reconstruction on received echo signals; 2. denoising and clustering the point cloud data by using a spatial clustering algorithm based on density to obtain the number of targets and a clustering center; 3. performing plane cutting on the target amplitude to acquire amplitude tangent plane information of the target point cloud, so that the current personnel state is judged more accurately; 4. aiming at the condition that multiple persons are present, data are segmented through clustering, each target amplitude tangential plane information is analyzed, the peak value position is lower than a preset threshold value, the situation that the persons fall down is judged, otherwise, the persons are regarded as not falling down, and a time window is established to verify the results. The monitoring device comprises a millimeter wave radar, a control module and a sending module.
Description
Technical Field
The invention belongs to the technical field of millimeter wave radar monitoring, relates to radar signal processing and data processing technologies, and particularly relates to a millimeter wave radar falling monitoring method and device under a multi-person scene.
Background
Along with the continuous aggravation of the aging phenomenon of China, the health and safety problems of the old population are increasingly prominent. A fall event is a significant health risk in the life of elderly people, possibly resulting in serious physical injury and even life-threatening. Therefore, the development of fall monitoring technology has become critical, aiming at timely identifying and responding to the fall situation of the elderly, so as to reduce the potential risk of injury; currently fall monitoring typically relies on environmental sensors, such as cameras installed in the home or wearable devices, such as smartwatches with Inertial Measurement Units (IMUs). However, for a broad population of elderly people, these devices present a variety of pain points; first, many elderly people are reluctant to wear contact devices, as this may cause their discomfort or contradiction; secondly, installing a camera at home may violate personal privacy, thereby leading the elderly to be reluctant to adopt the monitoring mode; in addition, most of fall monitoring devices in the market are designed for single monitoring, so that the condition that multiple persons are simultaneously present cannot be effectively processed, and accurate monitoring of falling events when the multiple persons are present cannot be realized; in view of the above-mentioned needs, there is an urgent need for a fall monitoring device that does not require contact and that can compromise privacy, and that is capable of efficiently identifying the fall behavior of the elderly, and that also requires an accurate fall judgment algorithm to distinguish between falls and other daily activities, so as to reduce the false alarm rate; meanwhile, the design of the equipment should respect the privacy rights of the old, and the privacy protection technology is adopted to ensure the information security and the data confidentiality; the novel multi-person falling monitoring equipment can provide more reliable guarantee for the health and safety of the old, and is expected to be an important breakthrough in the field of old care.
Disclosure of Invention
The invention aims to: the fall monitoring radar system in the market at present cannot effectively perform fall monitoring under the condition that a plurality of people are simultaneously present; to cope with this challenge, the present study aims to develop a new algorithm to realize reliable fall monitoring of millimeter wave radars in the presence of multiple persons at the same time, thereby ensuring safe monitoring of users.
Technical principle and summary:
the millimeter wave radar continuously transmits frequency modulation continuous waves (Frequency Modulated Continuous Wave, FMCW) to the monitoring environment, and the frequency modulation continuous waves are reflected by a human body target to obtain an echo signal of the human body target; after the echo signals are processed, the motion state information of the human body target can be obtained; each echo signal represents a reflection point and comprises information such as distance, angle, radial speed, amplitude and the like; when a plurality of targets exist, a plurality of groups of echo signals exist, and a certain superposition exists among the plurality of groups of echo signals. Therefore, the data of the multiple sets of echo signals need to be reconstructed, and the reconstructed data mainly comprises the distance of the target, the height of the target, the horizontal direction information, the vertical direction information, the speed and the like.
The data after data reconstruction is called point cloud data (point cloud data), and the data reconstruction process is shown in fig. 3. The point cloud data can be analyzed by a series of algorithms, such as SAC-IA algorithm, DBSCAN algorithm and RANSAC algorithm; after analyzing the point cloud data, the position of the falling object can be found, and whether the monitoring object falls or not is judged.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a flow chart of the overall design of the monitoring device of the present invention;
FIG. 3 is a flow chart of the original signal processing as point cloud according to the present invention;
FIG. 4 is a point cloud cluster map of the present invention;
FIG. 5 is a point cloud cut view of the present invention;
FIG. 6 is a cut-away plan view of the amplitude intensity of the present invention.
Detailed Description
The present invention is further illustrated in the accompanying drawings and examples which are to be understood as being illustrative of the invention and not limiting the scope of the invention, and various equivalent modifications to the invention will fall within the scope of the appended claims after reading the invention.
Specific examples are given below:
in the example, 3 targets, namely three old people, are detected to be 3 people currently, and a radar board is accompanied with a plurality of interference points; referring to fig. 1 to 6, the monitoring device of the present embodiment includes a millimeter wave radar, a control module, and a transmitting module, as shown in fig. 2; the millimeter wave radar comprises a transmitting module and a receiving module, wherein the transmitting module comprises 22 transmitting antennas, and the receiving module comprises 27 receiving antennas.
The control module controls the millimeter wave radar and the sending module to realize echo signal preprocessing, point cloud data processing, point cloud amplitude data processing stages and other data analysis and decision.
The implementation process of the invention comprises the following steps:
s1: transmitting electromagnetic wave signals to a monitoring environment by utilizing a millimeter wave radar, performing signal processing on echoes, and generating point cloud data according to measurement vectors of each group;
s2: carrying out spatial clustering on point cloud data by using a spatial clustering algorithm based on density, filtering non-target point cloud, judging the number of targets by using a clustering result, and obtaining a clustering center as target position information;
s3: respectively carrying out plane cutting on the amplitude information of the target point cloud, taking 10cm as a segmentation segment, and accumulating the amplitude data of the point cloud in each segment to obtain the tangential plane information of the target point cloud;
s4: acquiring point cloud amplitude tangential plane data in each frame 250 cm, extracting position information of a tangential plane peak value, judging that a target person falls when the peak value position is lower than a preset threshold value, and otherwise, judging that the target person does not fall;
s5: and outputting confirmation, namely, in order to ensure the output accuracy, reducing false alarm caused by single frame error, creating a time window, and judging the result in the time window so as to ensure the output accuracy.
Further, in the step S1, a millimeter wave radar is utilized to transmit a frequency modulated continuous wave signal (FMCW signal) into the monitoring environment, and a series of data processing is performed on the echo signal to obtain point cloud data, as shown in fig. 3, the method for obtaining the point cloud data is as follows:
a1: the millimeter wave radar comprises a plurality of transmitting and receiving antennas, and after the radar board receives echo signals, the pulse data received by each receiving antenna is subjected to fast Fourier transform;
a2: static clutter filtering is carried out, and fast Fourier transformation is carried out in a slow time dimension, so that a distance-Doppler image is obtained;
a3: obtaining a target point on the distance-Doppler image through two-dimensional constant false alarm detection, wherein the target point comprises distance and speed information of the target point;
a4: calculating a space correlation matrix of each target pitch dimension, generating a vertical heat map through beam forming in the vertical direction, and finally obtaining the vertical angle of the target through peak value search on the heat map;
a5: calculating a space correlation matrix of each target azimuth dimension, generating a horizontal heat map through horizontal beam forming, finally obtaining a horizontal angle of a target through peak value searching on the heat map, and finally obtaining a point cloud containing target information, wherein the point cloud contains measurement vector information of distance, angle, radial speed and amplitude.
Further, in the step S2, the point cloud data is spatially clustered by using a DBSCAN algorithm, the number of targets is determined according to the clustering result, and non-target point clouds are filtered, as shown in fig. 4, the method for obtaining the number of targets and the clustering center is as follows:
a1: according to the DBSCAN algorithm, parameters of the DBSCAN algorithm, including radius r and minimum point number MinPts, need to be set; the neighborhood range, namely, the neighborhood with the point p as the center and the circle with the radius r as the p, is judged to be the number of points needed in the core point neighborhood by MinPts, and the algorithm flow is as follows:
preparation: inputting point cloud data to be clustered; setting parameters: distance r, minimum sampling point MinPts;
step 1, randomly selecting an unaccessed point p, and searching adjacent points in the radius r area;
step 2, judging whether the neighbor number in the radius r is more than or equal to MinPts,
if the point is more than or equal to MinPts, p is a core point, a cluster C is created at the moment, p is marked as a visited point, and the step 3 is skipped;
otherwise, p is a noise point, and p is a point after access;
step 3, marking the points in the r neighborhood as clusters C, continuously judging whether the points in the r neighborhood are core points or not, if the points are core points, setting the point at the moment (the point in the r neighborhood) as a new point p, and re-executing the step 3;
step 4, deleting the cluster C from the data set, and continuously executing the step 1;
and 5, stopping the algorithm when all the points indicate that the access is performed.
