CN113807459B - Inductive switch control method and system and electronic equipment - Google Patents
Inductive switch control method and system and electronic equipment Download PDFInfo
- Publication number
- CN113807459B CN113807459B CN202111136073.XA CN202111136073A CN113807459B CN 113807459 B CN113807459 B CN 113807459B CN 202111136073 A CN202111136073 A CN 202111136073A CN 113807459 B CN113807459 B CN 113807459B
- Authority
- CN
- China
- Prior art keywords
- phase
- vector
- inductive switch
- infrared detector
- infrared
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000001939 inductive effect Effects 0.000 title claims description 89
- 238000001514 detection method Methods 0.000 claims abstract description 131
- 238000012937 correction Methods 0.000 claims abstract description 83
- 239000013598 vector Substances 0.000 claims description 124
- 230000033001 locomotion Effects 0.000 claims description 35
- 238000003062 neural network model Methods 0.000 claims description 29
- 230000000694 effects Effects 0.000 claims description 21
- 230000001133 acceleration Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 230000002238 attenuated effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 239000000654 additive Substances 0.000 claims description 6
- 230000000996 additive effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006698 induction Effects 0.000 abstract description 31
- 238000000605 extraction Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 6
- 230000002035 prolonged effect Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000011144 upstream manufacturing Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03K—PULSE TECHNIQUE
- H03K17/00—Electronic switching or gating, i.e. not by contact-making and –breaking
- H03K17/94—Electronic switching or gating, i.e. not by contact-making and –breaking characterised by the way in which the control signals are generated
- H03K17/941—Electronic switching or gating, i.e. not by contact-making and –breaking characterised by the way in which the control signals are generated using an optical detector
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The application discloses a control method, a control system and an electronic device of an induction switch, which perform high-dimensional feature extraction by using phase information of an infrared detection signal, so that propagation parameters and noise interference information in a propagation process can be contained by relatively simple data, the information density in a high-dimensional feature space is improved, and the application also considers the characteristics of the infrared detection signal during propagation, so that the parameter correction of the uplink propagation is further performed based on a phase feature value, the extracted features further express the information of signal propagation, and the classification accuracy is improved.
Description
Technical Field
The present application relates to the field of intelligent inductive switches, and more particularly, to an inductive switch control method, system, and electronic device.
Background
Many kinds of human body induction automatic switches have been invented by human, including traditional passive infrared pyroelectric automatic induction switches and active infrared human body induction switches.
In principle, the traditional passive infrared pyroelectric human body induction switch works through the infrared rays emitted by the human body, and the induction switch can only be turned on by human body induction but not turned off by human body induction, that is, under the action of the switch, a person can only keep the action of turning on by continuous 'movement', and under the condition, the application range of the passive infrared pyroelectric human body induction switch is greatly limited.
The active infrared human body induction switch works by actively sending out infrared detection signals. Although the human body induction instant switch can realize the human body induction instant switch function of ' on-off by people ' in the coming of people's hand, the action range is limited, the human body can be induced to exist only in a limited range covered by an optical path of the human body induction switch, so that the on or off function is realized, and meanwhile, the human body induction switch in the mode has the problems of poor anti-interference capability and high self energy consumption.
It is therefore desirable to provide an optimized control scheme for a medium active inductive switch.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. Embodiments of the present application provide a method, system, and electronic device for controlling an inductive switch, which perform high-dimensional feature extraction by using phase information of an infrared detection signal itself, so that propagation parameters and noise interference information in a propagation process can be included with relatively simple data, so as to improve information density in a high-dimensional feature space, and further consider characteristics of the infrared detection signal during propagation, so that uplink parameter correction is further performed based on a phase feature value, so that the extracted features further express information of signal propagation, and classification accuracy is improved.
According to an aspect of the present application, there is provided an inductive switch control method, comprising:
acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination time period;
constructing phase data of the infrared detection signals at a series of preset time points into phase vectors arranged in a time dimension;
passing the phase vector through a deep neural network model to obtain a phase feature vector, wherein the phase feature vector is used for representing high-dimensional implicit features of phase data of infrared detection signals at each time point and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points;
calculating uplink correction eigenvalues of all positions in the phase eigenvector based on eigenvalues of all positions in the phase eigenvector, wherein the uplink correction eigenvalues are also generated based on the transmission power of the infrared detector, the distance between the infrared detector and a detection object, the small-scale attenuation effect parameters from the infrared detector to the detection object and the small-scale attenuation power components from the infrared detector to the detection object;
arranging the uplink correction eigenvalues at each position into uplink correction eigenvectors;
Inputting the uplink correction feature vector into a classifier to obtain a classification result, wherein the classification result is used for representing the motion mode of a monitored object; and
and determining the control state of the inductive switch based on the classification result.
In the above-mentioned inductive switch control method, passing the phase vector through a deep neural network model to obtain a phase feature vector includes: performing full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model to extract high-dimensional implicit characteristics of phase data of infrared detection signals at all time points in the phase vector; and performing one-dimensional convolutional encoding on the phase vector by using a one-dimensional convolutional layer of the deep neural network model to extract associated high-dimensional implicit features between phase data of infrared detection signals at two adjacent time points in the phase vector.
In the above-mentioned inductive switch control method, calculating the uplink correction eigenvalue of each position in the phase eigenvector based on the eigenvalue of each position in the phase eigenvector includes: based on the characteristic values of all the positions in the phase characteristic vector, calculating uplink correction characteristic values of all the positions in the phase characteristic vector according to the following formula; the formula is:
Wherein the method comprises the steps ofIs a phase characteristic value，T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is the small-scale attenuation effect parameter of the infrared detector to the detection object, hT ,O Is the small-scale attenuated power component of the infrared detector to the detection object, and sigma 2 Representing the power of the additive white gaussian noise.
In the above-mentioned inductive switch control method, the small-scale attenuation effect parameters from the infrared detector to the detection object include path loss and shielding loss; and the small-scale attenuated power component of the infrared detector to the detection object is related to the emission frequency of the infrared detector.
In the above-mentioned inductive switch control method, inputting the uplink correction feature vector into a classifier to obtain a classification result includes: inputting the uplink correction feature vector into a Softmax classification function of the classifier to obtain a plurality of probability values of the uplink correction feature vector respectively belonging to different motion mode labels; and determining a motion mode label corresponding to the maximum probability value in the plurality of probability values as the classification result.
In the above-mentioned inductive switch control method, the motion mode tag includes: stationary, constant speed travel, acceleration travel, deceleration travel.
In the above-mentioned inductive switch control method, determining the control state of the inductive switch based on the classification result includes: responding to the classification result to be uniform traveling, and determining the prolonged closing time of the induction switch based on the uniform traveling speed; determining an extended off time of the inductive switch based on an acceleration of the acceleration travel in response to the classification result being uniform traveling; and determining an extended off time of the induction switch based on an acceleration of the deceleration traveling in response to the classification result being uniform traveling.
According to another aspect of the present application, there is provided an inductive switch control system comprising:
a data acquisition unit for acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination period;
a phase vector arrangement unit configured to arrange phase data of the series of infrared detection signals at predetermined time points obtained by the data acquisition unit into phase vectors in a time dimension;
the deep neural network processing unit is used for passing the phase vectors obtained by the phase vector arrangement unit through a deep neural network model to obtain phase feature vectors, wherein the phase feature vectors are used for representing high-dimensional implicit features of phase data of infrared detection signals at all time points and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points;
An uplink correction eigenvalue calculation unit, configured to calculate an uplink correction eigenvalue for each position in the phase eigenvector based on the eigenvalue for each position in the phase eigenvector obtained by the deep neural network processing unit, where the uplink correction eigenvalue is further generated based on a transmission power of the infrared detector, a distance between the infrared detector and a detection object, a small-scale attenuation effect parameter from the infrared detector to the detection object, and a small-scale attenuation power component from the infrared detector to the detection object;
a feature vector generation unit configured to arrange the uplink correction feature values obtained by the uplink correction feature value calculation unit at each position into an uplink correction feature vector;
a classification unit, configured to input the uplink correction feature vector obtained by the feature vector generation unit into a classifier to obtain a classification result, where the classification result is used to represent a motion mode of a monitored object; and
and the determining unit is used for determining the control state of the inductive switch based on the classification result obtained by the classifying unit.
In the above-mentioned inductive switch control system, the deep neural network processing unit includes: the full-connection coding subunit is used for carrying out full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model so as to extract high-dimensional implicit characteristics of phase data of infrared detection signals at each time point in the phase vector; and a one-dimensional convolution encoding subunit, configured to perform one-dimensional convolution encoding on the phase vector using a one-dimensional convolution layer of the depth neural network model to extract a high-dimensional implicit feature of a correlation between phase data of infrared detection signals at two adjacent time points in the phase vector.
In the above-mentioned inductive switch control system, the uplink correction feature value calculating unit is further configured to: based on the characteristic values of all the positions in the phase characteristic vector, calculating uplink correction characteristic values of all the positions in the phase characteristic vector according to the following formula; the formula is:
wherein the method comprises the steps ofIs the characteristic value of phase, T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is the small-scale attenuation effect parameter of the infrared detector to the detection object, hT ,O Is the small-scale attenuated power component of the infrared detector to the detection object, and sigma 2 Representing the power of the additive white gaussian noise.
In the above-mentioned inductive switch control system, the small-scale attenuation effect parameters of the detection object from the infrared detector include path loss and shielding loss; and the small-scale attenuated power component of the infrared detector to the detection object is related to the emission frequency of the infrared detector.
In the above-mentioned inductive switch control system, the classification unit is further configured to: inputting the uplink correction feature vector into a Softmax classification function of the classifier to obtain a plurality of probability values of the uplink correction feature vector respectively belonging to different motion mode labels; and determining a motion mode label corresponding to the maximum probability value in the plurality of probability values as the classification result.
In the above-mentioned inductive switch control system, the movement pattern tag includes: stationary, constant speed travel, acceleration travel, deceleration travel.
In the above-described inductive switch control system, the determining unit is further configured to: responding to the classification result to be uniform traveling, and determining the prolonged closing time of the induction switch based on the uniform traveling speed; determining an extended off time of the inductive switch based on an acceleration of the acceleration travel in response to the classification result being uniform traveling; and determining an extended off time of the induction switch based on an acceleration of the deceleration traveling in response to the classification result being uniform traveling.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the inductive switch control method as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the inductive switch control method as described above.
Compared with the prior art, the induction switch control method, the induction switch control system and the electronic equipment provided by the application have the advantages that the high-dimensional characteristic extraction is carried out by using the phase information of the infrared detection signal, so that the propagation parameters and noise interference information in the propagation process can be contained by relatively simple data, the information density in the high-dimensional characteristic space is improved, and the characteristics of the infrared detection signal in propagation are considered, so that the uplink propagation parameters are further corrected based on the phase characteristic value, the extracted characteristics further express the signal propagation information, and the classification accuracy is improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is an application scenario diagram of an inductive switch control method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of controlling an inductive switch according to an embodiment of the application;
FIG. 3 is a schematic diagram of a system architecture of a method for controlling an inductive switch according to an embodiment of the application;
FIG. 4 is a flow chart of a method for controlling an inductive switch according to an embodiment of the application, wherein the phase vector is passed through a deep neural network model to obtain a phase eigenvector;
FIG. 5 is a block diagram of an inductive switch control system according to an embodiment of the application;
FIG. 6 is a block diagram of a deep neural network processing unit in an inductive switch control system according to an embodiment of the application;
fig. 7 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Scene overview
As described above, the active infrared human body induction switch works by actively emitting an infrared detection signal. Although the human body induction instant switch can realize the human body induction instant switch function of ' on-off by people ' in the coming of people's hand, the action range is limited, the human body can be induced to exist only in a limited range covered by an optical path of the human body induction switch, so that the on or off function is realized, and meanwhile, the human body induction switch in the mode has the problems of poor anti-interference capability and high self energy consumption. Accordingly, in order to set the on-time of the inductive switch based on the movement pattern of the human body, it is desirable to provide an inductive switch control scheme.
That is, in pattern recognition based on the infrared detection signal, it is necessary to consider characteristics of the infrared detection signal at the time of propagation in addition to data of the infrared detection signal itself, such as a phase, and therefore, it is necessary to perform appropriate transformation in a high-dimensional feature space of the signal data so that the extracted features can further accurately express information of signal propagation in order to improve accuracy of regression.
Based on this, the phase data of the infrared detection signal at a series of predetermined time points within the determination period is first acquired, because the phase data can contain noise interference information in the course of propagation in addition to general information such as propagation distance, propagation time, and therefore, the propagation environment characteristics of the signal can be expressed relatively accurately.
The resulting phase vector is then input into a deep neural network model to obtain a phase feature vector, the deep neural network comprising fully connected layers and one-dimensional convolutional layers alternately arranged so as to include correlation features of phases between respective time points in the extracted high-dimensional features.
Further, since the infrared detection signal is transmitted by the infrared detector and returned by the detection object, this corresponds substantially to the upstream propagation in the wireless propagation, and hence the upstream correction eigenvalue thereof is calculated from the phase eigenvalue of the phase eigenvector, specifically:
Wherein the method comprises the steps ofIs the characteristic value of phase, T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is a small-scale attenuation effect parameter from an infrared detector to a detection object, and comprises path lossAnd shielding loss, h T,O Is the small-scale attenuated power component of the infrared detector to the detection object, is related to the emission frequency, and sigma 2 Representing the power of the additive white gaussian noise.
And finally, inputting the uplink correction characteristic vector formed by the uplink correction characteristic values into a classifier to obtain a classification result of the motion mode.
Based on this, the application provides a control method of an inductive switch, which comprises the following steps: acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination time period; constructing phase data of the infrared detection signals at a series of preset time points into phase vectors arranged in a time dimension; passing the phase vector through a deep neural network model to obtain a phase feature vector, wherein the phase feature vector is used for representing high-dimensional implicit features of phase data of infrared detection signals at each time point and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points; calculating uplink correction eigenvalues of all positions in the phase eigenvector based on eigenvalues of all positions in the phase eigenvector, wherein the uplink correction eigenvalues are also generated based on the transmission power of the infrared detector, the distance between the infrared detector and a detection object, the small-scale attenuation effect parameters from the infrared detector to the detection object and the small-scale attenuation power components from the infrared detector to the detection object; arranging the uplink correction eigenvalues at each position into uplink correction eigenvectors; inputting the uplink correction feature vector into a classifier to obtain a classification result, wherein the classification result is used for representing the motion mode of a monitored object; and determining the control state of the inductive switch based on the classification result.
Fig. 1 illustrates an application scenario diagram of an inductive switch control method according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, phase data of an infrared detection signal at a series of predetermined time points within a determination period is acquired by an infrared detector (e.g., T as illustrated in fig. 1) of an inductive switch (e.g., K as illustrated in fig. 1), which is disposed at a fixed position within a detection area and which is capable of detecting an infrared detection signal reflected back by a human body (e.g., P as illustrated in fig. 1) in different motion modes including stationary, uniform traveling, acceleration traveling, deceleration traveling, etc., wherein the inductive switch is communicatively connected to a powered device, e.g., a lighting device (e.g., L as illustrated in fig. 1). Then, the acquired phase data of the series of infrared detection signals at predetermined time points are input to a server (e.g., S as illustrated in fig. 1) in which an inductive switch control algorithm is deployed, wherein the server is capable of processing the acquired phase data of the series of infrared detection signals at predetermined time points with the inductive switch control algorithm to generate a classification result for representing a movement pattern of the monitoring object. Further, the control state of the inductive switch is determined based on the classification result, that is, the control state of the inductive switch is determined based on the motion mode of the detected human body, in such a way that the control of the inductive switch is more intelligent, for example, when the classification result is detected that the detected human body travels at a constant speed, the extended turn-off time of the inductive switch can be determined based on the speed of the detected human body traveling at the constant speed, so as to ensure the walking safety of the human body within a short period of time after leaving the detection area.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flow chart of a method of inductive switch control. As shown in fig. 2, a method for controlling an inductive switch according to an embodiment of the present application includes: s110, acquiring phase data of infrared detection signals at a series of preset time points in a judging time period; s120, constructing phase data of the infrared detection signals at a series of preset time points into phase vectors which are arranged according to time dimension; s130, passing the phase vector through a deep neural network model to obtain a phase feature vector, wherein the phase feature vector is used for representing high-dimensional implicit features of phase data of infrared detection signals at each time point and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points; s140, calculating uplink correction characteristic values of all positions in the phase characteristic vector based on the characteristic values of all positions in the phase characteristic vector, wherein the uplink correction characteristic values are also generated based on the transmission power of the infrared detector, the distance between the infrared detector and a detection object, the small-scale attenuation effect parameters from the infrared detector to the detection object and the small-scale attenuation power components from the infrared detector to the detection object; s150, arranging the uplink correction characteristic values at all positions into uplink correction characteristic vectors; s160, inputting the uplink correction feature vector into a classifier to obtain a classification result, wherein the classification result is used for representing a motion mode of a monitored object; and S170, determining the control state of the inductive switch based on the classification result.
Fig. 3 illustrates an architecture diagram of an inductive switch control method according to an embodiment of the application. As shown IN fig. 3, IN the network architecture of the inductive switch control method, first, phase data (e.g., IN as illustrated IN fig. 3) of the obtained infrared detection signals at the series of predetermined time points are structured to be arranged IN a time dimension as phase vectors (e.g., V1 as illustrated IN fig. 3); then, passing the phase vector through a deep neural network model (e.g., DNN as illustrated in fig. 3) to obtain a phase feature vector (e.g., VF1 as illustrated in fig. 3); then, based on the eigenvalues of the respective positions in the phase eigenvectors, uplink correction eigenvalues of the respective positions in the phase eigenvector are calculated (e.g., E as illustrated in fig. 3); next, the uplink correction feature values at the respective positions are arranged as an uplink correction feature vector (e.g., VF2 as illustrated in fig. 3); then, the uplink correction feature vector is input to a classifier (e.g., circle S as illustrated in fig. 3) to obtain a classification result for representing a movement pattern of the monitoring object; and finally, determining the control state of the inductive switch based on the classification result.
In step S110 and step S120, phase data of the infrared detection signals at a series of predetermined time points within the determination period are acquired, and the phase data of the infrared detection signals at the series of predetermined time points are structured to be arranged in the time dimension as a phase vector. It will be appreciated that when a person moves within the detection area of the inductive switch, it occasionally jumps out of the detection area, in which case it is still desirable for the illumination device to remain on, and if the person moves out of the detection area with a uniform motion, the time to remain on may be set based on the speed of the uniform motion, so that the illumination device can illuminate the person for a period of time after the person leaves the preset area to direct the person away from the detection area, thereby ensuring the safety of the person's walking within a short period of time after the person leaves the detection area.
In particular, it is considered that there is a difference in reflected infrared detection signals, for example, a difference in phase, when the human body is in different movement modes. Therefore, in the technical solution of the present application, first, phase data of an infrared detection signal at a series of predetermined time points in a determination period is acquired, and it should be understood that, since the phase data can contain noise interference information during propagation in addition to general information such as propagation distance and propagation time, propagation environment characteristics of the signal can be expressed relatively accurately. And then constructing the phase data of the infrared detection signals at a series of preset time points into phase vectors which are arranged according to the time dimension so as to facilitate the extraction of high-dimensional features of the follow-up deep neural network.
In a specific example, the phase data of the infrared detection signals at a series of predetermined time points within the determination period may be acquired by an infrared detector disposed at a fixed position within the detection area, it should be understood that in this specific example, the infrared detector is capable of detecting the infrared detection signals reflected back when the human body is in different movement modes, and the movement modes include: stationary, traveling at constant speed, accelerating, decelerating, etc.
In step S130, the phase vector is passed through a deep neural network model to obtain a phase feature vector for representing a high-dimensional implicit feature of phase data of the infrared detection signals at each time point and a high-dimensional implicit feature of correlation between phase data of the infrared detection signals at adjacent two time points. That is, firstly, the obtained phase vector is input into one or more fully connected layers of a deep neural network model to be processed so as to extract high-dimensional implicit features of the phase feature vector for representing phase data of infrared detection signals at each time point; and then inputting the obtained phase vector into a one-dimensional convolution layer of a deep neural network model for processing so as to extract associated high-dimensional implicit features between phase data of infrared detection signals of two adjacent time points in the phase vector, thereby obtaining the phase feature vector.
Fig. 4 illustrates a flowchart of passing the phase vector through a deep neural network model to obtain a phase eigenvector in an inductive switch control method according to an embodiment of the present application. As shown in fig. 4, passing the phase vector through a deep neural network model to obtain a phase eigenvector includes: s210, performing full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model to extract high-dimensional implicit characteristics of phase data of infrared detection signals at each time point in the phase vector; and S220, performing one-dimensional convolution encoding on the phase vector by using a one-dimensional convolution layer of the deep neural network model to extract associated high-dimensional implicit features between phase data of infrared detection signals at two adjacent time points in the phase vector.
In step S140, based on the eigenvalues of each position in the phase eigenvector, an uplink correction eigenvalue of each position in the phase eigenvector is calculated, where the uplink correction eigenvalue is further generated based on the transmission power of the infrared detector, the distance between the infrared detector and the detection object, the small-scale attenuation effect parameter from the infrared detector to the detection object, and the small-scale attenuation power component from the infrared detector to the detection object. It should be appreciated that in pattern recognition based on an infrared detection signal, it is necessary to consider the characteristics of the infrared detection signal as it propagates in addition to the data of the infrared detection signal itself, such as the phase. That is, since the infrared detection signal is transmitted by the infrared detector and returned by the detection object, this corresponds substantially to the upstream propagation in the wireless propagation. Therefore, in the technical scheme of the application, proper transformation is required to be performed in the high-dimensional feature space of the signal data, so that the extracted high-dimensional implicit features can further accurately express the information of the signal propagation, thereby being convenient for improving the accuracy of regression. In a specific example, the up-link correction eigenvalue is calculated by adopting eigenvalues based on each position in the phase eigenvector.
Specifically, in the embodiment of the present application, based on the eigenvalues of each position in the phase eigenvector, a process of calculating an uplink correction eigenvalue of each position in the phase eigenvector includes: based on the characteristic values of all the positions in the phase characteristic vector, calculating uplink correction characteristic values of all the positions in the phase characteristic vector according to the following formula;
the formula is:
wherein the method comprises the steps ofIs the characteristic value of phase, T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is the small-scale attenuation effect parameter from the infrared detector to the detection object, h T,O Is the small-scale attenuated power component of the infrared detector to the detection object, and sigma 2 Representing the power of the additive white gaussian noise. It is worth mentioning that here, the small-scale attenuation effect parameters from the infrared detector to the detection object include path loss and shielding loss; and the small-scale attenuated power component of the infrared detector to the detection object is related to the emission frequency of the infrared detector.
In step S150 and step S160, the uplink correction feature values at the respective positions are arranged as uplink correction feature vectors, and the uplink correction feature vectors are input into a classifier to obtain a classification result for representing a movement pattern of the monitoring object. It will be appreciated that by using the phase information for high dimensional feature extraction, the propagation parameters and the noise interference information during propagation can be contained in relatively simple data, thereby increasing the information density in the high dimensional feature space, and further performing upstream parameter correction based on the phase feature values, the extracted features can be made to further represent the information of signal propagation, improving the accuracy of classification.
Specifically, in the embodiment of the present application, first, the obtained uplink correction eigenvalues of the respective positions are arranged as an uplink correction eigenvector. And then, inputting the uplink correction feature vector into a Softmax classification function of the classifier to obtain a plurality of probability values of the uplink correction feature vector respectively belonging to different motion mode labels. And finally, determining the motion mode label corresponding to the maximum probability value in the plurality of probability values as the classification result. It should be noted that, here, the movement pattern tag includes: stationary, constant speed travel, acceleration travel, deceleration travel.
In step S170, a control state of the inductive switch is determined based on the classification result. Specifically, in the embodiment of the present application, the process of determining the control state of the inductive switch based on the classification result includes: if the classification result is responded to uniform traveling, determining the prolonged closing time of the induction switch based on the uniform traveling speed; if the classification result is responded to uniform traveling, determining the prolonged closing time of the inductive switch based on the acceleration of the accelerated traveling; and if the classification result is uniform speed running, determining the prolonged closing time of the inductive switch based on the acceleration of the deceleration running.
In summary, the induction switch control method of the embodiment of the application is clarified, which performs high-dimensional feature extraction by using the phase information of the infrared detection signal, so that the propagation parameter and noise interference information in the propagation process can be contained by relatively simple data, so as to improve the information density in the high-dimensional feature space, and the application also considers the characteristic of the infrared detection signal during propagation, so that the parameter correction of the uplink propagation is further performed based on the phase feature value, so that the extracted feature further expresses the signal propagation information, and the classification accuracy is improved.
Exemplary System
Fig. 5 illustrates a block diagram of an inductive switch control system in accordance with an embodiment of the present application. As shown in fig. 5, an inductive switch control system 500 according to an embodiment of the present application includes: a data acquisition unit 510 for acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination period; a phase vector arrangement unit 520 for constructing phase data of the infrared detection signals of the series of predetermined time points obtained by the data acquisition unit 510 to be arranged in a time dimension as a phase vector; a deep neural network processing unit 530, configured to pass the phase vectors obtained by the phase vector arrangement unit 520 through a deep neural network model to obtain phase feature vectors, where the phase feature vectors are used to represent high-dimensional implicit features of phase data of infrared detection signals at respective time points and associated high-dimensional implicit features between phase data of infrared detection signals at two adjacent time points; an uplink correction eigenvalue calculation unit 540, configured to calculate an uplink correction eigenvalue for each position in the phase eigenvector based on the eigenvalue for each position in the phase eigenvector obtained by the deep neural network processing unit 530, where the uplink correction eigenvalue is further generated based on a transmission power of the infrared detector, a distance between the infrared detector and a detection object, a small-scale attenuation effect parameter from the infrared detector to the detection object, and a small-scale attenuation power component from the infrared detector to the detection object; a feature vector generating unit 550, configured to arrange the uplink correction feature values obtained by the uplink correction feature value calculating unit 540 at each position into an uplink correction feature vector; a classification unit 560 for inputting the uplink-correction feature vector obtained by the feature vector generation unit 550 into a classifier to obtain a classification result, the classification result being used to represent a motion pattern of a monitored object; and a determining unit 570 for determining a control state of the inductive switch based on the classification result obtained by the classifying unit 560.
In one example, in the above-mentioned inductive switch control system 500, as shown in fig. 6, the deep neural network processing unit 530 includes: a full-connection coding subunit 531, configured to perform full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model to extract high-dimensional implicit features of phase data of the infrared detection signals at each time point in the phase vector; and a one-dimensional convolution encoding subunit 532, configured to perform one-dimensional convolution encoding on the phase vector using a one-dimensional convolution layer of the deep neural network model to extract a high-dimensional implicit feature of a correlation between phase data of infrared detection signals at two adjacent time points in the phase vector.
In one example, in the above-mentioned inductive switch control system 500, the uplink correction feature value calculating unit 540 is further configured to: based on the characteristic values of all the positions in the phase characteristic vector, calculating uplink correction characteristic values of all the positions in the phase characteristic vector according to the following formula; the formula is:
wherein the method comprises the steps ofIs the characteristic value of phase, T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is the small-scale attenuation effect parameter from the infrared detector to the detection object, h T,O Is the small-scale attenuated power component of the infrared detector to the detection object, and sigma 2 Representing the power of the additive white gaussian noise.
In one example, in the inductive switch control system 500 described above, the small-scale attenuation effect parameters of the infrared detector to the detection object include path loss and occlusion loss; and the small-scale attenuated power component of the infrared detector to the detection object is related to the emission frequency of the infrared detector.
In one example, in the above-mentioned inductive switch control system 500, the classifying unit 560 is further configured to: inputting the uplink correction feature vector into a Softmax classification function of the classifier to obtain a plurality of probability values of the uplink correction feature vector respectively belonging to different motion mode labels; and determining a motion mode label corresponding to the maximum probability value in the plurality of probability values as the classification result.
In one example, in the above-described inductive switch control system 500, the movement pattern tag includes: stationary, constant speed travel, acceleration travel, deceleration travel.
In one example, in the above-mentioned inductive switch control system 500, the determining unit 570 is further configured to: responding to the classification result to be uniform traveling, and determining the prolonged closing time of the induction switch based on the uniform traveling speed; determining an extended off time of the inductive switch based on an acceleration of the acceleration travel in response to the classification result being uniform traveling; and determining an extended off time of the induction switch based on an acceleration of the deceleration traveling in response to the classification result being uniform traveling.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described induction switch control system 500 have been described in detail in the above description of the induction switch control method with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
As described above, the inductive switch control system 500 according to the embodiment of the present application may be implemented in various terminal devices, such as a server of an inductive switch control algorithm, and the like. In one example, the inductive switch control system 500 according to embodiments of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the inductive switch control system 500 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the inductive switch control system 500 could equally be one of many hardware modules of the terminal device.
Alternatively, in another example, the inductive switch control system 500 and the terminal device may be separate devices, and the inductive switch control system 500 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present application is described with reference to fig. 7. As shown in fig. 7, the electronic device includes 10 includes one or more processors 11 and memory 12. The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to implement the functions of the inductive switch control method of the various embodiments of the application described above and/or other desired functions. Various contents such as a phase eigenvector, an upstream correction eigenvector, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input system 13 and an output system 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input system 13 may comprise, for example, a keyboard, a mouse, etc.
The output system 14 may output various information including classification results and the like to the outside. The output system 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 7 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the inductive switch control method according to the various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform steps in an inductive switch control method described in the above "exemplary method" section of the present description.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (9)
1. A method of controlling an inductive switch, comprising:
acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination time period;
Constructing phase data of the infrared detection signals at a series of preset time points into phase vectors arranged in a time dimension;
passing the phase vector through a deep neural network model to obtain a phase feature vector, wherein the phase feature vector is used for representing high-dimensional implicit features of phase data of infrared detection signals at each time point and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points;
calculating uplink correction eigenvalues of all positions in the phase eigenvector based on eigenvalues of all positions in the phase eigenvector, wherein the uplink correction eigenvalues are also generated based on the transmission power of the infrared detector, the distance between the infrared detector and a detection object, the small-scale attenuation effect parameters from the infrared detector to the detection object and the small-scale attenuation power components from the infrared detector to the detection object;
arranging the uplink correction eigenvalues at each position into uplink correction eigenvectors;
inputting the uplink correction feature vector into a classifier to obtain a classification result, wherein the classification result is used for representing the motion mode of a monitored object; and
and determining the control state of the inductive switch based on the classification result.
2. The inductive switch control method of claim 1, wherein passing the phase vector through a deep neural network model to obtain a phase eigenvector comprises:
performing full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model to extract high-dimensional implicit characteristics of phase data of infrared detection signals at all time points in the phase vector; and
and carrying out one-dimensional convolution encoding on the phase vector by using a one-dimensional convolution layer of the deep neural network model to extract high-dimensional implicit features of association between phase data of infrared detection signals at two adjacent time points in the phase vector.
3. The inductive switch control method according to claim 1, wherein calculating the uplink correction eigenvalue for each position in the phase eigenvector based on the eigenvalue for each position in the phase eigenvector comprises:
based on the characteristic values of all the positions in the phase characteristic vector, calculating uplink correction characteristic values of all the positions in the phase characteristic vector according to the following formula;
the formula is:
wherein the method comprises the steps ofIs the characteristic value of phase, T i Is the transmission power of the infrared detector, d i Is the distance between the infrared detector and the object to be detected, a T,O Is the small-scale attenuation effect parameter from the infrared detector to the detection object, h T,O Is the small-scale attenuated power component of the infrared detector to the detection object, and sigma 2 Representing the power of the additive white gaussian noise.
4. The inductive switch control method according to claim 3, wherein the small-scale attenuation effect parameters of the infrared detector to the detection object include path loss and shielding loss; and the small-scale attenuated power component of the infrared detector to the detection object is related to the emission frequency of the infrared detector.
5. The inductive switch control method according to claim 1, wherein inputting the uplink correction feature vector into a classifier to obtain a classification result comprises:
inputting the uplink correction feature vector into a Softmax classification function of the classifier to obtain a plurality of probability values of the uplink correction feature vector respectively belonging to different motion mode labels; and
and determining the motion mode label corresponding to the maximum probability value in the plurality of probability values as the classification result.
6. The inductive switch control method of claim 5, wherein the movement pattern tag comprises: stationary, constant speed travel, acceleration travel, deceleration travel.
7. An inductive switch control system, comprising:
a data acquisition unit for acquiring phase data of an infrared detection signal at a series of predetermined time points within a determination period;
a phase vector arrangement unit configured to arrange phase data of the series of infrared detection signals at predetermined time points obtained by the data acquisition unit into phase vectors in a time dimension;
the deep neural network processing unit is used for passing the phase vectors obtained by the phase vector arrangement unit through a deep neural network model to obtain phase feature vectors, wherein the phase feature vectors are used for representing high-dimensional implicit features of phase data of infrared detection signals at all time points and associated high-dimensional implicit features between the phase data of the infrared detection signals at two adjacent time points;
an uplink correction eigenvalue calculation unit, configured to calculate an uplink correction eigenvalue for each position in the phase eigenvector based on the eigenvalue for each position in the phase eigenvector obtained by the deep neural network processing unit, where the uplink correction eigenvalue is further generated based on a transmission power of the infrared detector, a distance between the infrared detector and a detection object, a small-scale attenuation effect parameter from the infrared detector to the detection object, and a small-scale attenuation power component from the infrared detector to the detection object;
A feature vector generation unit configured to arrange the uplink correction feature values obtained by the uplink correction feature value calculation unit at each position into an uplink correction feature vector;
a classification unit, configured to input the uplink correction feature vector obtained by the feature vector generation unit into a classifier to obtain a classification result, where the classification result is used to represent a motion mode of a monitored object; and
and the determining unit is used for determining the control state of the inductive switch based on the classification result obtained by the classifying unit.
8. The inductive switch control system of claim 7, wherein the deep neural network processing unit comprises:
the full-connection coding subunit is used for carrying out full-connection coding on the phase vector by using at least one full-connection layer of the deep neural network model so as to extract high-dimensional implicit characteristics of phase data of infrared detection signals at each time point in the phase vector; and
and the one-dimensional convolution coding subunit is used for carrying out one-dimensional convolution coding on the phase vector by using a one-dimensional convolution layer of the depth neural network model so as to extract high-dimensional implicit characteristics of association between phase data of infrared detection signals at two adjacent time points in the phase vector.
9. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the inductive switch control method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111136073.XA CN113807459B (en) | 2021-09-27 | 2021-09-27 | Inductive switch control method and system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111136073.XA CN113807459B (en) | 2021-09-27 | 2021-09-27 | Inductive switch control method and system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807459A CN113807459A (en) | 2021-12-17 |
| CN113807459B true CN113807459B (en) | 2023-11-07 |
Family
ID=78896760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111136073.XA Active CN113807459B (en) | 2021-09-27 | 2021-09-27 | Inductive switch control method and system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807459B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11326031A (en) * | 1997-12-08 | 1999-11-26 | Nippon Soken Inc | Measuring device and measuring method of propagation time by sound wave |
| EP2195795A1 (en) * | 2007-10-05 | 2010-06-16 | Cedes AG | Device for controlling a driven movement element, particularly a door or a gate |
| CN105793679A (en) * | 2013-12-09 | 2016-07-20 | 格立威系统有限公司 | Motion detection |
| CN108564130A (en) * | 2018-04-24 | 2018-09-21 | 南京师范大学 | It is a kind of based on the Infrared Target Recognition Method for singly drilling feature and Multiple Kernel Learning |
| CN110619373A (en) * | 2019-10-31 | 2019-12-27 | 北京理工大学 | Infrared multispectral weak target detection method based on BP neural network |
| CN112766465A (en) * | 2021-02-04 | 2021-05-07 | 广州信悦数码科技有限公司 | Training method of neural network for intelligent rotation performance detection |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI554034B (en) * | 2012-10-15 | 2016-10-11 | 陳家德 | Infrared ray on/off switch with automatic dimming capacity |
| US11720814B2 (en) * | 2017-12-29 | 2023-08-08 | Samsung Electronics Co., Ltd. | Method and system for classifying time-series data |
-
2021
- 2021-09-27 CN CN202111136073.XA patent/CN113807459B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11326031A (en) * | 1997-12-08 | 1999-11-26 | Nippon Soken Inc | Measuring device and measuring method of propagation time by sound wave |
| EP2195795A1 (en) * | 2007-10-05 | 2010-06-16 | Cedes AG | Device for controlling a driven movement element, particularly a door or a gate |
| CN105793679A (en) * | 2013-12-09 | 2016-07-20 | 格立威系统有限公司 | Motion detection |
| CN108564130A (en) * | 2018-04-24 | 2018-09-21 | 南京师范大学 | It is a kind of based on the Infrared Target Recognition Method for singly drilling feature and Multiple Kernel Learning |
| CN110619373A (en) * | 2019-10-31 | 2019-12-27 | 北京理工大学 | Infrared multispectral weak target detection method based on BP neural network |
| CN112766465A (en) * | 2021-02-04 | 2021-05-07 | 广州信悦数码科技有限公司 | Training method of neural network for intelligent rotation performance detection |
Non-Patent Citations (2)
| Title |
|---|
| 一种新的红外探测方法;刘丽萍;;宁夏工程技术(04);全文 * |
| 基于时频分析的人体红外热信号检测算法;陆兴华;陈锐俊;池坤丹;;国外电子测量技术(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807459A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102137151B1 (en) | Apparatus for noise canceling and method for the same | |
| US11531891B2 (en) | Cooking apparatus for determining cooked-state of cooking material and control method thereof | |
| KR102298541B1 (en) | Artificial intelligence apparatus for recognizing user from image data and method for the same | |
| US11501794B1 (en) | Multimodal sentiment detection | |
| KR102658112B1 (en) | Artificial intelligence apparatus for controlling auto stop system based on driving information and method for the same | |
| US11227596B2 (en) | Laundry scheduling device | |
| US20210161329A1 (en) | Cooking apparatus and control method thereof | |
| CN112733875A (en) | Apparatus and method for generating synthetic data in a generating network | |
| CN111414843B (en) | Gesture recognition method and terminal device | |
| KR20190095180A (en) | An artificial intelligence apparatus for controlling auto stop system and method for the same | |
| KR20210068993A (en) | Device and method for training a classifier | |
| CN113807459B (en) | Inductive switch control method and system and electronic equipment | |
| CN116373732A (en) | Control method and system for vehicle indicator lamp | |
| KR20210073930A (en) | Apparatus and method for controlling electronic apparatus | |
| CN115399769A (en) | Millimeter wave mapping system and method for generating point clouds and determining vital signs to define human mental states | |
| Ehrnsperger et al. | Real-time gesture detection based on machine learning classification of continuous wave radar signals | |
| EP4093155A1 (en) | Cooking apparatus using artificial intelligence and method for operating same | |
| US20220245932A1 (en) | Method and device for training a machine learning system | |
| Zhang et al. | Dynamic gesture recognition based on RF sensor and AE-LSTM neural network | |
| CN112819044A (en) | Method for training neural network for target operation task compensation of target object | |
| US11482039B2 (en) | Anti-spoofing method and apparatus for biometric recognition | |
| Boner et al. | Tiny tcn model for gesture recognition with multi-point low power tof-sensors | |
| US20210137311A1 (en) | Artificial intelligence device and operating method thereof | |
| CN113781845B (en) | Electronic fence establishing method and system for unmanned aerial vehicle and electronic equipment | |
| JP2023118101A (en) | Device and method for determining adversarial patch for machine learning system |
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 |