CN107643544B - Method for automatically detecting metal - Google Patents
Method for automatically detecting metal Download PDFInfo
- Publication number
- CN107643544B CN107643544B CN201710772193.6A CN201710772193A CN107643544B CN 107643544 B CN107643544 B CN 107643544B CN 201710772193 A CN201710772193 A CN 201710772193A CN 107643544 B CN107643544 B CN 107643544B
- Authority
- CN
- China
- Prior art keywords
- channel state
- state information
- abnormal
- metal
- wireless
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to a method for automatically detecting metal, which is based on a wireless network signal transmission technology and comprises the following steps: the wireless receiving end receives a wireless signal from the wireless transmitting end and evaluates the channel state information; identifying the abnormality of the channel state information change by using an abnormality detection algorithm; taking out the abnormal signal section, and removing noise in the signal through a Hampel filter and a 1D difference algorithm; then, judging whether a human body carries a metal substance or not by taking an abnormal mode of channel state information change caused by the reflection characteristic of metal as a target metal class through a proximity algorithm for distinguishing the target material from other material classes, and if so, sending an alarm signal; the detection method of the invention has lower false alarm rate; the existing wireless network and equipment are utilized, other specific detection equipment is not required to be installed, and the method has extremely high popularity; meanwhile, the detected person does not need to carry any additional sensing equipment, and the work of the checking personnel is facilitated.
Description
Technical Field
The invention belongs to the field of improvement of information processing technology, and particularly relates to a method for automatically detecting metal based on a wireless network.
Background
Public safety is becoming an increasingly important issue today due to the increasing rampant of terrorism. The detection of metals also becomes particularly important. At present, the following methods are mainly used for detecting metals: (1) the article identification is carried out by utilizing the penetrating power of X rays, the article identification is carried out by utilizing the penetrability of X rays, integrating the photoelectric technology, combining the technologies of a computer, digital signal processing and the like, and the information of an image is distinguished, extracted and distinguished by vision and pattern identification, so that the identification of articles such as metal and the like by foreign matter processing is finally realized; the X-ray is a free radiation ray, which is mainly used for medical diagnosis, and the security inspection equipment for baggage on the market at present mainly adopts the detection mode. But the realization cost is very high, the product is huge and heavy, and is difficult to transport and move, and the X-ray thereof can cause serious harm to human body and has certain technical requirements on users; (2) the presence of metal is detected by detecting the influence of metal on an electromagnetic field by generating a rapidly changing magnetic field through a coil through which an alternating current passes by using the principle of electromagnetic induction (hall effect, magnetic resistance, etc.). The oscillator emits a high-frequency magnetic field through the middle transmitting coil, and is connected with the two receiving coils, but the polarities of the high-frequency magnetic field are opposite, and under the condition that the magnetic fields are not interfered by the outside, voltage output signals generated by the high-frequency magnetic field and the receiving coils are mutually cancelled. Once metal impurities enter the magnetic field area, signals output by the two output coils cannot be offset, and the metal detector can detect the existence of metal. Compared with the mode (1), the method has lower cost and less harm to human body compared with the first mode, but needs short-distance detection, and has lower accuracy compared with the former mode. Therefore, both the above two methods must be performed under the condition of cooperation of the detected person, and corresponding actions or a specified position needs to be completed, so that the detection range and speed are greatly limited. Therefore, there is a great need to find a convenient and effective method for automatically detecting and responding to metals. In order to realize accurate detection of behaviors, methods of detecting using environmental devices, vision, or sensors have been proposed. However, the detection systems built by the methods have various defects.
Disclosure of Invention
The invention aims to provide a method for automatically detecting metals, and aims to solve the technical problems that in a specific indoor environment, the existing wireless network and equipment are utilized to effectively detect metals carried by a human body, and the functions of timely alarming and feeding back are achieved.
The invention is realized in such a way that a method for automatically detecting metals is based on a wireless network signal transmission technology, and the method comprises the following steps:
s1, the wireless receiving end receives the wireless signal from the wireless transmitting end and evaluates the channel state information;
s2, identifying whether the change of the channel state information is abnormal by using an abnormal detection algorithm, if so, executing a step S3, and if not, abandoning the detection signal and returning to the step S2;
s3, denoising the abnormal channel state information signal;
s4, judging whether a human body carries metal or not by taking an abnormal mode of channel state information change caused by a metal material class as a target material class according to a proximity algorithm for distinguishing different Euclidean distances of Amplitude Spectrum Densities (ASD) of the target material class and other material classes as characteristic items, if so, sending an alarm signal to an alarm device, and if not, passing detection;
when detecting, the position where a person stands needs to be satisfied and is not on the extension line of the connecting line of the transmitting terminal and the receiving terminal.
The further technical scheme of the invention is as follows: the step S1 further includes the following steps:
s11, acquiring initial channel state data, wherein the initial channel state data comprises CSI values of M subcarriers in N spatial streams based on a multi-input multi-output technology, and both N and M are natural numbers larger than 1;
s12, for each space flow, calculating the average value of CSI values of P continuous subcarriers at the same time point, and taking the average value as channel state information, wherein P is a natural number which is greater than 1 and less than M;
and S13, smoothing the channel state information by using a data filtering technology and a moving average method.
The further technical scheme of the invention is as follows: the step S2 is a time-series abnormality detection algorithm based on a local abnormality factor using an abnormality detection algorithm to identify the abnormality of the channel state information variation.
The further technical scheme of the invention is as follows: the step S2 further includes the following steps:
s21, performing data segmentation on the time sequence of the channel state information to obtain a subsequence, and calculating a local abnormal factor of the subsequence;
and S21, when the local abnormal factor is larger than or equal to the preset threshold value, outputting the subsequence as an abnormal mode.
The further technical scheme of the invention is as follows: the step S3 is based on using a Hampel filter and a 1D difference algorithm with the exception of recognizing the change of the channel state information.
The further technical scheme of the invention is as follows: the step S3 further includes the following steps:
s31, filtering all subcarriers in the signal information by using a Hampel filter;
and S32, uniformly interpolating the data in the preset time between the continuous measurements by using an ID linear interpolation algorithm and outputting the data.
The further technical scheme of the invention is as follows: the step S4 further includes the following steps:
s41, converting the wireless electromagnetic wave signals after the noise is removed from the time domain information into frequency domain information through Fourier transform based on a statistical learning theory; calculating Euclidean distances among various materials to serve as characteristic quantities, and taking the characteristic quantities as training samples; thereby establishing a high-dimensional characteristic model of an abnormal mode of channel state information change caused by various metal materials in a specific space;
s42, mapping the abnormal mode output in the step S32 to a high-dimensional feature model of a neighbor algorithm, and if an abnormal feature value is successfully matched with target matching data, determining that the radio electromagnetic wave signal detected in T time is influenced by metal;
and S43, judging whether the human body carries metal according to the influence of the metal on the wireless electromagnetic signal, and sending an alarm signal.
The further technical scheme of the invention is as follows: the step S43 is followed by the step of:
and S44, adjusting the high-dimensional feature model of the neighbor algorithm according to the response information feedback of the alarm signal.
The further technical scheme of the invention is as follows: the number of the wireless transmitting ends is one or more than two, and the number of the wireless receiving ends is one or more than two.
The further technical scheme of the invention is as follows: the steps of extracting the features and matching can be completed in a server of the wireless receiving end; or transmitting the data to a cloud server through wireless transmission to extract and match the characteristics; the alarm device is in a standby state before receiving the alarm instruction, and when the alarm instruction arrives, the alarm device enters an operating state and informs related workers of intervention in at least one mode of playing music, emitting light, whistling or text alarm.
The invention has the beneficial effects that: the invention is based on the radio transmission mechanism in the indoor environment, establishes the relation between the channel state information CSI and the metal substance, judges the behavior of the metal carried by the human body through the change of the CSI, and determines whether the detected person has the behavior of carrying the metal, thereby realizing the function of effective alarm, and the beneficial effects of the invention comprise: in the indoor environment with few ornaments (such as a laboratory), the detection accuracy of the detected behavior is 84-94%, and in the indoor environment with many ornaments (such as a dormitory), the detection accuracy also reaches 78%, and the false alarm rate is lower and is only 15-22%; the alarm signal can be sent out after the metal material is judged, the false alarm condition is processed by utilizing the self-learning function of the system, and the false alarm rate is further reduced; the detection method is based on the existing wireless network and equipment, the detection work of the metal carried by the human body is carried out, other specific detection equipment is not required to be installed in the detected environment, the detection method can be used in any environment in the radio electromagnetic wave, and has extremely high popularity.
Drawings
Fig. 1 is a flowchart of a detection method for automatically detecting a metal according to an embodiment of the present invention.
Fig. 2 is a flowchart of an implementation of the method for automatically detecting metals carried by a human body according to the embodiment of the present invention.
Detailed Description
Fig. 1 shows a flow chart of a method for automatically detecting metal, which is based on a wireless network signal transmission technology and is detailed as follows:
step S1, the wireless receiving end receives the wireless signal from the wireless transmitting end and evaluates the channel state information; in practical application, the method for automatically detecting the metal can be realized on an application server. Preferably, the wireless receiving end is a wireless network card, the wireless transmitting end is a wireless router, the method establishes a relation between wireless signals and influences of metal on the wireless signals based on a radio propagation mechanism in an indoor environment, and only existing wireless network equipment needs to be used, namely, whether the detected person carries the metal or not is judged and an alarm is given out through analyzing changes of the wireless signals caused by the fact that the detected person carries the metal substance, so that the influence of surrounding environment factors on material detection is reduced, and the accuracy of detection is greatly improved. In a specific indoor environment, rich channel state information of a wireless network can be collected through a wireless network card. In the invention, the number of the wireless transmitting ends is one or more than two, and the number of the wireless receiving ends is one or more than two. In the system, a plurality of antennas are respectively used for transmitting and receiving wireless signals; the wireless network card used by the system may receive channel state information. Preferably, the number of the wireless transmitting ends and the number of the wireless receiving ends are both 2 or 3. As shown in fig. 1, there are two wireless transmitting terminals (first transmitter and second transmitter) and two wireless receiving terminals (first receiving terminal and second receiving terminal) in the detected environment. Wherein a first receiving end receives CSI (short for channel state information, in the field of wireless communication, CSI is a channel property of a communication link and describes a fading factor of a signal on each transmission path) from a first transmitter, and a second receiving end receives CSI from a second transmitter. In the detected environment, the detected person does not need to carry other additional equipment. The system detects the behavior of the detected person by using the CSI received by the two wireless receiving ends, and then judges whether the detected person carries metal.
In step S1, the evaluating the channel state information further includes: s11, acquiring initial channel state data, wherein the initial channel state data comprises CSI values of M subcarriers in N spatial streams based on a multi-input multi-output technology, and both N and M are natural numbers larger than 1; s12, for each space flow, calculating the average value of CSI values of P continuous subcarriers at the same time point, and taking the average value as channel state information, wherein P is a natural number which is greater than 1 and less than M; and S13, smoothing the channel state information by using a data filtering technology and a moving average method.
When the system starts to work, the wireless transmitting end transmits wireless network signals, and meanwhile, a wireless receiving end (such as a computer provided with a network card) in a specific area can collect CSI (channel state information) as initial channel state data and then perform data processing. Taking the 3 × 3 MIMO (Multiple-input Multiple-output) technique as an example, the initial csi data obtained in the sensing stage is divided into 9 spatial streams, and each stream has 30 subcarriers. Experiments show that the variation caused by the influence of metal on the wireless signal affects the data contained in different spatial streams, and affects all the subcarriers in each spatial stream similarly. Meanwhile, experiments show that environmental factors (such as temperature and room setting) can cause fluctuation of the collected CSI. Therefore, in the present invention, the CSI values of the 30 subcarriers in each independent spatial stream are aggregated into a single piece of channel state information. Preferably, for each spatial stream, the CSI average of 5 consecutive subcarriers is obtained, and the CSI average of the same time point is taken as the channel state information for 9 spatial streams. In order to reduce the interference of environmental factors, the present invention uses a data filtering technique and a moving average method, and in particular, uses a weighted moving average (weighted moving average) to smooth the channel state information processed as described above, so as to reduce the noise in the data.
Step S2, using the abnormal detection algorithm to identify whether the change of the channel state information is abnormal, if so, executing step S3, otherwise, abandoning the detection signal and returning to the step S2; the step S2 of recognizing the channel state information variation abnormality by using the abnormality detection algorithm is a time-series abnormality detection algorithm based on a local abnormality factor, and further includes: s21, performing data segmentation on the time sequence of the channel state information to obtain a subsequence, and calculating a local abnormal factor of the subsequence; s21, when the local abnormal factor is larger than or equal to the preset threshold value, outputting the subsequence as an abnormal mode; and S23, using a preset threshold value as a signal for judging whether the metal is reflected, setting the channel state information as abnormal information, and analyzing the CSI data of N continuous subcarriers within the abnormal time and T time later. The T time can be set in a self-defined way according to the requirements of a user, for example, the T time is set to be ten seconds. The specific numerical value can be set by self according to the requirements of users, and only N is set to be larger than 0.
Step S3, carrying out denoising processing on the abnormal channel state information signal; the step S3 is based on using a Hampel filter and a 1D difference algorithm with the exception of recognizing the change of the channel state information. In the denoising process, step S3 further includes: s31, filtering all subcarriers in the signal information by using a Hampel filter; a moving window is employed to determine the significance value using a plurality of data. If the filter determines that the data is valid, it is output. Otherwise, if the data is judged to be singular data, other effective values are used for replacing the singular data. And S32, uniformly interpolating the data in the preset time between the continuous measurements by using an ID linear interpolation algorithm and outputting the data. To solve the CSI information loss caused by sample jitter and outlier removal, interpolation in the inner CSI information is necessary. In particular, we use a 1D linear interpolation algorithm to ensure uniform interpolation in the data with an interval of 10ms between successive measurements. The unknown relation corresponding to the third item is estimated according to the known corresponding relation of the two items.
Step S4, according to the proximity algorithm for distinguishing different Euclidean distances of the Amplitude Spectrum Density (ASD) of the target material class and other material classes as characteristic items, judging whether the human body carries metal or not by taking the abnormal mode of the channel state information change caused by the metal material class as the target material class, if so, sending an alarm signal to an alarm device, and if not, passing the detection; the method further comprises the following steps in the process of judging whether the metal is carried or not: s41, converting the wireless electromagnetic wave signals after the noise is removed from the time domain information into frequency domain information through Fourier transform based on a statistical learning theory; calculating Euclidean distances among various materials to serve as characteristic quantities, and taking the characteristic quantities as training samples; thereby establishing a high-dimensional characteristic model of an abnormal mode of channel state information change caused by various metal materials in a specific space; based on the statistical learning theory, the wireless electromagnetic wave signal after the noise is removed is converted from the time domain information to the frequency domain information through the fourier transform, namely, the amplitude information in the time domain is converted into the Amplitude Spectral Density (ASD) of the received signal in the frequency domain to be represented. And then, calculating Euclidean distances among Amplitude Spectral Densities (ASDs) of various materials to be used as characteristic quantities, and using the characteristic quantities as training samples. Therefore, a high-dimensional characteristic model of an abnormal mode of channel state information change caused by various metal materials in a set space is established. S42, mapping the abnormal mode output in the step S32 to a high-dimensional feature model of a neighbor algorithm, and if an abnormal feature value is successfully matched with target matching data, determining that the radio electromagnetic wave signal detected in T time is influenced by metal; the abnormal pattern output in step S32 is mapped to a high-dimensional feature model of a nearest neighbor algorithm (KNN), and a target material class is isolated. That is, most of k nearest neighboring samples in the feature space of an abnormal data sample output in S23 belong to a certain class, the sample also belongs to the class and has the characteristics of the sample on the class. And the value of K is artificially set according to the characteristics of the sample. The machine learning algorithm matches the target data with the features stored in the feature library, and if one feature is successfully matched with the target data, the data detected in the T time is determined to be influenced by the metal. And S43, judging whether the human body carries metal according to the influence of the metal on the wireless electromagnetic signal, and sending an alarm signal. And step S44, adjusting a high-dimensional feature model of the neighbor algorithm according to the response information feedback of the alarm signal. And feeding back response information aiming at the alarm signal, and adjusting the high-dimensional characteristic model of the KNN. When the behavior of carrying metal is detected, the alarm processing stage is entered, and the system will give an alarm. If the alarm is turned off in time, the fact that the metal carried by the detected person does not cause danger to other people is indicated, at the moment, the system updates the historical record of behavior judgment of the person by using the feedback response information, and is used for adjusting and perfecting the KNN high-dimensional characteristic model and providing system feedback capable of optimizing detection and decision-making algorithms. If the alarm is not closed in time, the system judges the alarm is correct and stores the result into the feature library.
The invention is based on the radio transmission mechanism in the indoor environment, establishes the relation between the channel state information CSI and the metal substance, judges the behavior of the metal carried by the human body through the change of the CSI, and determines whether the detected person has the behavior of carrying the metal, thereby realizing the function of effective alarm, and the beneficial effects of the invention comprise: in the indoor environment with few ornaments (such as a laboratory), the detection accuracy of the detected behavior is 84-94%, and in the indoor environment with many ornaments (such as a dormitory), the detection accuracy also reaches 78%, and the false alarm rate is lower and is only 15-22%; the alarm signal can be sent out after the metal material is judged, the false alarm condition is processed by utilizing the self-learning function of the system, and the false alarm rate is further reduced; the detection method is based on the existing wireless network and equipment, the detection work of the metal carried by the human body is carried out, other specific detection equipment is not required to be installed in the detected environment, the detection method can be used in any environment in the radio electromagnetic wave, and has extremely high popularity.
The method for automatically detecting the metal comprises three important steps: CSI data processing, anomaly detection, and behavior classification.
As shown in fig. 2, the present invention further provides an implementation process of the automatic detection method for metals carried by a human body according to the embodiment, which includes the steps of:
s301, a wireless receiving end receives a wireless signal from a wireless transmitting end and collects initial channel state data;
s302, obtaining a CSI average value of the combined subcarriers as channel state information;
s303, smoothing the channel state information;
s304, estimating the normal contour of the channel state information by using an anomaly detection algorithm, and calculating a local anomaly factor;
s305, outputting an abnormal mode;
s306, removing noise from the output abnormal mode;
s307, mapping the denoised abnormal mode to a KNN high-dimensional feature model;
s308, classification is carried out by using KNN, wherein an abnormal mode of channel state information change caused by metal materials is taken as a target material class;
s309, judging whether the target material class is separated, if so, executing the step S310, otherwise, returning to the step S301;
s310, judging the behavior of carrying metal by a human body, and sending an alarm signal;
s311, judging whether the alarm is closed in time within a set time interval, if so, executing S312, otherwise, executing S313;
s312, feeding back closing operation and abnormal mode parameters to the system, and optimizing a detection and signal judgment algorithm;
and S313, storing the result into a feature library.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. A method for automatically detecting metals, the method being based on wireless network signal transmission technology, the method comprising the steps of:
s1, the wireless receiving end receives the wireless signal from the wireless transmitting end and evaluates the channel state information;
s2, identifying whether the change of the channel state information is abnormal by using an abnormal detection algorithm, if so, executing a step S3, and if not, abandoning the detection signal and returning to the step S2;
s3, denoising the abnormal channel state information;
s4, a neighbor algorithm for distinguishing according to different Euclidean distances of Amplitude Spectrum Densities (ASD) of a target material class and other material classes, and judging whether a human body carries metal or not by taking an abnormal mode of channel state information change caused by the metal material class as the target material class, if so, sending an alarm signal to an alarm device, and if not, passing detection;
during detection, the position where a person stands needs to be satisfied and is not on an extension line of a connecting line of a transmitting end and a receiving end;
the denoising processing in the step S3 is to use a Hampel filter and a 1D interpolation algorithm;
the step S3 further includes the following steps:
s31, filtering the identification channel state information by using a Hampel filter;
s32, uniformly interpolating the data in the preset time between continuous measurements by using a 1D linear interpolation algorithm and outputting the data;
the step S4 further includes the following steps:
s41, converting the wireless electromagnetic wave signals after the noise is removed from the time domain information into frequency domain information through Fourier transform based on a statistical learning theory; calculating Euclidean distances among various materials to serve as characteristic quantities, and taking the characteristic quantities as training samples; thereby establishing a high-dimensional characteristic model of an abnormal mode of channel state information change caused by various metal materials in a specific space;
s42, mapping the abnormal mode output in the step S32 to a high-dimensional feature model of a neighbor algorithm, and if an abnormal feature value is successfully matched with target matching data, determining that the radio electromagnetic wave signal detected in T time is influenced by metal;
and S43, judging whether the human body carries metal according to the influence of the metal on the wireless electromagnetic signal, and sending an alarm signal.
2. The method according to claim 1, wherein the step S1 further comprises the steps of:
s11, acquiring initial channel state data, wherein the initial channel state data comprises CSI values of M subcarriers in N spatial streams based on a multi-input multi-output technology, and both N and M are natural numbers larger than 1;
s12, for each space flow, calculating the average value of CSI values of P continuous subcarriers at the same time point, and taking the average value as channel state information, wherein P is a natural number which is greater than 1 and less than M;
and S13, smoothing the channel state information by using a data filtering technology and a moving average method.
3. The method of claim 2, wherein: the step S2 is a time-series abnormality detection algorithm based on a local abnormality factor using an abnormality detection algorithm to identify the abnormality of the channel state information variation.
4. The method according to claim 3, wherein the step S2 further comprises the steps of:
s21, performing data segmentation on the time sequence of the channel state information to obtain a subsequence, and calculating a local abnormal factor of the subsequence;
s22, when the local abnormal factor is larger than or equal to the preset threshold value, outputting the subsequence as an abnormal mode;
and S23, taking a preset threshold value as a signal for judging whether the metal is reflected or not, setting the channel state information as abnormal information, and analyzing the CSI data of N continuous subcarriers within the abnormal time and T time later.
5. The method according to claim 4, wherein said step S43 is followed by the step of:
and S44, adjusting the high-dimensional feature model of the neighbor algorithm according to the response information feedback of the alarm signal.
6. The method of claim 5, wherein the number of the wireless transmitting ends is one or more than two, and the number of the wireless receiving ends is one or more than two.
7. The method according to any of claims 1-6, wherein the steps of extracting features and matching are performed in a server at the wireless receiving end; or transmitting the data to a cloud server through wireless transmission to extract and match the characteristics; the alarm device is in a standby state before receiving the alarm instruction, and when the alarm instruction arrives, the alarm device enters an operating state and informs related workers of intervention in at least one mode of playing music, emitting light, whistling or text alarming.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710772193.6A CN107643544B (en) | 2017-08-31 | 2017-08-31 | Method for automatically detecting metal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710772193.6A CN107643544B (en) | 2017-08-31 | 2017-08-31 | Method for automatically detecting metal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107643544A CN107643544A (en) | 2018-01-30 |
| CN107643544B true CN107643544B (en) | 2020-08-18 |
Family
ID=61111378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710772193.6A Active CN107643544B (en) | 2017-08-31 | 2017-08-31 | Method for automatically detecting metal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107643544B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335620B (en) * | 2019-07-08 | 2021-07-27 | 广州欢聊网络科技有限公司 | Noise suppression method and device and mobile terminal |
| CN113203754A (en) * | 2021-05-13 | 2021-08-03 | 合肥工业大学 | Material inspection method based on wireless commercial equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104467991A (en) * | 2014-12-03 | 2015-03-25 | 无锡儒安科技有限公司 | Passive person detecting method and system based on WIFI physical layer information |
| CN104796204A (en) * | 2015-03-16 | 2015-07-22 | 深圳大学 | Metal carrying detection method based on wireless network |
| CN105527303A (en) * | 2015-12-04 | 2016-04-27 | 深圳大学 | Method and system for detecting material by using millimeter waves |
-
2017
- 2017-08-31 CN CN201710772193.6A patent/CN107643544B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104467991A (en) * | 2014-12-03 | 2015-03-25 | 无锡儒安科技有限公司 | Passive person detecting method and system based on WIFI physical layer information |
| CN104796204A (en) * | 2015-03-16 | 2015-07-22 | 深圳大学 | Metal carrying detection method based on wireless network |
| CN105527303A (en) * | 2015-12-04 | 2016-04-27 | 深圳大学 | Method and system for detecting material by using millimeter waves |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107643544A (en) | 2018-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zou et al. | Deepsense: Device-free human activity recognition via autoencoder long-term recurrent convolutional network | |
| CN110502105B (en) | Gesture recognition system and method based on CSI phase difference | |
| Chen et al. | Activity recognition based on micro-Doppler signature with in-home Wi-Fi | |
| CN101933058A (en) | Video sensor and alarm system and method with object and event classification | |
| CN110072186B (en) | Weighted naive Bayes indoor positioning method based on independent attributes | |
| Zhu et al. | TagCare: Using RFIDs to monitor the status of the elderly living alone | |
| CN107241696B (en) | Multipath effect distinguishing method and distance estimation method based on channel state information | |
| WO2008143698A1 (en) | Methods, systems and devices for detecting threatening objects and for classifying magnetic data | |
| CN107994960A (en) | A kind of indoor activity detection method and system | |
| CN107643544B (en) | Method for automatically detecting metal | |
| CN104796204B (en) | A kind of metal based on wireless network carries detection method | |
| CN109698724A (en) | Intrusion detection method, device, equipment and storage medium | |
| CN105787504B (en) | Human behavior recognition method and system | |
| Zhu et al. | NotiFi: A ubiquitous WiFi-based abnormal activity detection system | |
| Al-Qaness et al. | Device-free home intruder detection and alarm system using wi-fi channel state information | |
| CN112949487A (en) | WiFi-based ship cab personnel number detection method and system | |
| EP2567266A2 (en) | Method and system for sliding door pattern cancellation in metal detection | |
| CN116977807A (en) | Multi-sensor fusion-based intelligent monitoring system and method for refrigerator | |
| KR101207779B1 (en) | A signal processing apparatus for an equipment for electronic warfare and a signal processing method thereof | |
| CN106230544A (en) | The monitoring identification of a kind of automobile remote-control interference signal and localization method | |
| CN115412188A (en) | Power distribution station room operation behavior identification method based on wireless sensing | |
| CN108199757B (en) | A method of it is invaded using channel state information detection consumer level unmanned plane | |
| CN109918994A (en) | A kind of act of violence detection method based on commercial Wi-Fi | |
| Gupta et al. | Device-free crowd count estimation using passive UHF RFID technology | |
| Parada et al. | Smart surface: RFID-based gesture recognition using k-means algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |