CN113591677A - Contraband identification method and device, storage medium and computer equipment - Google Patents
Contraband identification method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113591677A CN113591677A CN202110857749.8A CN202110857749A CN113591677A CN 113591677 A CN113591677 A CN 113591677A CN 202110857749 A CN202110857749 A CN 202110857749A CN 113591677 A CN113591677 A CN 113591677A
- Authority
- CN
- China
- Prior art keywords
- electromagnetic wave
- contraband
- wave signals
- training
- frequency
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
- G06F2218/16—Classification; Matching by matching signal segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
Abstract
When the security inspection equipment is used for detecting contraband, the collected electromagnetic wave signals of the object to be detected can be preprocessed to obtain electromagnetic wave signals of a plurality of frequency bands, then the electromagnetic wave signals of each frequency band are sequentially input into the pre-configured classification model, after the electromagnetic wave signals of each frequency band are identified and classified through the classification model, the electromagnetic wave signals of each frequency band can be ensured to obtain accurate classification results, finally, the type of the contraband carried by the object to be detected is determined based on the classification results corresponding to the electromagnetic wave signals of each frequency band, and the accuracy rate of contraband identification can be further improved; moreover, by the contraband identification method, the contraband and the non-contraband can be identified, the types of the contraband can be identified, and the detection efficiency of the security inspection equipment can be improved.
Description
Technical Field
The invention relates to the field of security and protection, in particular to a method and a device for identifying contraband, a storage medium and computer equipment.
Background
Security devices have been spotlighted and used by an increasing number of businesses and users as an emerging thing in the security industry. For example, when the security inspection door works, the crystal oscillator generates 3.5-4.95M sinusoidal oscillation, the sinusoidal oscillation is divided into sine waves of about 7.8K by the frequency divider, the sine waves are input into a large coil of a door panel (area 7) to be subjected to electromagnetic wave transmission after being subjected to power amplification by a triode and the coil, and then the sine waves are respectively received by coils in areas 1-6 of the door.
In the prior art, when a security inspection door is used for detecting contraband, a received electromagnetic wave signal is mainly compared with a reference signal, if the electromagnetic wave signal changes, the output level of an acquisition card is changed, so that a CPU (central processing unit) scans data of the acquisition card in 6 areas within 300 milliseconds, judges the areas where the contraband is located and outputs and displays the data.
According to the above content, when the existing security inspection equipment is used for detecting contraband, only the zone position where the contraband is located can be judged and displayed, and the specific contraband type cannot be detected.
Disclosure of Invention
The invention aims to solve at least one of the technical defects, in particular to the technical defect that in the prior art, when security inspection equipment is used for detecting contraband, only the zone position where the contraband is located can be judged and displayed, and the specific contraband type cannot be detected.
The invention provides a contraband identification method, which comprises the following steps:
acquiring an electromagnetic wave signal of an object to be detected, which is acquired by security inspection equipment;
preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of a plurality of frequency bands;
sequentially inputting the electromagnetic wave signals of each frequency band into a pre-configured classification model to obtain a classification result corresponding to the electromagnetic wave signals of each frequency band output by the classification model; the classification model is obtained by taking the electromagnetic wave signal of the training object collected by the security inspection equipment as a training sample and taking the type of contraband carried by the training object as a sample label for training;
and determining the type of contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
Optionally, the step of obtaining electromagnetic wave signals of multiple frequency bands after preprocessing the electromagnetic wave signals includes:
converting the electromagnetic wave signal into a frequency domain signal;
and filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
Optionally, the step of filtering and segmenting the frequency domain signal to obtain electromagnetic wave signals of multiple frequency bands includes:
filtering the frequency domain signal by using a predefined function;
segmenting the frequency domain signals after filtering processing to obtain electromagnetic wave signals of a plurality of frequency bands;
wherein the predefined function comprises a band pass filter and a window function.
Optionally, the high cut-off frequency of the band-pass filter is greater than the low cut-off frequency of the band-pass filter, and the low cut-off frequency of the band-pass filter is greater than zero.
Optionally, the step of determining the type of contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band includes:
counting classification results corresponding to the electromagnetic wave signals of each frequency band;
and taking the classification result with the largest number of votes in all classification results as the type of the contraband carried by the object to be detected.
Optionally, the training process of the classification model includes:
inputting the electromagnetic wave signals of the training objects collected by the security inspection equipment into the classification model;
obtaining a classification result output by the classification model;
and updating model parameters by taking the type of contraband carried by the training object, which is the classification result predicted by the classification model on the input electromagnetic wave signal of the training object, as a target.
The invention also provides a contraband identification device, which comprises:
the signal acquisition module is used for acquiring electromagnetic wave signals of the object to be detected, which are acquired by the security inspection equipment during working;
the preprocessing module is used for preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of a plurality of frequency bands;
the classification module is used for sequentially inputting the electromagnetic wave signals of each frequency band into a pre-configured classification model to obtain a classification result corresponding to the electromagnetic wave signals of each frequency band output by the classification model; the classification model is obtained by taking the electromagnetic wave signal of the training object collected by the security inspection equipment as a training sample and taking the type of contraband carried by the training object as a sample label for training;
and the contraband identification module is used for determining the type of the contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
Optionally, the preprocessing module comprises:
the frequency domain conversion module is used for converting the electromagnetic wave signal into a frequency domain signal;
and the filtering segmentation module is used for filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
The present invention also provides a storage medium having stored therein computer readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the contraband identification method according to any of the above embodiments.
The invention also provides a computer device having stored therein computer readable instructions, which, when executed by one or more processors, cause the one or more processors to carry out the steps of the contraband identification method according to any one of the above embodiments.
According to the technical scheme, the embodiment of the invention has the following advantages:
according to the contraband identification method, the device, the storage medium and the computer equipment, when the security inspection equipment is used for contraband detection, collected electromagnetic wave signals of an object to be detected can be preprocessed to obtain electromagnetic wave signals of multiple frequency bands, then the electromagnetic wave signals of the frequency bands are sequentially input into the pre-configured classification model, as the electromagnetic wave signals are divided into the multiple frequency bands, after the electromagnetic wave signals of each frequency band are identified and classified through the classification model, the electromagnetic wave signals of each frequency band can be ensured to obtain more accurate classification results, finally, the type of contraband carried by the object to be detected is determined based on the classification results corresponding to the electromagnetic wave signals of each frequency band, and the accuracy of contraband identification can be further improved; in addition, the classification model in the application is obtained by training with the electromagnetic wave signal of the training object collected by the security inspection equipment as the training sample and the type of the contraband carried by the training object as the sample label, so that the contraband identification method can identify the contraband and the non-contraband, can also identify the type of the contraband, and is beneficial to improving the detection efficiency of the security inspection equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for identifying contraband according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a contraband identification apparatus according to an embodiment of the present invention;
fig. 3 is a schematic internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Security devices have been spotlighted and used by an increasing number of businesses and users as an emerging thing in the security industry. For example, when the security inspection door works, the crystal oscillator generates 3.5-4.95M sinusoidal oscillation, the sinusoidal oscillation is divided into sine waves of about 7.8K by the frequency divider, the sine waves are input into a large coil of a door panel (area 7) to be subjected to electromagnetic wave transmission after being subjected to power amplification by a triode and the coil, and then the sine waves are respectively received by coils in areas 1-6 of the door.
In the prior art, when a security inspection door is used for detecting contraband, a received electromagnetic wave signal is mainly compared with a reference signal, if the electromagnetic wave signal changes, the output level of an acquisition card is changed, so that a CPU (central processing unit) scans data of the acquisition card in 6 areas within 300 milliseconds, judges the areas where the contraband is located and outputs and displays the data.
According to the above content, when the existing security inspection equipment is used for detecting contraband, only the zone position where the contraband is located can be judged and displayed, and the specific contraband type cannot be detected.
Therefore, the present invention aims to solve the technical problem that in the prior art, when the security inspection equipment performs contraband detection, only the location of the contraband can be determined and displayed, and the specific contraband type cannot be detected, and provides the following technical scheme:
in an embodiment, as shown in fig. 1, fig. 1 is a schematic flowchart of a method for identifying contraband according to an embodiment of the present invention; the invention provides a contraband identification method, which comprises the following steps:
s110: and acquiring the electromagnetic wave signal of the object to be detected, which is acquired by the security inspection equipment.
In this step, before contraband identification, the electromagnetic wave signal of the object to be detected collected by the security inspection equipment can be obtained, and after the electromagnetic wave signal is detected and identified, the type of the contraband carried by the object to be detected can be determined.
