Multi-feature fusion traversing machine signal identification method, device, equipment and medium

Abstract

The invention provides a multi-feature fusion traversing machine signal identification method, device and equipment and a medium, and the method comprises the steps: obtaining the time-frequency features of a collected signal, and judging whether there is a suspected traversing machine signal based on the time-frequency features; performing frequency domain accumulation on the high-frequency part of the suspected signal of the traversing machine, performing mean filtering processing on the accumulated signal in the time domain direction, and identifying the filtered signal based on the pulse width to obtain a first traversing machine signal; obtaining the system of the suspected signal of the traversing machine, performing pulse period length superposition on the suspected signal of the traversing machine in the time domain according to the pulse period corresponding to the system of the suspected signal of the traversing machine, and identifying the superposed pulse signal based on the pulse width to obtain a second signal of the traversing machine; and performing intersection processing on the first crossing machine signal and the second crossing machine signal to complete crossing machine signal identification. According to the method, the signal of the traversing machine can be efficiently identified, the calculation complexity is remarkably reduced, and the false alarm rate is extremely low.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle supervision, and in particular to a multi-feature fusion crossing machine signal identification method, device, equipment and medium. BACKGROUND

[0002] The crossing machine is widely used due to its characteristics of high-speed flight, lightweight body and super maneuverability. However, with the rapid development of the crossing machine, "black flight" and "wild flight" incidents occur frequently, which not only pose a serious threat to aviation safety and public order, but also lead to new security risks such as invasion of personal privacy and interference with sensitive areas. The surge in safety accidents caused by illegal use of crossing machines makes unmanned aerial vehicle supervision and defense an urgent problem to be solved.

[0003] In the prior art, when the crossing machine signal is demodulated for image reconstruction, real-time decoding of the video stream is required, but due to the large amount of calculation in the process, the processing efficiency is low, which is difficult to match the real-time tracking demand of the crossing machine. The traditional detection mechanism based on RSSI threshold has significant limitations, especially in complex electromagnetic environments, where the same frequency band environmental interference signals will cause a sharp increase in false alarm rate, resulting in a decrease in detection sensitivity. Although the intelligent detection model based on the deep learning framework can show advantages in specific scenarios, it is limited by the magnitude of the accurate annotation dataset, and the model reasoning relies on the GPU acceleration environment, and there is also the problem of decreased recognition accuracy caused by environmental mutations. SUMMARY

[0004] In view of the defects in the prior art, the present application provides a multi-feature fusion crossing machine signal identification method, device, equipment and medium.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present application is as follows: On the one hand, the present application provides a multi-feature fusion crossing machine signal identification method, comprising the following steps: Obtaining the time-frequency feature of the collected signal, and determining whether there is a crossing machine suspected signal based on the time-frequency feature; Performing frequency domain accumulation on the high frequency part of the crossing machine suspected signal, and performing mean filtering processing on the time domain direction of the accumulated signal, identifying the filtered signal based on the pulse width, and obtaining the first crossing machine signal; Obtaining the type of the crossing machine suspected signal, superimposing the pulse period length of the crossing machine suspected signal in the time domain based on the pulse period of the crossing machine suspected signal corresponding to the type, and identifying the superimposed pulse signal based on the pulse width to obtain the second crossing machine signal; Performing intersection processing on the first crossing machine signal and the second crossing machine signal to complete the crossing machine signal identification.

[0006] Further, time-frequency characteristics of the collected signal are acquired, and suspected signals of the crossing machine are screened based on the time-frequency characteristics, including: The collected signal is converted to the frequency domain by Fourier transform, and the power spectral density of the signal is calculated according to the number of sampling points and the sampling rate; Two frequency points on both sides of the power of the crossing machine signal channel frequency are acquired, and the bandwidth difference between the two frequency points is calculated, if the bandwidth difference between the two frequency points is within 6MHz±2MHz, it is considered that there is a suspected signal in the crossing machine signal channel; if there is no frequency point meeting the requirements or the bandwidth difference between the two frequency points is not within 6MHz±2MHz, it is considered that there is no suspected signal in the crossing machine signal channel; Whether there is a suspected signal of the crossing machine is determined according to the time characteristic.

[0007] Further, whether there is a suspected signal of the crossing machine is determined according to the time characteristic, including: The suspected signal of the crossing machine signal channel in the time dimension is divided by the mean value method, and the points greater than the division value are determined as signals, and the points less than the division value are determined as noises; The proportion of rising and falling edges of the suspected signal to the total signal is counted, if the proportion is greater than 0.25, it is considered that there is a suspected signal of the crossing machine; if the proportion is not greater than 0.25, it is considered that there is no suspected signal of the crossing machine.

[0008] Further, the power spectral density of the signal is calculated according to the number of sampling points and the sampling rate:

[0009] Wherein, is the power spectral density; is the number of sampling points; is the sampling rate; is the imaginary unit; is the time domain signal; is the signal frequency.

[0010] Further, the filtered signal is identified based on the pulse width to obtain the first crossing machine signal, including: The filtered signal is segmented by threshold segmentation method; In the segmented signal, the signal with a pulse length within 18.4ms±0.3ms within every 20ms from the starting observation time is determined as the first crossing machine signal.

[0011] Further, the superimposed pulse signal is identified based on the pulse width to obtain the second crossing machine signal, including: The superimposed pulse signal is segmented by threshold segmentation method; Determine whether the signal in the segmented signal, from the start of the observation time, within 20 ms, the pulse length in 18.4 ms ± 0.3 ms is the second crossing machine signal.

[0012] Further, the threshold segmentation method is performed according to the following formula:

[0013] Wherein, The threshold value is T; The maximum amplitude is Amax; The minimum amplitude is Amin.

[0014] In another aspect, the present application provides a multi-feature fusion crossing machine signal recognition device, comprising: The first module is used for acquiring the time-frequency features of the collected signal, and determining whether there is a crossing machine suspected signal based on the time-frequency features; The second module is used for performing frequency domain accumulation on the high frequency part signal of the crossing machine suspected signal, and performing time domain direction mean filtering processing on the accumulated signal, and identifying the filtered signal based on the pulse width to obtain the first crossing machine signal; The third module is used for acquiring the mode of the crossing machine suspected signal, and performing pulse period length superposition on the crossing machine suspected signal in the time domain based on the pulse period corresponding to the mode of the crossing machine suspected signal, and identifying the superimposed pulse signal based on the pulse width to obtain the second crossing machine signal; The fourth module is used for performing intersection processing on the first crossing machine signal and the second crossing machine signal to complete the crossing machine signal recognition.

[0015] In another aspect, the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor executes the steps of the multi-feature fusion crossing machine signal recognition method when the computer program is executed.

[0016] In another aspect, the present application provides a computer readable storage medium, which stores a computer program, and the steps of the multi-feature fusion crossing machine signal recognition method are realized when the computer program is executed by the processor.

[0017] Compared with the prior art, the beneficial technical effects of the present application are: The application provides a multi-feature fusion crossing machine signal identification method, device, equipment and medium, which collects time-frequency features of signals, judges whether there is a crossing machine suspected signal based on the time-frequency features, so as to realize preliminary screening of the collected signals and reduce the data processing amount of subsequent signal identification; the high-frequency part of the crossing machine suspected signal is subjected to frequency domain accumulation, so as to eliminate field blanking signals, so that the accumulated pulse distribution of the high-frequency part of the signal is clearly displayed, the signal after accumulation is subjected to mean filtering processing in the time domain direction, so as to increase the stability of the signal, suppress noise, smooth the signal, improve the accuracy and robustness of signal identification, and the signal after filtering is identified based on the pulse width to obtain a first crossing machine signal; the crossing machine suspected signal is subjected to pulse period length superposition in the time domain by using the pulse period corresponding to the type of the crossing machine suspected signal, so as to superimpose the signal-to-noise ratio and improve the detection capability, and the superimposed pulse signal is identified based on the pulse width to obtain a second crossing machine signal. Finally, the first crossing machine signal and the second crossing machine signal are subjected to intersection processing, and crossing machine signal identification is completed.

[0018] The application comprehensively considers the time-frequency features, energy distribution characteristics, periodic pulse characteristics and pulse width characteristics of the crossing machine signal, constructs a multi-feature fusion identification model, can efficiently identify the crossing machine signal, significantly reduces the calculation complexity, has an extremely low false alarm rate, improves the target recognition ability in a low signal-to-noise ratio scene, and is suitable for real-time scenes such as low-altitude security. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only show some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from the structures shown in the drawings without creative labor.

[0020] Figure 1 A multi-feature fusion crossing machine signal identification method flowchart is provided for an embodiment; Figure 2 A high-frequency signal frequency domain accumulation filtering schematic diagram is provided for an embodiment, wherein Figure 2 (a) is a high-frequency signal frequency domain accumulation schematic diagram, Figure 2 (b) is a cumulative signal schematic diagram after mean filtering in the time domain direction; Figure 3 A low-frequency signal frequency domain accumulation filtering schematic diagram is provided for an embodiment, wherein Figure 3 (a) is a low-frequency signal frequency domain accumulation schematic diagram, Figure 3 (b) is a cumulative signal schematic diagram after mean filtering in the time domain direction; Figure 4A PAL system signal provided by an embodiment is a signal schematic diagram in which a PAL system pulse period is superimposed in time domain with a pulse period length; Figure 5 A PAL system signal provided by an embodiment is a signal schematic diagram in which a PAL system pulse period is superimposed in time domain with a pulse period length. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0022] Reference Figure 1 An embodiment provides a multi-feature fusion crossing machine signal recognition method, including the following steps: Time-frequency features of the collected signal are acquired, and whether there is a crossing machine suspected signal is judged based on the time-frequency features; The high-frequency part signal of the crossing machine suspected signal is accumulated in frequency domain, and the accumulated signal is processed by mean filtering in time domain direction, the filtered signal is recognized based on pulse width, and a first crossing machine signal is obtained; The system of the crossing machine suspected signal is acquired, the crossing machine suspected signal is superimposed in time domain with a pulse period corresponding to the system of the crossing machine suspected signal, and the superimposed pulse signal is recognized based on pulse width, and a second crossing machine signal is obtained; The first crossing machine signal and the second crossing machine signal are processed by intersection, and crossing machine signal recognition is completed.

[0023] In the above method, the time-frequency features of the collected signal are acquired, and whether there is a crossing machine suspected signal is judged based on the time-frequency features, so as to realize preliminary screening of the collected signal and reduce the data processing amount of subsequent signal recognition; the high-frequency part signal of the crossing machine suspected signal is accumulated in frequency domain, so as to eliminate field blanking signals, so as to clearly display the accumulated pulse distribution of the high-frequency part of the signal, and the accumulated signal is processed by mean filtering in time domain direction, so as to increase the stability of the signal and suppress noise, so as to smooth the signal, improve the accuracy and robustness of signal recognition, and then the filtered signal is recognized based on pulse width, and a first crossing machine signal is obtained; the crossing machine suspected signal is superimposed in time domain with a pulse period corresponding to the system of the crossing machine suspected signal, so as to superimpose the signal-to-noise ratio and improve the detection capability, and the superimposed pulse signal is recognized based on pulse width, and a second crossing machine signal is obtained. Finally, the first crossing machine signal and the second crossing machine signal obtained are processed by intersection, and crossing machine signal recognition is completed.

[0024] In a preferred embodiment, time-frequency characteristics of the collected signal are obtained, and suspected signals of the crossing machine are screened based on the time-frequency characteristics, including: The collected signal is converted to the frequency domain by Fourier transform, and the power spectral density of the signal is calculated according to the number of sampling points and the sampling rate; Two frequency points on both sides of the frequency of the crossing machine signal channel with a power drop of 3dB are obtained, and the bandwidth difference between the two frequency points is calculated. If the bandwidth difference between the two frequency points is within 6MHz±2MHz, it is considered that there is a suspected signal in the crossing machine signal channel. If there is no frequency point meeting the requirements or the bandwidth difference between the two frequency points is not within 6MHz±2MHz, it is considered that there is no suspected signal in the crossing machine signal channel; Whether there is a suspected signal of the crossing machine is determined according to the time characteristic.

[0025] Firstly, the power spectral density of the signal is calculated based on the frequency domain characteristics of the collected signal to find two frequency points on both sides of the frequency of the crossing machine signal channel with a power drop of 3dB, and the bandwidth difference between the two frequency points is calculated, so as to screen the collected signal and determine whether there is a suspected signal in the crossing machine signal channel. Since the bandwidth of the crossing machine analog image signal is mostly 6MHz, usually within 5MHz-8MHz, 6MHz±2MHz is taken as the bandwidth difference determination range. If there is a suspected signal, the signal is further determined according to the time characteristic to screen out the suspected signal of the crossing machine. Through two screenings, a large number of samples can be quickly distinguished, the sample quantity is reduced, the calculation amount is reduced, the calculation time is saved, and the calculation complexity is reduced.

[0026] In a preferred embodiment, whether there is a suspected signal of the crossing machine is determined according to the time characteristic, including: The suspected signal in the time dimension of the crossing machine signal channel is divided into two parts by the mean value method, and the points greater than the division value are determined as signals and the points less than the division value are determined as noises; The proportion of the rising and falling edges of the suspected signal to the total signal is counted. If the proportion is greater than 0.25, it is considered that there is a suspected signal of the crossing machine. If the proportion is not greater than 0.25, it is considered that there is no suspected signal of the crossing machine.

[0027] For digital signals, the signal is in an on / off mode, and common ones are square waves. Therefore, the rising and falling edges of the digital signal are relatively few after division, and the proportion to the total signal is low. Through the above setting, the digital signal and the analog signal in the suspected signal in the time dimension of the crossing machine signal channel are effectively distinguished, and the existence determination of the suspected signal of the crossing machine is completed.

[0028] The power spectral density of the signal is calculated according to the number of sampling points and the sampling rate as follows:

[0029] wherein, is the power spectral density; is the number of sampling points; is the sampling rate; is the imaginary unit; is the time domain signal; is the signal frequency.

[0030] For the acquisition of the first crossing machine signal, specifically, the crossing machine analog signal uses NTSC and PAL (Phase Alternating Line) two systems, considering that the frequency of the field blanking signal in the two systems is in the low frequency part of the baseband signal, therefore, the high frequency part signal of the crossing machine suspected signal is selected for frequency domain accumulation to eliminate the field blanking signal, so as to clearly show the accumulated pulse distribution of the high frequency part of the signal.

[0031] In an embodiment, the results of frequency domain accumulation of the high frequency part and the low frequency part of the crossing machine suspected signal and the mean filtering processing in the time domain direction are respectively shown, and the results are as shown in Figure 2 , Figure 3 From Figure 2 (a), it can be seen that after the frequency domain accumulation of the high frequency part of the crossing machine suspected signal, the accumulated pulse distribution of the high frequency part of the signal can be clearly seen, Figure 2 (b) can be seen, after the mean filtering processing in the time domain direction, the signal curve becomes smooth, which can more accurately identify the signal. From Figure 3 It can be seen that the low frequency part will have a certain degree of influence on the detection sensitivity due to the influence of the line synchronization signal; specifically, because of the existence of the synchronization signal, the noise part of the signal will be raised, thereby reducing the detection sensitivity; and the field blanking signal pulse is short in time and narrow in frequency bandwidth, and the signal recognition error rate is high; specifically, the narrow frequency domain accumulation range is easy to miss the signal, and the wide frequency domain accumulation range averages the signal energy, thereby leading to low sensitivity, so the low frequency part is not selected for processing and subsequent identification.

[0032] In an embodiment, the crossing machine analog signal of the PAL system is identified, the filtered signal is identified based on the pulse width, and the first crossing machine signal is obtained, including: The threshold segmentation method is used to segment the filtered signal; It is determined that in the segmented signal, from the start observation time, the signal with a pulse length of 18.4ms±0.3ms within 20ms is the first crossing machine signal.

[0033] Through the superposition of threshold segmentation and period (corresponding to the pulse period of the system), it is determined that the signal with the pulse length and the period meeting the above setting is the first crossing machine signal.

[0034] The threshold segmentation method is according to the following formula:

[0035] Wherein, is a threshold value; is a maximum amplitude; is a minimum amplitude.

[0036] For the acquisition of the second crossing machine signal, specifically, the crossing machine analog signal uses two systems of NTSC and PAL, the refresh rate of the NTSC system is 60Hz, and the pulse period is 16.67ms; the refresh rate of the PAL system is 50Hz, and the pulse period is 20ms; considering that the pulse characteristics of the crossing machine are consistent in each period, therefore, the pulse signal time domain is superimposed according to the period length, and the original pulse characteristics can be maintained. Therefore, the pulse period length of the crossing machine suspected signal is superimposed in the time domain according to the pulse period corresponding to the crossing machine suspected signal system, the superimposition operation is that the 20ms-40ms data is superimposed on the 0ms-20ms signal, and then the 40ms-60ms data is superimposed on the last superimposed signal, and the processing is carried out in this way, a complete period of pulse signal can be obtained, and the signal-to-noise ratio can be superimposed through the superimposition operation, and the detection capability is improved.

[0037] In an embodiment, the processing results after superimposition of the period length corresponding to the system and the period length corresponding to the non-system are shown, and the results are shown in Figure 4 , Figure 5 . Figure 4 It is a signal schematic diagram of the PAL system signal superimposed in the time domain with the PAL system pulse period, it can be seen that the superimposed signal forms a complete period, and compared with Figure 4 and Figure 2 , it can more obviously identify the crossing machine signal and improve the detection capability. Figure 5 It is a signal schematic diagram of the PAL system signal superimposed in the time domain with the NTSC system pulse period, from the figure, it can be seen that after superimposition of the period length corresponding to the non-system, multiple signal pulses will appear, which does not conform to the signal characteristics and is not convenient for identification of the crossing machine signal.

[0038] In an embodiment, the PAL system crossing machine analog signal is identified, the superimposed pulse signal is identified based on the pulse width, and the second crossing machine signal is obtained, including: The superimposed pulse signal is segmented by using the threshold segmentation method; It is determined that in the segmented signal, from the starting observation time, every 20ms, the signal with a pulse length of 18.4ms±0.3ms is the second crossing machine signal.

[0039] In an embodiment, a multi-feature fusion crossing machine signal recognition device is provided, comprising: A first module is configured to acquire time-frequency features of a collected signal, and determine whether a crossing machine suspected signal exists based on the time-frequency features; A second module is configured to perform frequency domain accumulation on a high frequency part signal of the crossing machine suspected signal, perform mean filtering processing on the accumulated signal in a time domain direction, and identify the filtered signal based on a pulse width to obtain a first crossing machine signal; A third module is configured to acquire a mode of the crossing machine suspected signal, perform pulse period length superposition on the crossing machine suspected signal in a time domain based on a pulse period corresponding to the mode of the crossing machine suspected signal, and identify the superposed pulse signal based on a pulse width to obtain a second crossing machine signal; A fourth module is configured to perform intersection processing on the first crossing machine signal and the second crossing machine signal to complete crossing machine signal recognition.

[0040] In another aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the multi-feature fusion crossing machine signal recognition method provided in any of the above embodiments when executing the computer program. The computer device can be a server. The computer device comprises a processor, a memory, a network interface and a database connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store sample data. The network interface of the computer device is configured to communicate with an external terminal through a network connection.

[0041] In another aspect, the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the multi-feature fusion crossing machine signal recognition method provided in any of the above embodiments.

[0042] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0043] The details of the present application are as follows.

[0044] The technical features of the above embodiments can be combined in any way. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0045] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of the present application.

