CN116740846A - RFID intelligent top-mounted access control terminal control method - Google Patents
RFID intelligent top-mounted access control terminal control method Download PDFInfo
- Publication number
- CN116740846A CN116740846A CN202310966592.1A CN202310966592A CN116740846A CN 116740846 A CN116740846 A CN 116740846A CN 202310966592 A CN202310966592 A CN 202310966592A CN 116740846 A CN116740846 A CN 116740846A
- Authority
- CN
- China
- Prior art keywords
- signal
- audio
- sound source
- acquiring
- sound
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000013136 deep learning model Methods 0.000 claims abstract description 15
- 230000005236 sound signal Effects 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 8
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000004807 localization Effects 0.000 claims description 4
- 230000005855 radiation Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 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
- 238000013461 design Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The application discloses an RFID intelligent top-mounted access control terminal control method which is applied to an access control terminal, wherein a radio frequency module of the access control terminal comprises a signal processing module and two groups of directional antennas, and the two groups of directional antennas are arranged at intervals and face different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps: acquiring a sound source signal; sending the sound source signal into a pre-trained deep learning model to output a positioning signal; and controlling the directional antennas facing the user in the two groups of directional antennas to be connected with the signal processing module according to the positioning signals. The antenna of the access control terminal has a larger radiation distance range and a larger radiation angle range.
Description
Technical Field
The application relates to the technical field of access control, in particular to an RFID intelligent top-mounted access control terminal control method.
Background
The RFID technology is a non-contact near-distance automatic identification technology, and the basic principle is that by means of the energy transmission characteristic of electromagnetic field coupling, a radio frequency signal is utilized to supply power to an electronic tag, and a signal sent by the electronic tag is obtained, so that the electronic tag is identified, and further, the object is automatically identified. Compared with the traditional access control terminal, the RFID intelligent access control terminal is higher in recognition efficiency and accuracy.
The RFID intelligent access control terminal is widely applied to the fields of clothing business over-retail, personnel access management, fixed asset, intelligent warehouse management, vehicle management and the like; compared with other installation modes, the roof-mounted door control occupies fewer places, and therefore the roof-mounted door control is widely applied. Aiming at the application scenario that the RFID intelligent top-mounted access control terminal is applied to an intelligent access door, the personnel access management is realized, and how to improve the identification distance of an RFID system with low cost is a current research hot spot.
Disclosure of Invention
The application mainly aims to provide a control method of an RFID intelligent top-mounted access control terminal, aiming at improving the identification distance of an RFID system at low cost.
In the RFID intelligent top-mounted access terminal control method, the access terminal is used for identifying users entering and exiting a door, and the radio frequency module of the access terminal comprises a signal processing module and two groups of directional antennas, wherein the two groups of directional antennas are arranged at intervals and face different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps: acquiring a sound source signal; sending the sound source signal into a pre-trained deep learning model to output a positioning signal; wherein the positioning signal comprises a first direction signal and a second direction signal; and controlling the directional antennas facing the user in the two groups of directional antennas to be connected with the signal processing module according to the positioning signals.
In an embodiment, the sound source signals comprise at least two sound source signals of different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps:
acquiring distance signals according to sound source signals in two different directions;
and controlling the transmitting power of the corresponding antenna according to the distance signal.
In one embodiment, the sound source signal comprises a footstep sound signal, and the RFID intelligent top-mounted access control terminal control method comprises the following steps:
presetting the identification power of an antenna according to the frequency of the footstep sound; wherein the recognition power is in a proportional relationship with the frequency of the footstep sound.
In one embodiment, the acquisition of the sound source signal is: acquiring a sound source signal in a preset time interval, wherein the sound source signal comprises a plurality of frames of audio frames;
feeding the acoustic source signal into a pre-trained deep learning model to output a localization signal, comprising:
acquiring and storing spatial features of the audio frames;
the spatial characteristics of the L-th to N-th frames of audio frames with time sequence are sent into a fusion network to output the space-time joint characteristics of the audio frames; the spatial characteristics of the L-1 frame audio frame are prestored, the spatial characteristics of the N frame audio frame are obtained in real time, L is greater than or equal to 1, and N is greater than or equal to L;
and outputting a positioning signal according to the space-time joint characteristic of the audio frame.
In an embodiment, the method for controlling the RFID intelligent top-loading access terminal further includes:
and when L is greater than 10, deleting the spatial characteristics of the L-1 frame audio frame.
In one embodiment, acquiring and storing spatial features of an audio frame includes:
respectively imaging an audio frame and the audio frame of the next frame to obtain a first audio image and a second audio image;
acquiring first association features of a first audio image and a second audio image;
the first association feature and the first audio image are subjected to splicing processing to obtain a spliced image;
and sending the spliced images into a fully-connected network for fusion processing to obtain the spatial characteristics of the audio frames.
In an embodiment, acquiring the first associated feature of the first audio image and the second audio image comprises:
convolving the first audio image to obtain a first feature map;
convolving the second audio image to obtain a second feature map;
splicing the first feature map and the second feature map to obtain a spliced image;
and sending the spliced images into a fully-connected network for fusion processing to obtain a first correlation characteristic.
In one embodiment, before sending the acoustic source signal into the pre-trained deep learning model to output the localization signal, the method further comprises:
the method comprises the steps of obtaining the mean square energy of each audio frame of a continuous audio frame interval;
acquiring the mean value of the mean square energy of all the audio frames, and recording the mean value as the mean square energy mean value;
if the mean square energy of more than 60% of the audio frames in the continuous audio frame interval is greater than the mean square energy mean value, the audio frames in the continuous audio frame interval are sent to a pre-trained deep learning model.
In one embodiment, outputting the positioning signal based on the spatio-temporal joint characteristics of the audio frames comprises:
sending the fusion characteristic into an orientation classifier, acquiring orientation characteristic information, and outputting a first direction signal or a second direction signal;
sending the orientation characteristic information into a step sound class classifier, and outputting a human step sound signal or a non-human step sound signal;
when the step sound class classifier outputs human step sound signals, the directional antennas facing the user in the two groups of directional antennas are controlled to be connected with the signal processing module according to the positioning signals. If the step sound class classifier outputs a non-human step sound signal, the current connection state of the antenna and the signal processing module is maintained.
In one embodiment, the access terminal comprises a controller, the radio frequency module further comprises an antenna switch, and the antenna switch is provided with two groups of first ends and a second end; the two groups of first ends of the line switch are connected with the two groups of antennas in a one-to-one correspondence manner, the second end of the antenna switch is connected with the first end of the signal processing module, and the controlled end of the antenna switch module and the second end of the signal processing module are respectively connected with the controller.
According to the technical scheme, the direction of the user relative to the access control terminal is obtained through the sound source signal, and the directional antenna facing the user is controlled to be connected with the signal processing module, so that the antenna of the access control terminal has a larger radiation distance range and a larger radiation angle range.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an embodiment of a method for controlling an RFID intelligent top entry control terminal according to the present application;
FIG. 2 is a flowchart of another embodiment of a method for controlling an RFID intelligent top-loading access terminal according to the present application;
fig. 3 is a flowchart of a control method of an RFID intelligent top-loading access terminal according to another embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Furthermore, descriptions such as those referred to as "first," "second," and the like, are provided for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying an order of magnitude of the indicated technical features in the present disclosure. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.
The access control terminal is used for identifying users entering and exiting the door, and in some scenes, the users enter a preset place (such as a library) from the intelligent access door, and the access control terminal needs to identify the identities of the users as far as possible and confirm whether the users leave the library or enter the library.
In an embodiment of the application, a radio frequency module of an access terminal comprises a signal processing module, two groups of directional antennas, an antenna change-over switch and a signal processing module, wherein the two groups of directional antennas are arranged at intervals and have different orientations, and the antenna change-over switch is provided with two groups of first ends and a second end; the two groups of first ends of the line switch are connected with the two groups of antennas in a one-to-one correspondence manner, the second end of the antenna switch is connected with the first end of the signal processing module, and the controlled end of the antenna switch module and the second end of the signal processing module are respectively connected with the controller of the access control terminal.
Compared with an omni-directional antenna, the directional antenna adopted by the embodiment has a larger radiation distance range under the same condition, but has a smaller radiation angle range; based on the above situation, firstly, the application improves the radiation angle range of the antennas by setting the two groups of directional antennas with different orientations, and secondly, the two groups of directional antennas are arranged at intervals because the space between the two groups of antennas is not required to be radiated, thereby further improving the radiation distance range of the antennas; the interval distance can be set according to the appearance design requirement of the product and the actual application scene; in addition, the application uses the change-over switch, multiplexes the signal processing module, has reduced the power consumption and cost.
Referring to fig. 1, in an embodiment, in order to implement effective switching of two groups of antennas, the RFID intelligent top-loading access control terminal control method includes:
s100, acquiring a sound source signal;
the sound source signal may be acquired by a single microphone or an array of microphones, for example. The sound source signal includes at least amplitude information and frequency information.
S200, sending the sound source signal into a pre-trained deep learning model to output a positioning signal; wherein the positioning signal comprises a first direction signal and a second direction signal;
for example, a large number of sound source signals from a first direction and a second direction may be acquired and marked as first direction signals and second direction signals; and then training the depth information model by using the marked sound source signals.
And S300, controlling the directional antennas facing the user in the two groups of directional antennas to be connected with the signal processing module according to the positioning signals.
The two sets of directional antennas are respectively corresponding to a first direction signal and a second direction signal, when the sound source signal indicates that the user is coming from the first direction, the directional antenna controlling the first direction is connected with the signal processing module, and when the sound source signal indicates that the user is coming from the second direction, the directional antenna controlling the second direction is connected with the signal processing module. Each set of directional antennas may include multiple directional antennas with a complement of radiation ranges to collectively radiate a larger angular range. In addition, the positioning signal may also confirm whether the user is leaving or entering.
According to the technical scheme, the direction of the user relative to the access control terminal is obtained through the sound source signal, and the directional antenna facing the user is controlled to be connected with the signal processing module, so that the antenna of the access control terminal has a larger radiation distance range and a larger radiation angle range.
In an embodiment, the sound source signals comprise sound source signals of at least two different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps: acquiring distance signals according to sound source signals in two different directions; and controlling the transmitting power of the corresponding antenna according to the distance signal. The two differently directed sound source signals refer to the different direction of the sound source relative to the microphone.
According to the embodiment, two microphones with different positions can be arranged, the directions of the same sound source signal relative to different microphones are different, and the time for receiving the sound source signal is also different, so that the distance between the sound source signal and an access terminal can be calculated, and the transmitting power of an antenna is set to be larger as the distance is longer.
In one embodiment, the sound source signal comprises a footstep sound signal; in this embodiment, the method for controlling the RFID intelligent top-loading access control terminal includes: :
presetting the identification power of the antenna according to the frequency of the footstep sound; wherein the identification power is proportional to the frequency of the footstep sound.
In some scenarios, the user may pass through the intelligent access door at a faster speed, such as running, and the frequency of the footstep sound may also increase, so that the higher the frequency, the faster the user speed, and the greater the identification power of the set antenna, the more the omission ratio and the false detection ratio may be reduced.
In practical application, in order to improve the accuracy of direction detection, S100, the acquiring a sound source signal is acquiring a sound source signal within a preset time interval, where the sound source signal includes multiple frames of audio frames.
The sound source signal is continuously acquired, that is, the microphone always acquires the sound source signal during the operation of the access terminal, so that the sound source signal needs to be continuously detected and classified.
In an embodiment, in order to reduce the calculation amount of the deep learning model, the deep learning model is beneficial to being deployed at an access control terminal, the calculation force requirement of a reader is reduced, and meanwhile, the detection accuracy is considered.
Referring to fig. 2, step S200, the step of sending the sound source signal into the pre-trained deep learning model to output a localization signal includes:
s201, acquiring and storing spatial features of an audio frame;
in practical applications, the characteristics of the audio frame itself may be obtained. For example, the amplitude, frequency and root mean square of the audio frame, or the audio is imaged to obtain the spatial characteristics of the audio image, or the associated characteristics of the audio frame and the audio frame of the next frame can be obtained, for example, the audio frame and the audio frame of the next frame are respectively imaged to obtain a first audio image and a second audio image, and then the optical flow information and the pixel change information of the first audio image and the second audio image are obtained.
S202, spatial features of the L-th to N-th audio frames with time sequence are sent into a fusion network to output space-time joint features of the audio frames; the spatial characteristics of the L-1 frame audio frame are prestored, the spatial characteristics of the N frame audio frame are obtained in real time, L is greater than or equal to 1, and N is greater than or equal to L;
for example, in the first calculation, 10 audio frames may be sampled first, and the space-time joint features of the 10 audio frames may be obtained and recorded as first to tenth space-time joint features and stored; and in the second calculation, acquiring an air-air joint characteristic, namely an eleventh air-air joint characteristic, and then in the second calculation, sending the air-air joint characteristic into the second to eleventh air joint characteristics of the time fusion network, wherein only 1 frame is acquired in real time, so that the calculated amount is reduced, and the subsequent third and fourth calculations are similar. Furthermore, in some embodiments, when L is greater than 10, the spatial features of the L-1 st audio frame are deleted to save storage space. In practical applications, numbers other than 10 may be used, for example 15, 20.
When the method is needed, the characteristics output by the fusion network also comprise time characteristics because the L-th to N-th audio frames with time sequences are included, and the calculation time is reduced because the spatial characteristics of the acquired partial audio frames are recycled. The temporal order of the L-th to N-th audio frames may be sequentially from early to late.
S203, outputting a positioning signal according to the space-time joint characteristics of the audio frames. The space-time combined characteristic can be specifically sent to a softmax function to achieve acquisition of the positioning signal.
Referring to fig. 3, in one embodiment, S201 acquires spatial features of an audio frame and stores the spatial features including:
s2011, respectively imaging an audio frame and an audio frame of the next frame to obtain a first audio image and a second audio image;
the imaging may be acquisition of mel-frequency spectrograms, glamer angle field maps, wavelet transform maps, etc.
S2012, acquiring first association features of the first audio image and the second audio image;
s2013, performing stitching processing on the first associated feature and the first audio image to obtain a stitched image;
s2014, sending the spliced images into a fully-connected network for fusion processing to obtain the spatial characteristics of the audio frames.
In this embodiment, the spatial features of the audio frame include both information of the audio frame itself (information of the first audio image) and change information of the audio frame (first associated features of the first audio image and the second audio image), which is beneficial to improving detection accuracy. It should be noted that, the simultaneous acquisition of the information and the change information of the audio frame brings about a larger calculation amount, but the subsequent recognition step can repeatedly use the spatial features of the audio frame because the spatial features of part of the audio frame are stored, so that only the spatial features of one frame of audio frame need to be acquired for each subsequent recognition, and therefore, the depth information model of the application has higher accuracy and lower calculation amount.
In an embodiment, S2012, the acquiring the first associated feature of the first audio image and the second audio image specifically includes: convolving the first audio image to obtain a first feature map; convolving the second audio image to obtain a second feature map; splicing the first feature map and the second feature map to obtain a spliced image; and sending the spliced images into a fully-connected network for fusion processing to obtain a first correlation characteristic.
In comparison with the acquisition of optical flow information or pixel change information of the first audio image and the second audio image, the present embodiment acquires convolution information, the process of convolution processing extracts the features of the first audio image and the second audio image, and the data amount of the first feature map and the second feature map is smaller than the first audio image and the second audio image. Compared with the scheme of acquiring a light flow graph through optical flow calculation or acquiring a pixel difference graph through pixel difference calculation, the embodiment is beneficial to reducing the calculation amount.
In order to reduce the interference of the sound source signal, the sound source signal needs to be filtered first, and in one embodiment, before the sound source signal is sent to the pre-trained deep learning model to output the positioning signal, the method further includes:
the method comprises the steps of obtaining the mean square energy of each audio frame of a continuous audio frame interval;
the consecutive audio frame section refers to audio frames, such as the above-mentioned L-th to N-th frames, or 10 frames, of which the depth information pattern is recognized once.
Acquiring the mean value of the mean square energy of all the audio frames, and recording the mean value as the mean square energy mean value; if the mean square energy of more than 60% of the audio frames in the continuous audio frame interval is greater than the mean square energy mean value, the audio frames in the continuous audio frame interval are sent to a pre-trained deep learning model.
In this embodiment, define: if the mean square energy of the audio frames below 60% of the continuous audio frame interval is less than the mean square energy mean value, the continuous audio frame interval is considered not to be the user's footstep. If the mean square energy of more than 60% of the audio frames in the continuous audio frame interval is greater than the mean square energy mean value, the continuous audio frame interval is considered to be the footstep sound of the user. And the comparison object is the mean value of the mean square energy of all the audio frames, thus reducing the interference of the environmental interference sound source.
In practical application, the mean square energy of the audio frames of less than 60% of the multiple continuous audio frame intervals is smaller than the mean square energy mean value, so that the entrance guard terminal can be controlled to enter a low-power consumption mode, and only the microphone works at the moment.
In some embodiments, S203, outputting the positioning signal according to the spatio-temporal joint characteristics of the audio frame comprises:
sending the fusion characteristics into an orientation classifier, acquiring orientation characteristic information, and outputting a first direction signal or a second direction signal;
sending the orientation characteristic information into a step sound class classifier, and outputting a human step sound signal or a non-human step sound signal;
when the step sound class classifier outputs human step sound signals, the directional antennas facing the user in the two groups of directional antennas are controlled to be connected with the signal processing module according to the positioning signals. If the step sound class classifier outputs a non-human step sound signal, the current connection state of the antenna and the signal processing module is maintained.
In this embodiment, the two classifiers may use a cross entropy loss function to perform loss calculation and counter-propagate, where the cross entropy loss function may enable labels of the two classifiers to both affect the weight matrix of the model. The present embodiment uses a footstep class classifier and an orientation classifier in series; in training the model, the labels of the data may include human or non-human footstep sounds, first direction signals, or second direction signals. Because the orientation is distinguished firstly, and then whether human footstep sounds are distinguished or not, the recognition logic of the neural network is more met.
The foregoing description is only of the optional embodiments of the present application, and is not intended to limit the scope of the application, and all the equivalent structural changes made by the description of the present application and the accompanying drawings or the direct/indirect application in other related technical fields are included in the scope of the application.
Claims (10)
1. The RFID intelligent top-mounted access control terminal control method is characterized in that a radio frequency module of the access control terminal comprises a signal processing module and two groups of directional antennas, wherein the two groups of directional antennas are arranged at intervals and face different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps:
acquiring a sound source signal;
sending the sound source signal into a pre-trained deep learning model to output a positioning signal; wherein the positioning signal comprises a first direction signal and a second direction signal;
and controlling the directional antennas facing the user in the two groups of directional antennas to be connected with the signal processing module according to the positioning signals.
2. The method for controlling the RFID intelligent top-loading access terminal according to claim 1, wherein the sound source signals include at least two sound source signals in different directions; the RFID intelligent top-loading type access control terminal control method comprises the following steps:
acquiring distance signals according to sound source signals in two different directions;
and controlling the transmitting power of the corresponding antenna according to the distance signal.
3. The RFID intelligent top-loading access terminal control method of claim 2, wherein the sound source signal comprises a footstep sound signal, the RFID intelligent top-loading access terminal control method comprising:
presetting the identification power of the antenna according to the frequency of the footstep sound; wherein the identification power is proportional to the frequency of the footstep sound.
4. The method for controlling an RFID intelligent top-loading access terminal as claimed in claim 3, wherein the acquiring the sound source signal is: acquiring a sound source signal in a preset time interval, wherein the sound source signal comprises a plurality of frames of audio frames;
the sending the sound source signal into a pre-trained deep learning model to output a localization signal, comprising:
acquiring and storing spatial features of the audio frames;
the spatial characteristics of the L-th to N-th frames of audio frames with time sequence are sent into a fusion network to output the space-time joint characteristics of the audio frames; the spatial characteristics of the L-1 frame audio frame are prestored, the spatial characteristics of the N frame audio frame are obtained in real time, L is greater than or equal to 1, and N is greater than or equal to L;
and outputting a positioning signal according to the space-time joint characteristic of the audio frame.
5. The method for controlling an RFID smart top-loading access terminal as claimed in claim 4, further comprising:
and when L is greater than 10, deleting the spatial characteristics of the L-1 frame audio frame.
6. The method for controlling an RFID intelligent top-loading access terminal of claim 4, wherein the acquiring and storing spatial features of the audio frame comprises:
respectively imaging an audio frame and the audio frame of the next frame to obtain a first audio image and a second audio image;
acquiring first association features of a first audio image and a second audio image;
the first association feature and the first audio image are subjected to splicing processing to obtain a spliced image;
and sending the spliced images into a fully-connected network for fusion processing to obtain the spatial characteristics of the audio frames.
7. The method of controlling an RFID intelligent top-loading access terminal of claim 6, wherein obtaining the first associated characteristic of the first audio image and the second audio image comprises:
convolving the first audio image to obtain a first feature map;
convolving the second audio image to obtain a second feature map;
splicing the first feature map and the second feature map to obtain a spliced image;
and sending the spliced images into a fully-connected network for fusion processing to obtain a first correlation characteristic.
8. The method for controlling an RFID smart top-loading access terminal according to any one of claims 4 to 7, wherein before the feeding the sound source signal into the pre-trained deep learning model to output the positioning signal, further comprising:
the method comprises the steps of obtaining the mean square energy of each audio frame of a continuous audio frame interval;
acquiring the mean value of the mean square energy of all the audio frames, and recording the mean value as the mean square energy mean value;
if the mean square energy of more than 60% of the audio frames in the continuous audio frame interval is greater than the mean square energy mean value, the audio frames in the continuous audio frame interval are sent to a pre-trained deep learning model.
9. The method of controlling an RFID intelligent top-loading access terminal of claim 6, wherein outputting a positioning signal based on a spatio-temporal joint characteristic of an audio frame comprises:
sending the fusion characteristics into an orientation classifier, acquiring orientation characteristic information, and outputting a first direction signal or a second direction signal;
sending the orientation characteristic information into a step sound class classifier, and outputting a human step sound signal or a non-human step sound signal;
when the step sound class classifier outputs human step sound signals, the directional antennas facing the user in the two groups of directional antennas are controlled to be connected with the signal processing module according to the positioning signals. If the step sound class classifier outputs a non-human step sound signal, the current connection state of the antenna and the signal processing module is maintained.
10. The method of claim, wherein the access terminal comprises a controller, and the radio frequency module further comprises an antenna switch having two sets of first ends and a second end; the two groups of first ends of the line switch are connected with the two groups of antennas in a one-to-one correspondence manner, the second end of the antenna switch is connected with the first end of the signal processing module, and the controlled end of the antenna switch module and the second end of the signal processing module are respectively connected with the controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310966592.1A CN116740846A (en) | 2023-08-02 | 2023-08-02 | RFID intelligent top-mounted access control terminal control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310966592.1A CN116740846A (en) | 2023-08-02 | 2023-08-02 | RFID intelligent top-mounted access control terminal control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116740846A true CN116740846A (en) | 2023-09-12 |
Family
ID=87918885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310966592.1A Pending CN116740846A (en) | 2023-08-02 | 2023-08-02 | RFID intelligent top-mounted access control terminal control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116740846A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130009820A1 (en) * | 2011-07-08 | 2013-01-10 | Psion Inc. | Antenna apparatus for determining the position of a radio-frequency transponder |
| US20130278388A1 (en) * | 2007-07-27 | 2013-10-24 | Lucomm Technologies, Inc. | Systems and methods for object localization and path identification based on rfid sensing |
| US20140375431A1 (en) * | 2007-07-27 | 2014-12-25 | Lucomm Technologies, Inc. | Systems and methods for object localization and path identification based on rfid sensing |
| CN107195057A (en) * | 2017-06-27 | 2017-09-22 | 天津市滨海新区军民融合创新研究院 | A kind of intelligent access control system and its control method |
| CN110223715A (en) * | 2019-05-07 | 2019-09-10 | 华南理工大学 | It is a kind of based on sound event detection old solitary people man in activity estimation method |
| CN212341991U (en) * | 2020-01-03 | 2021-01-12 | 上海思亮信息技术股份有限公司 | Self-service police article borrowing and returning system |
| WO2021164389A1 (en) * | 2020-02-21 | 2021-08-26 | 深圳市云伽智能技术有限公司 | Intelligent lock access control system, control method and apparatus, device, and storage medium |
| CN116065329A (en) * | 2021-10-29 | 2023-05-05 | 青岛海尔洗衣机有限公司 | Control method and device for clothes treatment equipment |
-
2023
- 2023-08-02 CN CN202310966592.1A patent/CN116740846A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130278388A1 (en) * | 2007-07-27 | 2013-10-24 | Lucomm Technologies, Inc. | Systems and methods for object localization and path identification based on rfid sensing |
| US20140375431A1 (en) * | 2007-07-27 | 2014-12-25 | Lucomm Technologies, Inc. | Systems and methods for object localization and path identification based on rfid sensing |
| US20130009820A1 (en) * | 2011-07-08 | 2013-01-10 | Psion Inc. | Antenna apparatus for determining the position of a radio-frequency transponder |
| CN107195057A (en) * | 2017-06-27 | 2017-09-22 | 天津市滨海新区军民融合创新研究院 | A kind of intelligent access control system and its control method |
| CN110223715A (en) * | 2019-05-07 | 2019-09-10 | 华南理工大学 | It is a kind of based on sound event detection old solitary people man in activity estimation method |
| CN212341991U (en) * | 2020-01-03 | 2021-01-12 | 上海思亮信息技术股份有限公司 | Self-service police article borrowing and returning system |
| WO2021164389A1 (en) * | 2020-02-21 | 2021-08-26 | 深圳市云伽智能技术有限公司 | Intelligent lock access control system, control method and apparatus, device, and storage medium |
| CN116065329A (en) * | 2021-10-29 | 2023-05-05 | 青岛海尔洗衣机有限公司 | Control method and device for clothes treatment equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934117B (en) | Pedestrian re-identification detection method based on generation of countermeasure network | |
| CN110659543B (en) | Gesture recognition-based vehicle control method and system and vehicle | |
| CN104794894A (en) | Automobile whistle noise monitoring device, system and method | |
| JPH07151857A (en) | System for tracking and guiding millimeter wave of three-dimensional image | |
| CN111882681B (en) | Vehicle information identification method based on parking behavior and parking system | |
| CN107301358A (en) | Passive electronic label, passive electronic label control method, apparatus and system | |
| DE112017004427T5 (en) | SYSTEM AND METHOD FOR DETERMINING A MICROWAVE BEAM AND A POWER ADJUSTMENT FOR A WIRELESS POWER TRANSMISSION IN A VOLUME | |
| CN103218621A (en) | Identification method of multi-scale vehicles in outdoor video surveillance | |
| CN112859033A (en) | Target detection method, device and related equipment | |
| CN110058233A (en) | A kind of anti-duplicity interference method of multistatic SARS system | |
| KR20210007225A (en) | Method and apparatus for determining the location of a user device in a vehicle environment | |
| CN110109090A (en) | Circumstances not known multi-target detection method and device based on microwave radar | |
| CN111862616A (en) | Open area vehicle information identification method and parking system | |
| CN116740846A (en) | RFID intelligent top-mounted access control terminal control method | |
| Abdou et al. | Crowd counting: a survey of machine learning approaches | |
| CN109547936A (en) | Indoor orientation method based on Wi-Fi signal and environmental background sound | |
| CN116559778B (en) | Vehicle whistle positioning method and system based on deep learning | |
| CN110121055B (en) | Method and apparatus for object recognition | |
| CN116777953A (en) | Remote sensing image target tracking method based on multi-scale feature aggregation enhancement | |
| US20050152582A1 (en) | Multiple person detection apparatus and method | |
| CN116406056A (en) | Street lamp control method and device based on IA-YOLO target detection | |
| CN109714094A (en) | A kind of blind adaptive beamforming algorithm | |
| Thomanek et al. | Comparing visual data fusion techniques using fir and visible light sensors to improve pedestrian detection | |
| Zhu et al. | Fusion of wireless signal and computer vision for identification and tracking | |
| CN113591695A (en) | Pedestrian re-identification method and device based on millimeter wave radar point cloud |
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 |