It is understood that the security devices herein include, but are not limited to, security doors, hand-held metal detectors, security X-ray machines, hazardous liquid detectors, vehicle bottom video scopes, in-shoe metal detectors, hose endoscopes, and the like, typically used in police anti-terrorism, airports, stations, courthouses, inspection yards, and the like.
The security inspection refers to security inspection, for example, when a passenger who needs to board in an airport is subjected to security inspection, the security inspection mainly inspects whether the passenger and the luggage articles thereof carry dangerous articles such as firearms, ammunition, flammability, explosiveness, corrosion, toxic radioactivity and the like, so as to ensure the personal and property safety of the aircraft and the passengers; the security inspection door is mainly used for detecting whether a passenger carries metal objects, such as coins, keys, copper foil, aluminum foil, silver foil, zinc sheets, copper sheets, iron blocks, copper blocks, cutters, guns, belt bombs, vest bombs, various tank bodies and pipe bodies.
The object to be measured may be a person who is undergoing security check, or may be an item of luggage or the like undergoing security check, which is not limited herein.
S120: and preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of a plurality of frequency bands.
In this step, after the electromagnetic wave signal of the object to be detected acquired by the security inspection device is acquired in step S110, the electromagnetic wave signal may be preprocessed so as to obtain electromagnetic wave signals of multiple frequency bands.
It can be understood that the actually acquired electromagnetic wave signal is an analog signal, before the electromagnetic wave signal is digitally processed, the analog electromagnetic wave signal needs to be sampled with a sampling period T and discretized into a digital signal, and the selection of the sampling period can be determined according to the bandwidth of the analog electromagnetic wave signal, so as to avoid frequency domain aliasing distortion of the signal.
Certain quantization noise and distortion are brought in the process of quantizing the scattered electromagnetic wave signals. Therefore, before the electromagnetic wave signal is detected, the electromagnetic wave signal can be preprocessed, the preprocessing operation includes but is not limited to filtering and frequency band division operation, the electromagnetic wave signal can be filtered to remove noise and increase signal intensity, the filtered electromagnetic wave signal can be divided into electromagnetic wave signals of multiple frequency bands after frequency band division processing, and therefore local features of the electromagnetic wave signal can be accurately identified, and a final detection result is accurate.
S130: and sequentially inputting the electromagnetic wave signals of each frequency band into a pre-configured classification model to obtain a classification result corresponding to the electromagnetic wave signals of each frequency band output by the classification model.
In this step, after the electromagnetic wave signals are preprocessed in step S120 to obtain electromagnetic wave signals of multiple frequency bands, the electromagnetic wave signals of each frequency band may be sequentially input into a pre-configured classification model, so that the classification model identifies and classifies the electromagnetic wave signals of each frequency band, and outputs a classification result corresponding to the electromagnetic wave signals of each frequency band.
The classification model is obtained by taking an electromagnetic wave signal of a training object collected by security inspection equipment as a training sample and taking the type of contraband carried by the training object as a sample label for training.
It should be understood that the training object herein refers to an object to be tested during model training, and the training object may be a person undergoing security check, or an item of baggage undergoing security check, and the like, and is not limited herein.
The types of contraband carried by the training objects can be contraband and non-contraband, the contraband can comprise metal objects, the metal objects can comprise mobile phones, coins, keys, copper foils, aluminum foils, silver foils, zinc sheets, copper sheets, iron blocks, copper blocks, cutters, guns, waistband bombs, vest bombs and various tanks and pipes, and the non-contraband can be other objects except the contraband.
After the classification model takes the electromagnetic wave signals of the training objects collected by the security inspection equipment as training samples and takes the types of contraband carried by the training objects as sample labels to perform repeated iterative training, the classification model can be put into normal security inspection operation.
In addition, the training samples input in the classification model training process may be electromagnetic wave signals of the training target in a segmented form.
S140: and determining the type of contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
In this step, the electromagnetic wave signals of each frequency band are sequentially input into the pre-configured classification model in step S130, and after the classification result corresponding to the electromagnetic wave signal of each frequency band output by the classification model is obtained, the type of contraband carried by the object to be detected can be determined according to the classification result corresponding to the electromagnetic wave signal of each frequency band.
For example, after the classification model outputs the classification result corresponding to the electromagnetic wave signal of each frequency band, the classification result corresponding to the electromagnetic wave signal of each frequency band may be fused through a fusion algorithm, for example, when the classification model outputs the classification result corresponding to the electromagnetic wave signal of each frequency band, the confidence of the classification result is given, and then the classification result corresponding to the electromagnetic wave signal of each frequency band is weighted and fused according to the confidence corresponding to the electromagnetic wave signal of each frequency band, so as to determine the type of contraband carried by the object to be detected.