[0046] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-feature fusion crossing machine signal recognition method, characterized in that, The method comprises the following steps: acquiring time-frequency characteristics of the collected signal, and determining whether a suspected signal of the crossing machine exists based on the time-frequency characteristics; performing frequency domain accumulation on a high frequency part signal of the suspected signal of the crossing machine, performing mean value filtering processing on the accumulated signal in the time domain direction, identifying the filtered signal based on pulse width, and obtaining a first crossing machine signal; acquiring a mode of the suspected signal of the crossing machine, superimposing the suspected signal of the crossing machine in the time domain according to a pulse period corresponding to the mode of the suspected signal of the crossing machine, identifying the superimposed pulse signal based on pulse width, and obtaining a second crossing machine signal; performing intersection processing on the first crossing machine signal and the second crossing machine signal, and completing crossing machine signal identification.

2. The multi-feature fused crossing machine signal identification method of claim 1, wherein, The method comprises the following steps: performing Fourier transform on the collected signal to convert the signal to the frequency domain, and calculating the power spectral density of the signal according to the number of sampling points and the sampling rate; acquiring two frequency points at which the power on both sides of the channel frequency of the crossing machine signal decreases by 3 dB, calculating the bandwidth difference between the two frequency points, and regarding the suspected signal as existing in the crossing machine signal channel if the bandwidth difference between the two frequency points is within 6 MHz ± 2 MHz; otherwise, regarding the suspected signal as not existing in the crossing machine signal channel; determining whether the suspected signal of the crossing machine exists according to the time characteristic.

3. The multi-feature fused crossing machine signal identification method of claim 2, wherein, The method comprises the following steps: dividing the suspected signal of the crossing machine in the time dimension by half using the mean value method, and determining that a point greater than the halved value is a signal and a point less than the halved value is noise; calculating the proportion of rising and falling edges of the suspected signal in the total signal, and regarding the suspected signal as existing if the proportion is greater than 0.25; otherwise, regarding the suspected signal as not existing.

4. The multi-feature fused crossing machine signal identification method of claim 2, wherein, The method for calculating the power spectral density of the signal according to the number of sampling points and the sampling rate comprises the following steps: wherein, is the power spectral density; is the number of samples; is the sampling rate; is the imaginary unit; is the time domain signal; is the signal frequency.

5. The multi-feature fused crossing machine signal identification method of claim 1, wherein, performing threshold segmentation on the filtered signal; determining, in the segmented signal, that a signal with a pulse length within 18.4 ms ± 0.3 ms in every 20 ms since the start of the observation time is the first crossing machine signal. The method for identifying the superimposed pulse signal based on pulse width to obtain the second crossing machine signal comprises the following steps:

6. The multi-feature fused crossing machine signal identification method of claim 1, wherein, performing threshold segmentation on the superimposed pulse signal; determining, in the segmented signal, that a signal with a pulse length within 18.4 ms ± 0.3 ms in every 20 ms since the start of the observation time is the second crossing machine signal. The threshold segmentation method is performed according to the following formula:

7. The multi-feature fused crossing-machine signal identification method of any one of claims 5 or 6, wherein, The method comprises the following steps: wherein is a threshold value; is a maximum amplitude value; is a minimum amplitude value.

8. A multi-feature fusion crossing machine signal recognition device, characterized in that, a first module is configured to acquire time-frequency characteristics of the collected signal, and determine whether a suspected signal of the crossing machine exists based on the time-frequency characteristics; a second module is configured to perform frequency domain accumulation on a high frequency part signal of the suspected signal of the crossing machine, perform mean value filtering processing on the accumulated signal in the time domain direction, identify the filtered signal based on pulse width, and obtain a first crossing machine signal; ​ The third module is configured to acquire a mode of the crossing machine suspected signal, perform pulse period length superposition on the crossing machine suspected signal in a time domain according to a pulse period corresponding to the mode of the crossing machine suspected signal, perform identification on the superimposed pulse signal based on a pulse width, and obtain a second crossing machine signal; The fourth module is configured to perform intersection processing on the first crossing machine signal and the second crossing machine signal, and complete the crossing machine signal identification. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor implements the multi-feature fusion crossing machine signal identification method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the processor and is executed by the processor to implement the multi-feature fusion crossing machine signal identification method according to any one of claims 1 to 6.

Images