A2: clustering the preprocessed three-dimensional point cloud data according to set parameters by using a DBSCAN algorithm, dividing the data points into core points, boundary points and noise points, connecting the core points and the data points to form clusters;
a3: and analyzing the clustering result of the DBSCAN, deleting the interference points, and distributing a unique identifier to each cluster according to different clustering clusters.
In this embodiment, from the clustering result in fig. 4, it may be analyzed that 3 monitoring targets exist in the current detection environment and are accompanied by a plurality of interference points.
Further, in the step S3, plane cutting is performed on the amplitude information of the target point cloud, 10cm is used as a segment, the point cloud data is cut, and the amplitude data of each segment of the point cloud is accumulated to obtain the intensity tangent plane information of the target point cloud, which comprises the following steps:
a1: respectively extracting point cloud data of different clusters, and equally spacing cutting the data with the height lower than 200cm, as shown in fig. 5;
a2: and cutting the point cloud data of each group of cluster by taking 10cm as a unit, and accumulating and summing the point cloud amplitude data in each section to obtain the amplitude intensity tangential plane information of the target point cloud, as shown in fig. 6.
Further, in the step S4, the method for extracting the peak position information of the tangential plane and judging whether the target person falls according to the peak position is as follows:
a1: finding out a peak value in the two-dimensional data of the point cloud amplitude intensity, and determining peak value position information;
a2: it is determined whether the peak position exceeds a predetermined threshold to determine whether a fall has occurred.
Further, in the step S5, a time window is created, and the method for ensuring the output accuracy by judging the result in the time window is as follows:
a1: defining a time window, wherein the fall judgment is carried out in the time period, the size of the time window can be adjusted according to application requirements, and is usually about 10 s, and the starting time of the time window can be synchronous with the time of the fall monitoring start or slightly delayed according to requirements;
a2: continuously collecting results of fall monitoring, including whether a fall occurs or not and an occurrence timestamp, in a time window;
a3: and once the time window is over, verifying and judging the falling monitoring result in the time window, if multiple independent falling monitoring results appear, indicating that falling occurs, increasing the reliability of the monitoring result, setting a threshold value, and for example, confirming that falling occurs when the number of times of falling monitored in the time window reaches or exceeds the threshold value.
Further, after the falling is confirmed, the sending module of the monitoring device sends falling early warning, and the sending module can send short messages, micro messages, calls and the like to give an alarm.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art who is within the technical scope of the present invention shall be covered by the scope of the present invention by making equivalents and modifications according to the technical scheme of the present invention and the inventive concept thereof.
Claims (10)
1. The millimeter wave radar falling monitoring method in the multi-person scene is characterized by comprising the following steps:
s1: transmitting electromagnetic wave signals to a monitoring environment by utilizing a millimeter wave radar, performing signal processing on echoes, and generating point cloud data according to measurement vectors of each group;
s2: carrying out spatial clustering on point cloud data by using a spatial clustering algorithm based on density, filtering non-target point cloud, judging the number of targets by using a clustering result, and obtaining a clustering center as target position information;
s3: respectively carrying out plane cutting on the amplitude information of the target point cloud, taking 10cm as a segmentation segment, and accumulating the amplitude data of the point cloud in each segment to obtain the tangential plane information of the target point cloud;
s4: acquiring point cloud amplitude tangential plane data in each frame 250 cm, extracting position information of a tangential plane peak value, judging that a target person falls when the peak value position is lower than a preset threshold value, and otherwise, judging that the target person does not fall;
s5: and outputting confirmation, namely, in order to ensure the output accuracy, reducing false alarm caused by single frame error, creating a time window, and judging the result in the time window so as to ensure the output accuracy.
2. The method for detecting fall of millimeter wave radar in a multi-person scene according to claim 1, wherein each measurement vector in step S1 contains information of distance, angle, radial velocity and amplitude.
3. The method for monitoring the falling of the millimeter wave radar in the multi-person scene according to claim 1, wherein in the step S1, the millimeter wave radar is used for transmitting a frequency modulation continuous wave signal into a monitoring environment, and a series of data processing is performed on echo signals to obtain point cloud data, and the method for obtaining the point cloud data is as follows:
a1: the millimeter wave radar comprises a plurality of transmitting and receiving antennas, and after the radar board receives echo signals, the pulse data received by each receiving antenna is subjected to fast Fourier transform;
a2: static clutter filtering is carried out, and fast Fourier transformation is carried out in a slow time dimension, so that a distance-Doppler image is obtained;
a3: obtaining a target point on the distance-Doppler image through two-dimensional constant false alarm detection, wherein the target point comprises distance and speed information of the target point;
a4: calculating a space correlation matrix of each target pitch dimension, generating a vertical heat map through beam forming in the vertical direction, and finally obtaining the vertical angle of the target through peak value search on the heat map;
a5: calculating a space correlation matrix of each target azimuth dimension, generating a horizontal heat map through horizontal beam forming, finally obtaining a horizontal angle of a target through peak value searching on the heat map, and finally obtaining a point cloud containing target information, wherein the point cloud contains measurement vector information of distance, angle, radial speed and amplitude.
4. The method for monitoring the falling of the millimeter wave radar in the multi-person scene according to claim 1, wherein in the step S2, the method for performing spatial clustering on point cloud data by using a DBSCAN algorithm and filtering non-target point clouds to obtain the number of targets and a clustering center is as follows:
a1: according to the DBSCAN algorithm, parameters of the DBSCAN algorithm, including radius r and minimum point number MinPts, need to be set; the neighborhood range, namely, the neighborhood with the point p as the center and the circle with the radius r as the p, is judged to be the number of points needed in the core point neighborhood by MinPts, and the algorithm flow is as follows:
preparation: inputting point cloud data to be clustered; setting parameters: distance r, minimum sampling point MinPts;
step 1, randomly selecting an unaccessed point p, and searching adjacent points in the area with the radius r;
step 2, judging whether the neighbor number in the radius r is more than or equal to MinPts,
if the point is more than or equal to MinPts, p is a core point, a cluster C is created at the moment, p is marked as a visited point, and the step 3 is skipped;
otherwise, p is a noise point, and p is a point after access;
step 3, marking the points in the r neighborhood as clusters C, continuously judging whether the points in the r neighborhood are core points or not, if the points are core points, setting the point at the moment (the point in the r neighborhood) as a new point p, and re-executing the step 3;
step 4, deleting the cluster C from the data set, and continuing to execute the step 1;
step 5, stopping the algorithm when all points indicate access;
a2: clustering the preprocessed three-dimensional point cloud data according to set parameters by using a DBSCAN algorithm, dividing the data points into core points, boundary points and noise points, connecting the core points and the data points to form clusters;
a3: and analyzing the clustering result of the DBSCAN, deleting the interference points, and distributing a unique identifier to each cluster according to different clustering clusters.
5. The method for monitoring the falling of the millimeter wave radar in the multi-person scene according to claim 1, wherein in the step S3, plane cutting is performed on the amplitude information of the target point cloud, 10cm is used as a segment, the point cloud data are cut, the amplitude data of each segment of the point cloud are accumulated to obtain the intensity tangent plane information of the target point cloud, and the specific steps are as follows:
a1: respectively extracting point cloud data of different clusters, and carrying out equidistant cutting on the data with the height lower than 200 cm;
a2: and cutting the point cloud data of each group of cluster by taking 10cm as a unit, and accumulating and summing the point cloud amplitude data in each section to obtain the amplitude intensity tangential plane information of the target point cloud.
6. The method for monitoring the falling of the millimeter wave radar in the multi-person scene according to claim 1, wherein the step S4 is characterized in that the method for extracting the peak position information of the tangential plane and judging whether the target person falls according to the peak position is as follows:
a1: finding out a peak value in the two-dimensional data of the point cloud amplitude intensity, and determining peak value position information;
a2: it is determined whether the peak position exceeds a predetermined threshold to determine whether a fall has occurred.
7. The method for monitoring the fall of the millimeter wave radar in the multi-person scene according to claim 1, wherein the step S5 is to create a time window, and the output accuracy is ensured by judging the result in the time window, which comprises the following specific steps:
a1: defining a time window, wherein the fall judgment is carried out in the time period, the size of the time window can be adjusted according to application requirements, and is usually about 10 s, and the starting time of the time window can be synchronous with the time of the fall monitoring start or slightly delayed according to requirements;
a2: continuously collecting results of fall monitoring, including whether a fall occurs or not and an occurrence timestamp, in a time window;
a3: and once the time window is over, verifying and judging the falling monitoring result in the time window, if multiple independent falling monitoring results appear, indicating that falling occurs, increasing the reliability of the monitoring result, setting a threshold value, and for example, confirming that falling occurs when the number of times of falling monitored in the time window reaches or exceeds the threshold value.