In addition, the fusion algorithm can also determine the types of contraband carried by the object to be detected in a voting mode. For example, for the classification result corresponding to the electromagnetic wave signal of each frequency band, a new prediction result can be obtained by voting and fusing according to the principle that minority obeys majority, and the prediction result is the type of contraband carried by the object to be detected in the present application.
It should be noted that, in the method for identifying contraband, when the type of the contraband carried by the object to be detected is determined, if the object to be detected is a person who is receiving security inspection, and after the electromagnetic wave signal of the person who is receiving security inspection is collected, it is detected that the electromagnetic wave signal does not contain a component of the contraband, it indicates that the person who is receiving security inspection does not carry the contraband; when the electromagnetic wave signal is detected to contain the components of the contraband, the personnel receiving security inspection is indicated to carry the contraband, and the type of the carried contraband can be determined through the classification model of the application.
In the above embodiment, when the security inspection device is used for detecting contraband, the collected electromagnetic wave signals of the object to be detected may be preprocessed to obtain electromagnetic wave signals of multiple frequency bands, and then the electromagnetic wave signals of the frequency bands are sequentially input into the pre-configured classification model, because the electromagnetic wave signals are divided into multiple frequency bands, after the electromagnetic wave signals of each frequency band are identified and classified by the classification model, the electromagnetic wave signals of each frequency band can be ensured to obtain a more accurate classification result, and finally, the type of the contraband carried by the object to be detected is determined based on the classification result corresponding to the electromagnetic wave signals of each frequency band, so that the accuracy of contraband identification can be further improved; in addition, the classification model in the application is obtained by training with the electromagnetic wave signal of the training object collected by the security inspection equipment as the training sample and the type of the contraband carried by the training object as the sample label, so that the contraband identification method can identify the contraband and the non-contraband, can also identify the type of the contraband, and is beneficial to improving the detection efficiency of the security inspection equipment.
The above embodiments describe the contraband detection method of the present application, and the following describes the steps of processing the electromagnetic wave signal in the present application.
In an embodiment, the step of preprocessing the electromagnetic wave signal in step S120 to obtain electromagnetic wave signals of multiple frequency bands may include:
s121: and converting the electromagnetic wave signal into a frequency domain signal.
S122: and filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
In this embodiment, before the filtering processing is performed on the electromagnetic wave signal, the frequency domain conversion may be performed on the electromagnetic wave signal to obtain a corresponding frequency domain signal, and then an appropriate filter is selected to perform filtering processing and segmentation on the frequency domain signal, so as to obtain the electromagnetic wave signals of multiple frequency bands.
In the above embodiment, the steps of processing the electromagnetic wave signals in the present application are described, and a description will be given below of how to perform filtering processing on the frequency domain signals and segment the frequency domain signals to obtain electromagnetic wave signals of multiple frequency bands in the present application.
In an embodiment, the step of filtering and segmenting the frequency domain signal in step S122 to obtain electromagnetic wave signals of multiple frequency bands may include:
s221: and carrying out filtering processing on the frequency domain signal by using a predefined function.
S222: segmenting the frequency domain signals after filtering processing to obtain electromagnetic wave signals of a plurality of frequency bands; wherein the predefined function comprises a band pass filter and a window function.
In this embodiment, when the frequency domain signal is subjected to the filtering process, a predefined function may be used, and the predefined function may include a band pass filter and a window function.
For example, the calculation formula for performing the filtering process on the frequency domain signal may be: y [ n ]]＝x[n]·gw[n,f1,f2]，
Wherein, x [ n ]]Is a frequency domain signal corresponding to the electromagnetic wave signal, yn]Is the output, gw[n,f1,f2]Comprising filters and window functions, gw[n,f1,f2]Is calculated in the manner of gw[n,f1,f2]＝g[n,f1,f2]·w[n]，w[n]Is a Hamming window for smoothing gwThe truncation characteristic of the function is such that,
in addition, g [ n, f ]1,f2]Is a band-pass filter with cut-off characteristic in frequency domain and is calculated by g [ n, f ]1,f2]＝2f2sinc(2πf2n)-2f1sinc(2πf1n), here sinc (x) sin (x)/x, where f1,f2Low and high, respectively, truncation frequencies, both learnable, the truncation frequencies all being randomly initialized to 0, fs/2]Value of range, fsIs the signal sampling rate.
After the frequency domain signal is filtered, the frequency domain signal after filtering can be further divided into frequency bands, so that electromagnetic wave signals of multiple frequency bands are obtained. When the frequency band is divided, the division may be performed according to the sampling frequency of the electromagnetic wave signal.
In the above embodiment, a description is made on how to filter and segment the frequency domain signal to obtain electromagnetic wave signals of multiple frequency bands in the present application, and a band pass filter in the present application will be described below.
In one embodiment, the high cutoff frequency of the band pass filter is greater than the low cutoff frequency of the band pass filter, and the low cutoff frequency of the band pass filter is greater than zero.
In this embodiment, to better extract effective information from low frequencies, Mel frequencies are used for the initialization of the truncation frequency. In addition, to ensure f1＞0,f2＞f1，f1Is defined as taking the absolute value, f2Is defined as f2＝f1+|f2-f1|。
The above embodiments illustrate the band-pass filter in the present application, and how the present application can only determine the type of contraband carried by the object to be measured will be described below.
In an embodiment, the step of determining the type of contraband carried by the object to be tested based on the classification result corresponding to the electromagnetic wave signal of each frequency band in step S140 may include:
s141: and counting the classification result corresponding to the electromagnetic wave signal of each frequency band.
S142: and taking the classification result with the largest number of votes in all classification results as the type of the contraband carried by the object to be detected.
In this embodiment, when determining the type of contraband carried by the object to be measured, the determination may be performed based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
For example, the classification result corresponding to the electromagnetic wave signal of each frequency band may be counted, and then the classification result with the largest number of votes in each classification result is used as the type of the contraband carried by the object to be detected.
For example, after the classification result corresponding to the electromagnetic wave signal of each frequency band is obtained, if the classification result with the largest number of votes obtained through statistics is that the type of contraband corresponding to the currently detected electromagnetic wave signal is a mobile phone, it indicates that the type of contraband carried by the currently detected object is the mobile phone.
Further, if there are multiple contraband types corresponding to the classification result with the largest number of votes after counting, it indicates that more than one contraband type is carried by the current object to be detected, and may include metal articles such as a mobile phone, a key, and a necklace.
The above embodiments describe how the present application can only determine the types of contraband carried by the object to be measured, and a training process of the classification model in the present application will be described below.
In one embodiment, the training process of the classification model may include:
s151: and inputting the electromagnetic wave signals of the training objects acquired by the security check equipment into the classification model.
S152: and obtaining a classification result output by the classification model.
S153: and updating model parameters by taking the type of contraband carried by the training object, which is the classification result predicted by the classification model on the input electromagnetic wave signal of the training object, as a target.
In this embodiment, when the classification model uses the electromagnetic wave signal of the training object collected by the security inspection device as the training sample, and uses the type of the contraband carried by the training object as the sample tag to perform multiple iterative training, and during each iterative training, the classification result predicted by the classification model on the input electromagnetic wave signal of the training object approaches to the type of the contraband carried by the training object as the target, and the model parameters are updated.
And if the classification result predicted by the current classification model on the electromagnetic wave signal corresponding to the input training object approaches to the type of contraband carried by the training object, stopping updating the model parameters, and taking the current classification model as a final classification model.
The contraband identification apparatus provided in the embodiment of the present application is described below, and the contraband identification apparatus described below and the contraband identification method described above may be referred to in correspondence with each other.
In an embodiment, as shown in fig. 2, fig. 2 is a schematic structural diagram of a contraband identification apparatus according to an embodiment of the present invention; the invention also provides a contraband identification device, which comprises a signal acquisition module 210, a preprocessing module 220, a classification module 230 and a contraband identification module 240, and specifically comprises the following components:
the signal obtaining module 210 is configured to obtain an electromagnetic wave signal of the object to be detected, which is collected by the security inspection equipment during operation.
The preprocessing module 220 is configured to preprocess the electromagnetic wave signals to obtain electromagnetic wave signals of multiple frequency bands.
The classification module 230 is configured to sequentially input the electromagnetic wave signals of each frequency band into a pre-configured classification model, so as to obtain a classification result corresponding to the electromagnetic wave signal of each frequency band output by the classification model; the classification model is obtained by taking the electromagnetic wave signals of the training objects collected by the security inspection equipment as training samples and taking the types of contraband carried by the training objects as sample labels for training.
And a contraband identification module 240, configured to determine the type of contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
In the above embodiment, when the security inspection device is used for detecting contraband, the collected electromagnetic wave signals of the object to be detected may be preprocessed to obtain electromagnetic wave signals of multiple frequency bands, and then the electromagnetic wave signals of the frequency bands are sequentially input into the pre-configured classification model, because the electromagnetic wave signals are divided into multiple frequency bands, after the electromagnetic wave signals of each frequency band are identified and classified by the classification model, the electromagnetic wave signals of each frequency band can be ensured to obtain a more accurate classification result, and finally, the type of the contraband carried by the object to be detected is determined based on the classification result corresponding to the electromagnetic wave signals of each frequency band, so that the accuracy of contraband identification can be further improved; in addition, the classification model in the application is obtained by training with the electromagnetic wave signal of the training object collected by the security inspection equipment as the training sample and the type of the contraband carried by the training object as the sample label, so that the contraband identification method can identify the contraband and the non-contraband, can also identify the type of the contraband, and is beneficial to improving the detection efficiency of the security inspection equipment.
In one embodiment, the preprocessing module 220 may include:
and the frequency domain conversion module is used for converting the electromagnetic wave signal into a frequency domain signal.
And the filtering segmentation module is used for filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
In one embodiment, the filter segmentation module may include:
and the filtering module is used for filtering the frequency domain signal by using a predefined function.
The segmentation module is used for segmenting the frequency domain signals after the filtering processing to obtain electromagnetic wave signals of a plurality of frequency bands; wherein the predefined function comprises a band pass filter and a window function.
In one embodiment, the high cutoff frequency of the band pass filter is greater than the low cutoff frequency of the band pass filter, and the low cutoff frequency of the band pass filter is greater than zero.
In one embodiment, the contraband identification module 240 may include:
and the statistical module is used for counting the classification result corresponding to the electromagnetic wave signal of each frequency band.
And the determining module is used for taking the classification result with the largest number of votes in all classification results as the type of the contraband carried by the object to be detected.
In one embodiment, the training process of the classification model may include:
and the input module is used for inputting the electromagnetic wave signals of the training objects acquired by the security check equipment into the classification model.
And the output module is used for obtaining the classification result output by the classification model.
And the parameter updating module is used for updating model parameters by taking the classification result predicted by the classification model on the input electromagnetic wave signal of the training object as a target, wherein the classification result approaches to the type of contraband carried by the training object.
In one embodiment, the present invention further provides a storage medium having stored therein computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the contraband identification method according to any one of the above embodiments.
In one embodiment, the present invention further provides a computer device having stored therein computer readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the contraband identification method according to any of the above embodiments.
Fig. 3 is a schematic diagram illustrating an internal structure of a computer device according to an embodiment of the present invention, and the computer device 300 may be provided as a server, as shown in fig. 3. Referring to fig. 3, a computer device 300 includes a processing component 302 that further includes one or more processors and memory resources, represented by memory 301, for storing instructions, such as application programs, that are executable by the processing component 302. The application programs stored in memory 301 may include one or more modules that each correspond to a set of instructions. Further, the processing component 302 is configured to execute instructions to perform the text recognition method of any of the embodiments described above.
The computer device 300 may also include a power component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input output (I/O) interface 305. The computer device 300 may operate based on an operating system stored in memory 301, such as Windows Server, Mac OS XTM, Unix, Linux, Free BSDTM, or the like.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, the embodiments may be combined as needed, and the same and similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of contraband identification, the method comprising:
acquiring an electromagnetic wave signal of an object to be detected, which is acquired by security inspection equipment;
preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of a plurality of frequency bands;
sequentially inputting the electromagnetic wave signals of each frequency band into a pre-configured classification model to obtain a classification result corresponding to the electromagnetic wave signals of each frequency band output by the classification model; the classification model is obtained by taking the electromagnetic wave signal of the training object collected by the security inspection equipment as a training sample and taking the type of contraband carried by the training object as a sample label for training;
and determining the type of contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
2. The method for identifying contraband according to claim 1, wherein the step of preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of multiple frequency bands comprises:
converting the electromagnetic wave signal into a frequency domain signal;
and filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
3. The contraband identification method according to claim 2, wherein said step of filtering and segmenting the frequency domain signal to obtain electromagnetic wave signals of multiple frequency bands comprises:
filtering the frequency domain signal by using a predefined function;
segmenting the frequency domain signals after filtering processing to obtain electromagnetic wave signals of a plurality of frequency bands;
wherein the predefined function comprises a band pass filter and a window function.
4. The contraband identification method of claim 3, wherein a high cut-off frequency of the band-pass filter is greater than a low cut-off frequency of the band-pass filter, and the low cut-off frequency of the band-pass filter is greater than zero.
5. The contraband identification method according to claim 1, wherein the step of determining the type of contraband carried by the object to be tested based on the classification result corresponding to the electromagnetic wave signal of each frequency band comprises:
counting classification results corresponding to the electromagnetic wave signals of each frequency band;
and taking the classification result with the largest number of votes in all classification results as the type of the contraband carried by the object to be detected.
6. The contraband identification method according to claim 1, wherein the training process of the classification model comprises:
inputting the electromagnetic wave signals of the training objects collected by the security inspection equipment into the classification model;
obtaining a classification result output by the classification model;
and updating model parameters by taking the type of contraband carried by the training object, which is the classification result predicted by the classification model on the input electromagnetic wave signal of the training object, as a target.
7. A contraband identification apparatus, comprising:
the signal acquisition module is used for acquiring electromagnetic wave signals of the object to be detected, which are acquired by the security inspection equipment during working;
the preprocessing module is used for preprocessing the electromagnetic wave signals to obtain electromagnetic wave signals of a plurality of frequency bands;
the classification module is used for sequentially inputting the electromagnetic wave signals of each frequency band into a pre-configured classification model to obtain a classification result corresponding to the electromagnetic wave signals of each frequency band output by the classification model; the classification model is obtained by taking the electromagnetic wave signal of the training object collected by the security inspection equipment as a training sample and taking the type of contraband carried by the training object as a sample label for training;
and the contraband identification module is used for determining the type of the contraband carried by the object to be detected based on the classification result corresponding to the electromagnetic wave signal of each frequency band.
8. The contraband identification method of claim 7, wherein the preprocessing module comprises:
the frequency domain conversion module is used for converting the electromagnetic wave signal into a frequency domain signal;
and the filtering segmentation module is used for filtering and segmenting the frequency domain signals to obtain electromagnetic wave signals of a plurality of frequency bands.
9. A storage medium, characterized by: the storage medium having stored therein computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the contraband identification method of any of claims 1 to 7.
10. A computer device, characterized by: the computer device has stored therein computer-readable instructions which, when executed by one or more processors, cause the one or more processors to carry out the steps of the contraband identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857749.8A CN113591677A (en) | 2021-07-28 | 2021-07-28 | Contraband identification method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857749.8A CN113591677A (en) | 2021-07-28 | 2021-07-28 | Contraband identification method and device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591677A true CN113591677A (en) | 2021-11-02 |
Family
ID=78251086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110857749.8A Pending CN113591677A (en) | 2021-07-28 | 2021-07-28 | Contraband identification method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591677A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140231649A1 (en) * | 2011-04-29 | 2014-08-21 | Tsinghua University | Concealed dangerous articles detection method and device |
| US20160018557A1 (en) * | 2014-07-21 | 2016-01-21 | Nuctech Company Limited | Methods and devices for inspecting liquid |
| CN107886050A (en) * | 2017-10-16 | 2018-04-06 | 电子科技大学 | Utilize time-frequency characteristics and the Underwater targets recognition of random forest |
| CN108845321A (en) * | 2018-04-19 | 2018-11-20 | 北京三快在线科技有限公司 | Recognition methods, device and the unmanned smart machine of target object |
| CN109375220A (en) * | 2018-03-30 | 2019-02-22 | 清华大学 | Safety check system and its data processing method |
| CN109470720A (en) * | 2018-09-29 | 2019-03-15 | 深圳市华讯方舟太赫兹科技有限公司 | Liquid identification method, vector extracting method, Liquid identification device and storage medium |
| CN109870697A (en) * | 2018-12-27 | 2019-06-11 | 东莞理工学院 | A kind of object detection and classification method based on ultrasonic acoustic |
| CN109978892A (en) * | 2019-03-21 | 2019-07-05 | 浙江啄云智能科技有限公司 | A kind of intelligent safety inspection method based on terahertz imaging |
| CN110956225A (en) * | 2020-02-25 | 2020-04-03 | 浙江啄云智能科技有限公司 | Contraband detection method and system, computing device and storage medium |
| CN210572738U (en) * | 2019-08-27 | 2020-05-19 | 王玲 | Electronic data acquisition, processing and transmission system of millimeter wave contraband detector |
| CN111709445A (en) * | 2020-05-14 | 2020-09-25 | 北京航空航天大学 | Electromagnetic emission element identification method based on frequency spectrum characteristics |
-
2021
- 2021-07-28 CN CN202110857749.8A patent/CN113591677A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140231649A1 (en) * | 2011-04-29 | 2014-08-21 | Tsinghua University | Concealed dangerous articles detection method and device |
| US20160018557A1 (en) * | 2014-07-21 | 2016-01-21 | Nuctech Company Limited | Methods and devices for inspecting liquid |
| CN107886050A (en) * | 2017-10-16 | 2018-04-06 | 电子科技大学 | Utilize time-frequency characteristics and the Underwater targets recognition of random forest |
| CN109375220A (en) * | 2018-03-30 | 2019-02-22 | 清华大学 | Safety check system and its data processing method |
| CN108845321A (en) * | 2018-04-19 | 2018-11-20 | 北京三快在线科技有限公司 | Recognition methods, device and the unmanned smart machine of target object |
| CN109470720A (en) * | 2018-09-29 | 2019-03-15 | 深圳市华讯方舟太赫兹科技有限公司 | Liquid identification method, vector extracting method, Liquid identification device and storage medium |
| CN109870697A (en) * | 2018-12-27 | 2019-06-11 | 东莞理工学院 | A kind of object detection and classification method based on ultrasonic acoustic |
| CN109978892A (en) * | 2019-03-21 | 2019-07-05 | 浙江啄云智能科技有限公司 | A kind of intelligent safety inspection method based on terahertz imaging |
| CN210572738U (en) * | 2019-08-27 | 2020-05-19 | 王玲 | Electronic data acquisition, processing and transmission system of millimeter wave contraband detector |
| CN110956225A (en) * | 2020-02-25 | 2020-04-03 | 浙江啄云智能科技有限公司 | Contraband detection method and system, computing device and storage medium |
| CN111709445A (en) * | 2020-05-14 | 2020-09-25 | 北京航空航天大学 | Electromagnetic emission element identification method based on frequency spectrum characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485268B (en) | Image identification method and device | |
| CN106920233B (en) | Scratch detection method, apparatus and electronic equipment based on image procossing | |
| US9460367B2 (en) | Method and system for automating an image rejection process | |
| CN104834942A (en) | Remote sensing image change detection method and system based on mask classification | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN107390259A (en) | A kind of nuclide identification method based on SVD and SVM | |
| Campos et al. | False alarm reduction in wavelength–resolution SAR change detection schemes by using a convolutional neural network | |
| Xu et al. | A defect inspection for explosive cartridge using an improved visual attention and image-weighted eigenvalue | |
| CN115439693A (en) | Training method of target recognition network model, electronic device and program product | |
| CN110687513A (en) | Human body target detection method, device and storage medium | |
| CN111126112A (en) | Candidate region determination method and device | |
| CN113591677A (en) | Contraband identification method and device, storage medium and computer equipment | |
| Xu et al. | Marine radar oil spill monitoring technology based on dual-threshold and c–v level set methods | |
| CN111245815B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN108169248A (en) | A kind of adaptive S parameter matching process for liquid hazardous material detection | |
| US10557787B1 (en) | Detection of compounds in material samples utilizing a transformation and subsequent decomposition | |
| CN111259926A (en) | Meat freshness detection method and device, computing equipment and storage medium | |
| CN111339986A (en) | Frequency law mining method and system for equipment based on time domain/frequency domain analysis | |
| Miah et al. | Design of multidimensional sensor fusion system for road pavement inspection | |
| CN114092840A (en) | Brain-like intelligent image identification method and device applied to unmanned aerial vehicle | |
| Rhee | Gaussian filtering detection using band pass residual and contrast of forgery image | |
| Manerikar et al. | Adaptive target recognition: A case study involving airport baggage screening | |
| Mostfa et al. | Design and implementation of vehicles identification and tracking system | |
| Penariu et al. | A parallel approach on airport runways detection using MPI and CImg | |
| CN110276282B (en) | Dangerous liquid identification method and device and computer readable storage medium |
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 |