8. The millimeter wave radar falling monitoring device under the multi-person scene is characterized in that whether a target falls is monitored by using the millimeter wave radar falling monitoring method under the multi-person scene according to the claims 1-7, and the device comprises a millimeter wave radar and a control module, wherein the millimeter wave radar comprises a transmitting module and a receiving module, and the control module comprises a data processing module and a transmitting module.
9. The device for monitoring the fall of the millimeter wave radar in the multi-person scene according to claim 8, wherein the transmitting module can transmit electromagnetic wave signals, the receiving module can receive echo signals, and the control module controls the time sequence, the data processing and the judgment of the whole system.
10. The millimeter wave radar fall monitoring device in a multi-person scenario of claim 8, wherein the sending module can alarm by sending a short message, calling for help, and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311836517.XA CN117784124A (en) | 2023-12-28 | 2023-12-28 | Millimeter wave radar falling monitoring method and device in multi-person scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311836517.XA CN117784124A (en) | 2023-12-28 | 2023-12-28 | Millimeter wave radar falling monitoring method and device in multi-person scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117784124A true CN117784124A (en) | 2024-03-29 |
Family
ID=90385174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311836517.XA Pending CN117784124A (en) | 2023-12-28 | 2023-12-28 | Millimeter wave radar falling monitoring method and device in multi-person scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117784124A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118485970A (en) * | 2024-07-15 | 2024-08-13 | 浪潮宽广科技(青岛)有限公司 | High-rise fire personnel searching method and system based on radar |
-
2023
- 2023-12-28 CN CN202311836517.XA patent/CN117784124A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118485970A (en) * | 2024-07-15 | 2024-08-13 | 浪潮宽广科技(青岛)有限公司 | High-rise fire personnel searching method and system based on radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110488264A (en) | Personnel's detection method, device, electronic equipment and storage medium | |
| US20150260838A1 (en) | Sparse Array RF Imaging for Surveillance Applications | |
| EP2464991B1 (en) | A method for human only activity detection based on radar signals | |
| CN109765539A (en) | Indoor user behavior monitoring method and device, electrical equipment and home monitoring system | |
| CN112394334B (en) | Clustering device and method for radar reflection points and electronic equipment | |
| CN106408940A (en) | Microwave and video data fusion-based traffic detection method and device | |
| CN110070155B (en) | Comprehensive behavior recognition method and system for prisoner based on wearable equipment | |
| CN115542308B (en) | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar | |
| CN111627185A (en) | Fall alarm method and device and fall detection system | |
| WO2011112740A1 (en) | Method and system for position and track determination | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN117784124A (en) | Millimeter wave radar falling monitoring method and device in multi-person scene | |
| CN109061631A (en) | A kind of intelligent security guard Millimeter Wave Phased Array Antenna radar warning system and method | |
| Chen et al. | A safe-distance control scheme to avoid new infection like COVID-19 virus using millimeter-wave radar | |
| JP2011112465A (en) | Aircraft position measuring system, response signal discriminating method, and response signal discriminating program for use in the system | |
| CN110398735B (en) | Multi-radar-based perception data processing method and system | |
| CN110687513A (en) | Human body target detection method, device and storage medium | |
| CN112102370B (en) | Target tracking method and device, storage medium and electronic device | |
| CN118053261A (en) | Anti-spoofing early warning method, device, equipment and medium for smart campus | |
| CN113009486A (en) | Human body sensing method and system based on millimeter wave radar | |
| CN111986523A (en) | Target monitoring device and monitoring method for urban low-speed small unmanned aerial vehicle | |
| CN117872354A (en) | Fusion method, device, equipment and medium of multi-millimeter wave Lei Dadian cloud | |
| CN111025288B (en) | Security radar monitoring device and system | |
| CN116758467A (en) | Monitoring alarm method and device in civil aviation security equipment field | |
| CN116520315A (en) | Target recognition system, target recognition method and target recognition device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |