signal detection device

Abstract

To provide a signal detection device, a signal detection method, and a program for suppressing a time required for signal detection.SOLUTION: A signal detection device 300 includes a generation unit 321 that generates spectrum data on the basis of a received radio signal, a determination unit 322 that determines whether to image the spectrum data by determining whether the radio signal satisfies a predetermined condition, an imaging unit 323 that converts the spectrum data generated by the generation unit 321 into a spectrum image on the basis of the determination result of the determination unit 322, and a detection unit 324 that performs signal detection processing based on the spectrum image converted by the imaging unit 323.SELECTED DRAWING: Figure 13

Description

[Technical Field]

[0001] The present invention relates to a signal detection device, a signal detection method, and a program. [Background technology]

[0002] 2. Description of the Related Art There are known techniques used to detect the presence or absence of a signal and the location of the signal on a frequency from signal data received using a radio wave sensor or the like.

[0003] Non-Patent Document 1 is an example of such a technology. For example, Non-Patent Document 1 describes a signal detection method using deep learning, which applies an object detection algorithm based on deep learning and enables the automation of power threshold setting for detection. Specifically, Non-Patent Document 1 converts spectrum data into a spectrum image, and then has a learning model detect signal regions. Such a signal detection method using deep learning is expected to eliminate the need to set a power threshold, which has been a challenge in non-learning approaches, if sufficient spectrum images, which are received signal images with appropriate annotation data, can be prepared.

[0004] Further, as a related technique, for example, there is Patent Document 1. Patent Document 1 describes detecting and monitoring the reception strength of a received signal for each frequency. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-295155 [Non-patent literature]

[0006] [Non-Patent Document 1] Y. Ghanney, W. Ajib, “Radio Frequency Interference Detection using Deep Learning,” 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1-5. Summary of the Invention [Problem to be solved by the invention]

[0007] In the case of the technology described in Non-Patent Document 1, since it is a detection method targeted at spectrum images, it takes time to perform inference per image. As a result, for example, in conditions where inference needs to be performed using a central processing unit (CPU), the detection processing time may exceed the required delay time. As such, there has been a problem in that signal detection may take a long time due to the time required for image generation, etc.

[0008] Therefore, an object of the present invention is to provide a signal detection device, a signal detection method, and a program that can solve the problem that signal detection may take a long time. [Means for solving the problem]

[0009] In order to achieve this object, a signal detection device according to one embodiment of the present disclosure comprises: a generation unit that generates spectrum data based on a received radio signal; a determination unit that determines whether or not the spectrum data is to be visualized by determining whether or not the wireless signal satisfies a predetermined condition; an imaging unit that converts the spectrum data generated by the generation unit into a spectrum image based on the determination by the determination unit; a detection unit that performs signal detection processing based on the spectrum image converted by the imaging unit; have The structure is as follows.

[0010] Furthermore, a signal detection method according to another aspect of the present disclosure includes: The information processing device generating spectrum data based on the received radio signals; determining whether the spectrum data is to be imaged by determining whether the wireless signal satisfies a predetermined condition; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. The structure is as follows.

[0011] Furthermore, a program according to another aspect of the present disclosure includes: In the information processing device, generating spectrum data based on the received radio signals; determining whether the spectrum data is to be imaged by determining whether the wireless signal satisfies a predetermined condition; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. It is a program for realizing the processing. [Effects of the Invention]

[0012] According to the above-described configurations, it is possible to provide a signal detection device, a signal detection method, and a program that can reduce the time required for signal detection. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram illustrating an example configuration of a signal detection device according to a first embodiment of the present disclosure. [Figure 2] FIG. 10 is a diagram for explaining an example of a spectrum image. [Figure 3] FIG. 10 is a diagram illustrating an example of a threshold determination process. [Figure 4]FIG. 10 is a diagram for explaining another example of the threshold value determination process. [Figure 5] FIG. 10 is a diagram illustrating an example of estimated coordinates. [Figure 6] 10 is a flowchart illustrating an example of the operation of the signal detection device. [Figure 7] 10 is a flowchart showing a detailed example of the process of step S104. [Figure 8] FIG. 10 is a block diagram showing another example of the configuration of the signal detection device. [Figure 9] 10 is a flowchart showing another example of the operation of the signal detection device. [Figure 10] 10 is a flowchart showing a detailed example of the process of step S301. [Figure 11] FIG. 10 is a diagram illustrating an example of a division process. [Figure 12] 10 is an example of a hardware configuration of a signal detection device according to a second embodiment of the present disclosure. [Figure 13] FIG. 1 is a block diagram showing an example of the configuration of a signal detection device. DETAILED DESCRIPTION OF THE INVENTION

[0014] [First embodiment] A first embodiment of the present disclosure will be described with reference to FIGS. 1 to 11. FIG. 1 is a block diagram showing an example of the configuration of a signal detection device 100. FIG. 2 shows an example of a spectrum image. FIGS. 3 and 4 are diagrams for explaining an example of a threshold determination process. FIG. 5 is a diagram for explaining an example of estimated coordinates. FIGS. 6 and 7 are flowcharts showing an example of the operation of the signal detection device 100. FIG. 8 is a block diagram showing another example of the configuration of the signal detection device 100. FIGS. 9 and 10 are flowcharts showing another example of the operation of the signal detection device 100. FIG. 11 is a diagram for explaining an example of a division process.

[0015] In a first embodiment of the present disclosure, a signal detection device 100 is described, which is an information processing device that detects the presence or absence of a signal and the location of the signal on a frequency band from wireless signal data received using a radio wave sensor 200 that receives a wireless signal. As described below, the signal detection device 100 in this embodiment checks whether the received wireless signal data satisfies a predetermined condition. For example, the signal detection device 100 generates spectrum data by performing a fast discrete Fourier transform (FFT) on the wireless signal data. The signal detection device 100 then checks whether the signal transmission state has changed based on the power of each frequency bin (FFT bin) in the generated spectrum data. For example, if the signal detection device 100 determines that the condition is met when it is determined that the signal transmission state has changed, for example, if a frequency bin with a fluctuation amount greater than a predetermined threshold exists when compared with the spectrum data of the previous frame, the signal detection device 100 converts the spectrum data into a spectrum image. The signal detection device 100 then uses the converted spectrum image to cause a trained model 121, which is a training model, to detect a signal region. In this way, when the conditions are satisfied, the signal detection device 100 performs signal detection processing by converting the image into a spectrum image. In other words, the signal detection device 100 is configured to thin out the images to be generated based on predetermined conditions.

[0016] Fig. 1 shows an example of the configuration of a signal detection device 100. Referring to Fig. 1, the signal detection device 100 has, as main components, for example, a communication I / F unit 110, a storage unit 120, and an arithmetic processing unit 130. Note that the signal detection device 100 may be realized by a single information processing device, or may be realized on the cloud, etc.

[0017] The communication I / F unit 110 is made up of a data communication circuit etc. The communication I / F unit 110 performs data communication with an external device such as the radio wave sensor 200 connected via a communication line.

[0018] The storage unit 120 is a storage device such as a hard disk or a memory. The storage unit 120 stores processing information and a program 125 required for various processes in the arithmetic processing unit 130. The program 125 is read into the arithmetic processing unit 130 and executed to realize various processing units. The program 125 is read in advance from an external device or a recording medium via a data input / output function such as the communication I / F unit 110, and is stored in the storage unit 120. Main information stored in the storage unit 120 includes, for example, a trained model 121, wireless signal information 122, image information 123, and output information 124.

[0019] The trained model 121 is a model generated by performing training based on a spectrum image to which appropriate annotation data has been added. For example, the trained model 121 is trained in advance to output estimated coordinates of a signal region in response to an input spectrum image.

[0020] Specifically, for example, the trained model 121 is generated in advance in an external device that performs machine learning by performing machine learning processing such as adjusting weight values ​​using multiple spectrum images to which labels indicating the coordinates of signal regions are attached. The trained model 121 is acquired in advance from the external device via the communication I / F unit 110 or the like and stored in the storage unit 120. Note that the trained model 121 may be configured to be generated in the signal detection device 100, for example, by the signal detection device 100 having a function as a learning unit that performs machine learning.

[0021] As a signal detection algorithm for the learning approach, one-stage methods such as You Look at Once (YOLO) or Single Shot Detector (SSD) may be used, or two-stage methods such as Faster Region CNN (Faster R-CNN) or Mask R-CNN may be used. Alternatively, other deep learning object detection algorithms may be used for signal detection.

[0022] The wireless signal information 122 includes wireless signal data transmitted from an arbitrary transmitting device and received by the radio wave sensor 200, etc. For example, the wireless signal information 122 is updated in response to reception of wireless signal data by the receiving unit 131.

[0023] The image information 123 includes spectrum images obtained by converting spectrum data generated by performing fast discrete Fourier transform processing on the radio signal data included in the radio signal information 122. Specifically, for example, the image information 123 includes spectrum images corresponding to radio signal data that the determination unit 135, which will be described later, determines to satisfy a condition, among the radio signal data included in the radio signal information 122.

[0024] For example, FIG. 2 shows an example of a spectrum image. In FIG. 2, the horizontal axis represents frequency, and the vertical axis represents signal strength (dB). For example, each peak in FIG. 2 represents a signal transmitted from a different transmitting device (including a base station). The value of each pixel is, for example, black or white (0 or 255). Note that the example shown in FIG. 2 shows an example of a spectrum image in which the area containing the signal is painted white and the background is painted black. However, the spectrum image may be other than that shown in FIG. 2, such as by painting the ridge lines of the signal black and the rest white (or vice versa).

[0025] The output information 124 includes information acquired as a result of the signal detection process, such as whether or not a signal exists in the wireless signal data, the location of the signal on the frequency, etc. For example, the output information 124 can include at least one of information indicating the estimated coordinates of the signal area detected by an area estimation unit 137 (described later), information indicating the center frequency or bandwidth converted based on the estimated coordinates by an estimated value conversion unit 138 (described later), and the like.

[0026] The arithmetic processing unit 130 includes an arithmetic device such as a CPU and its peripheral circuits. The arithmetic processing unit 130 reads and executes a program 125 from the storage unit 120, thereby causing the above hardware and the program 125 to cooperate with each other to realize various processing units. Major processing units realized by the arithmetic processing unit 130 include, for example, a receiving unit 131, a spectrum generating unit 132, a power calculating unit 133, a threshold determining unit 134, a determining unit 135, an imaging unit 136, a region estimating unit 137, an estimated value converting unit 138, and an output unit 139.

[0027] The receiving unit 131 receives wireless signal data received by the radio wave sensor 200 or the like via the communication I / F unit 110 or the like. The receiving unit 131 also stores the received wireless signal data in the storage unit 120 as wireless signal information 122. The receiving unit 131 may also receive wireless signal data from an external device other than the radio wave sensor 200 via the communication I / F unit 110 or the like.

[0028] The spectrum generation unit 132 generates spectrum data from the radio signal data by performing fast discrete Fourier transform processing on the radio signal data included in the radio signal information 122. For example, the spectrum generation unit 132 generates spectrum data every time the receiving unit 131 receives radio signal data. In other words, the spectrum generation unit 132 generates spectrum data of a new frame every time the receiving unit 131 receives radio signal data. Furthermore, the power calculation unit 133 calculates the received power for each frequency bin in the spectrum data generated by the spectrum generation unit 132. The functions of the spectrum generation unit 132 and the power calculation unit 133 may be realized using known technology.

[0029] The threshold determination unit 134 determines a threshold used when determining whether the signal transmission state has changed. For example, the threshold determination unit 134 determines the threshold based on a plurality of spectrum data generated from radio signal data received for a predetermined period of time. Note that the predetermined period of time may be set arbitrarily.

[0030] As an example, the threshold determination unit 134 can determine the threshold based on a cumulative distribution function of power fluctuations. For example, the threshold determination unit 134 generates multiple frames of spectrum data from radio signal data received over a predetermined period of time and calculates the amount of power fluctuation between frames for each frequency bin. The threshold determination unit 134 also generates a cumulative distribution function (CDF) of power fluctuations for each frequency bin, as shown in FIG. 3. The threshold determination unit 134 then determines the threshold based on the generated cumulative distribution function. For example, when the number of frames to be imaged is set to approximately 50%, the threshold determination unit 134 determines the value of point 1c, which is obtained by drawing a line horizontally from point 1a, where 0.5, and vertically dropping from point 1b, where 1b, the line intersects with the CDF curve, as the threshold value of the amount of received power fluctuations (P_(Th,n)). The proportion of frames to be imaged may be set arbitrarily.

[0031] Alternatively, the threshold determination unit 134 may determine the threshold based on the average power and standard deviation for each frequency bin when a signal is present. For example, the threshold determination unit 134 generates multiple frames of spectrum data from radio signal data received over a predetermined period of time, and calculates the average power m and standard deviation σ for each frequency bin when a signal is present. Then, the threshold determination unit 134 determines the threshold based on the average power m and standard deviation σ when a signal is present, and a positive integer coefficient k (e.g., a value from 1 to 3). For example, the threshold determination unit 134 determines a value such as m+kσ or m-kσ as the threshold. As an example, the threshold determination unit 134 may determine m+2σ as the first threshold and m-2σ as the second threshold. In this case, as shown in FIG. 4, if the difference between the first threshold and the second threshold, i.e., the difference from the average power m, is in the range 2a shown in FIG. 4, it is determined that the signal transmission state has not changed, and if it is in the range 2b, it is determined that the transmission state has changed. The threshold value determination unit 134 may use different values ​​of k for the positive and negative directions.

[0032] The threshold value determining unit 134 may determine the threshold value by a method other than the above-mentioned example. The threshold value determining unit 134 may determine a predetermined value or the like as the threshold value.

[0033] The determination unit 135 determines whether or not the transmission state of the signal has changed, using the threshold determined by the threshold determination unit 134. Then, for example, if the determination unit 135 determines that the transmission state of the signal has changed, it determines to visualize the spectrum data. On the other hand, if it determines that the transmission state of the signal has not changed, it determines not to visualize the spectrum data.

[0034] Specifically, for example, the determination unit 135 checks whether or not there is a frequency bin in the spectrum data generated by the spectrum generation unit 132 where the amount of power fluctuation from the previous frame, etc., is equal to or greater than a threshold. For example, if there is a frequency bin where the amount of power fluctuation is equal to or greater than the threshold, the determination unit 135 determines that the signal transmission state has changed and decides to visualize the spectrum data. On the other hand, if there is no frequency bin where the amount of power fluctuation is equal to or greater than the threshold, the determination unit 135 determines that the signal transmission state has not changed and decides not to visualize the spectrum data.

[0035] For example, if the amount of fluctuation (difference value) between the power value of the previous frame and the power value of the current frame is large in the positive direction, it is considered that signal transmission has started. On the other hand, if the amount of power fluctuation is large in the negative direction, it is considered that signal transmission has stopped. Also, if the amount of power fluctuation is small, it is considered that the signal transmission state or the signal non-transmission state continues. Therefore, in the present invention, a threshold determination is performed on the amount of power fluctuation for each frequency bin as expressed by Equation 1, thereby determining whether or not to thin out the frame.

number

[0036] Furthermore, the determination unit 135 may determine whether the transmission state of the signal has changed by checking, for each frequency bin, whether the received power is equal to or greater than a first threshold or equal to or less than a second threshold. For example, if the spectrum data includes a frequency bin whose received power is equal to or greater than the first threshold or equal to or less than a second threshold, the determination unit 135 may determine that the transmission state of the signal has changed and decide to visualize the spectrum data. On the other hand, if the spectrum data does not include a frequency bin whose received power is equal to or greater than the first threshold or equal to or less than the second threshold, the determination unit 135 may determine that the transmission state of the signal has not changed and decide not to visualize the spectrum data.

[0037] The imaging unit 136 converts the spectrum data into a spectrum image in accordance with the result of the determination by the determination unit 135. For example, the imaging unit 136 converts the spectrum data that the determination unit 135 has determined to be imaged into a spectrum image in, for example, BMP or PNG format, as illustrated in Fig. 2. The imaging unit 136 also stores the converted spectrum image in the storage unit 120 as image information 123. The imaging unit 136 may convert the spectrum data into a spectrum image using known technology.

[0038] The region estimation unit 137 is a detection unit that performs signal detection processing based on a spectrum image. For example, the region estimation unit 137 inputs the spectrum image converted by the imaging unit 136 to the trained model 121. Then, the region estimation unit 137 detects a signal region using the trained model 121 and outputs estimated coordinates. In addition, the region estimation unit 137 can store the estimated coordinates in the storage unit 120 as output information 124.

[0039] As an example, the region estimation unit 137 outputs estimated coordinates indicating the position (e.g., coordinates) of a signal region detected as an object using a signal detection algorithm (object detection algorithm) such as the above-mentioned YOLO, as well as the width and height of the signal region. For example, when a YOLO-based signal detection algorithm is used, estimated coordinates expressed as (x, y, width, height) may be output. An example of estimated coordinates is shown in FIG. 5. With reference to FIG. 5, for example, x indicates the x-axis value of the upper left coordinate of the detected signal region, y indicates the y-axis value of the upper left coordinate of the detected signal region, width indicates the width of the detected signal region, and height indicates the height of the detected signal region. The region estimation unit 137 may output estimated coordinates in a format other than the above example.

[0040] The estimated value conversion unit 138 is a detection unit that performs signal detection processing using the processing results of the region estimation unit 137. For example, the estimated value conversion unit 138 calculates the center frequency, bandwidth, etc. of the detection signal from the estimated coordinates output by the region estimation unit 137. Specifically, for example, the estimated value conversion unit 138 calculates the center frequency, bandwidth, etc. from the estimated coordinates (e.g., (x, y, width, height)) using the relationship between the bandwidth (the inverse of the sampling rate) and the number of FFT points (the number of pixels on the horizontal axis of the image) when generating a spectrum image. Furthermore, the estimated value conversion unit 138 can store the center frequency, bandwidth, etc. of the detection signal in the storage unit 120 as output information 124. The processing of the estimated value conversion unit 138 may also be known.

[0041] The output unit 139 outputs the information included in the output information 124 to an external device or the like via the communication I / F unit 110 or the like. The output unit 139 may be configured to display the information included in the output information 124 on an image display device or the like connected to the signal detection device 100.

[0042] The above is an example of the configuration of the signal detection device 100. Next, an example of the operation of the signal detection device 100 will be described with reference to FIG.

[0043] Fig. 6 shows an example of the operation of the signal detection device 100. Referring to Fig. 6, the receiving unit 131 receives wireless signal data received by the radio wave sensor 200 or the like via the communication I / F unit 110 or the like (step S101).

[0044] The spectrum generation unit 132 performs fast discrete Fourier transform processing on the radio signal data included in the radio signal information 122, thereby generating spectrum data from the radio signal data (step S102).

[0045] The power calculation unit 133 calculates the received power for each frequency bin in the spectrum data generated by the spectrum generation unit 132 (step S103).

[0046] The threshold determination unit 134 and the determination unit 135 perform a thinning-out determination process. That is, using the threshold determined by the threshold determination unit 134, the determination unit 135 determines whether or not to convert the spectrum data into a spectrum image. Furthermore, the imaging unit 136 and the region estimation unit 137 perform a region estimation process based on the spectrum image. That is, by inputting the spectrum image visualized by the imaging unit 136 to the trained model 121, the region estimation unit 137 detects a signal region and outputs estimated coordinates. In this way, the threshold determination unit 134, the determination unit 135, the imaging unit 136, and the region estimation unit 137 perform a thinning-out determination process and a region estimation process (step S104).

[0047] The estimated value conversion unit 138 calculates the center frequency, bandwidth, etc. of the detection signal from the estimated coordinates output by the region estimation unit 137 (step S105).

[0048] After the process of step S105, the output unit 139 may output information indicating the estimated coordinates, the center frequency, the bandwidth, and the like.

[0049] The above is an example of the operation of the signal detection device 100. Next, the process of step S104 will be described in more detail with reference to FIG.

[0050] 7, the determination unit 135 calculates the amount of power fluctuation from the previous frame for each frequency bin, for example (step S201). Also, the threshold determination unit 134 determines a threshold.

[0051] The determination unit 135 determines whether or not there is a frequency bin whose variation amount is greater than the determined threshold (step S202). If there is no frequency bin whose variation amount is greater than the determined threshold (step S202, No), the determination unit 135 determines not to visualize the spectrum data. On the other hand, if there is a frequency bin whose variation amount is greater than the determined threshold (step S202, Yes), the determination unit 135 determines to visualize the spectrum data.

[0052] The imaging unit 136 converts the spectrum data into a spectrum image according to the result of the determination by the determination unit 135 (step S203).

[0053] The region estimation unit 137 inputs the spectrum image converted by the imaging unit 136 to the trained model 121. Then, the region estimation unit 137 detects a signal region using the trained model 121 and outputs estimated coordinates (step S204).

[0054] The above is a detailed example of the process in step S104 shown in FIG.

[0055] As described above, the signal detection device 100 includes the determination unit 135 and the imaging unit 136. With this configuration, the imaging unit 136 can convert the spectrum data that the determination unit 135 has determined to be imaged into a spectrum image. In other words, the imaging unit 136 can thin out the objects to be imaged. In other words, with the above configuration and operation, it becomes possible to thin out the wireless signal data to be processed by the learning model for signal detection. As a result, the total amount of wireless signal data to be processed is reduced, which has the effect of improving the average detection processing speed.

[0056] The signal detection device 100 described above illustrates a case in which it determines whether to perform thinning processing or the like on the entire spectrum data generated from wireless signal data. However, when training the detection process, inputting the entire spectrum image into the training model may result in excessive memory usage, preventing the learning process from progressing. Furthermore, when the signal to be detected is present only in a portion of the reception band, inputting an image of the area where the signal is not present may result in a decrease in frame rate.

[0057] Therefore, the signal detection device 100 may be configured to divide the spectrum data into M divided regions (M is a natural number equal to or greater than 2) and determine whether or not to perform imaging for each divided region. That is, as shown in FIG. 8, the arithmetic processing unit 130 of the signal detection device 100 may have a function as a dividing unit 140 that divides the spectrum data into M regions by executing a program 125 stored in the storage unit 120. When the signal detection device 100 includes the dividing unit 140, the determining unit 135 may determine whether or not to perform imaging for each divided region divided by the dividing unit 140. Furthermore, the processing after imaging by the imaging unit 136 may also be performed for each divided region.

[0058] 9 shows an example of operation when the signal detection device 100 includes the dividing section 140. Referring to FIG. 9, the processes of steps S101, S102, and S103 may be the same as those described with reference to FIG.

[0059] The threshold determination unit 134 and the determination unit 135 perform a thinning-out determination process. That is, the determination unit 135 determines whether or not to convert the divided regions into spectrum images using the threshold determined by the threshold determination unit 134. Furthermore, the imaging unit 136 and the region estimation unit 137 perform a region estimation process based on a partial spectrum image obtained by imaging the divided regions. In this way, when the signal detection device 100 includes the division unit 140, the threshold determination unit 134, the determination unit 135, the imaging unit 136, and the region estimation unit 137 perform a thinning-out determination process and a region estimation process for each divided region (step S301).

[0060] The estimated value conversion unit 138 calculates the center frequency, bandwidth, etc. of the detection signal from the estimated coordinates output by the region estimation unit 137 (step S302). At this time, the estimated value conversion unit 138 can calculate the center frequency, bandwidth, etc., taking into consideration that the spectrum data is divided into divided regions.

[0061] Next, the process of step S301 will be described in more detail with reference to Fig. 10. Referring to Fig. 10, the dividing unit 140 divides the spectrum data into M divided regions (step S401).

[0062] Thereafter, the process is looped for each divided region. That is, the processes from step S402 to step S405 are performed for each of the M divided regions into which the spectrum data is divided (M is a natural number of 2 or more).

[0063] The determining unit 135 calculates the amount of power fluctuation from the previous frame for each frequency bin included in the divided region (step S402). Also, the threshold determining unit 134 determines a threshold.

[0064] The determination unit 135 determines whether or not there is a frequency bin whose variation amount is greater than the determined threshold (step S403). If there is no frequency bin whose variation amount is greater than the determined threshold (step S403, No), the determination unit 135 determines not to image the divided region. On the other hand, if there is a frequency bin whose variation amount is greater than the determined threshold (step S403, Yes), the determination unit 135 determines to image the divided region.

[0065] The imaging unit 136 converts the divided region into a partial spectrum image according to the result of the determination by the determination unit 135 (step S404).

[0066] The region estimation unit 137 inputs the partial spectrum image converted by the imaging unit 136 to the trained model 121. Then, the region estimation unit 137 detects a signal region using the trained model 121 and outputs estimated coordinates (step S405).

[0067] In this way, the signal detection device 100 may include the dividing unit 140. By including the dividing unit 140, the signal detection device 100 can perform area estimation processing by imaging only a part of the divided areas, as shown in Fig. 11. As a result, it is possible to further improve the processing speed.

[0068] When dividing the spectrum data, the dividing unit 140 may divide the spectrum data into multiple divided regions so that the frequencies included therein partially overlap. In other words, the divided regions divided by the dividing unit 140 may have frequencies that partially overlap with other divided regions. Simply dividing the spectrum data into M equal parts may result in signals present at the boundaries being cut off and unable to be detected. This risk can be alleviated by configuring the dividing unit 140 to divide the spectrum data so that the frequencies included therein partially overlap. The overlap ratio may be set arbitrarily.

[0069] In the above example, a modified example of the signal detection device 100 has been described in which processing such as threshold determination is performed after division by the division unit 140. However, the signal detection device 100 may be configured, for example, to divide only regions equal to or greater than the threshold after threshold determination and to image the divided regions. In other words, the division unit 140 may be configured to divide the spectrum data after processing by the determination unit 135.

[0070] [Second embodiment] Next, a second embodiment of the present invention will be described with reference to Fig. 12 and Fig. 13. Fig. 13 shows an example of the configuration of a signal detection device 300. In Figs.

[0071] The signal detection device 300 is an information processing device that detects the presence or absence of a signal and the location of the signal on a frequency based on a wireless signal. Fig. 12 shows an example of the hardware configuration of the signal detection device 300. Referring to Fig. 12, the signal detection device 300 has, as an example, the following hardware configuration. ·CPU(Central Processing Unit)301(Arithmetic unit) ROM (Read Only Memory) 302 (storage device) RAM (Random Access Memory) 303 (storage device) Programs 304 loaded into RAM 303 A storage device 305 for storing the program group 304 A drive device 306 that reads and writes data from a recording medium 310 outside the information processing device A communication interface 307 for connecting to a communication network 311 outside the information processing device Input / output interface 308 for inputting and outputting data Bus 309 connecting each component

[0072] 13 by the CPU 301 acquiring and executing the program group 304. The program group 304 is stored in advance in the storage device 305 or the ROM 302, for example, and is loaded into the RAM 303 or the like by the CPU 301 for execution as needed. The program group 304 may be supplied to the CPU 301 via the communication network 311, or may be stored in advance in the recording medium 310, with the drive device 306 reading out the program and supplying it to the CPU 301.

[0073] 12 shows an example of the hardware configuration of the signal detection device 300. The hardware configuration of the signal detection device 300 is not limited to the above-described case. For example, the signal detection device 300 may be configured with only a part of the above-described configuration, such as excluding the drive device 306.

[0074] The generation unit 321 generates spectrum data based on the received radio signal. For example, the generation unit 321 may receive the radio signal from a radio wave sensor connected to the signal detection device 300 or another external device.

[0075] The determination unit 322 determines whether or not the spectrum data is to be visualized by determining whether or not the radio signal satisfies a predetermined condition. For example, the determination unit 322 determines whether or not the radio signal satisfies a predetermined condition by determining whether or not the received power for each frequency bin in the spectrum data satisfies a predetermined condition.

[0076] The imaging unit 323 converts the generated spectrum data into a spectrum image based on the determination by the determining unit 322 .

[0077] The detection unit 324 performs signal detection processing based on the spectrum image converted by the imaging unit 323. For example, the detection unit 324 performs signal detection processing using a learning model that has been learned in advance.

[0078] As described above, the signal detection device 300 includes the determination unit 322, the imaging unit 323, and the detection unit 324. With this configuration, the imaging unit 323 can convert the spectrum data that the determination unit 322 has determined to be imaged into a spectrum image. In other words, the imaging unit 323 can thin out the objects to be imaged. As a result, the detection unit 324 can perform signal detection processing based on the spectrum image that has been thinned out in advance. This reduces the time required for signal detection.

[0079] The above-described signal detection device 300 can be realized by incorporating a predetermined program into an information processing device such as the signal detection device 300. Specifically, a program according to another aspect of the present invention is a program for causing an information processing device such as the signal detection device 300 to realize processing of generating spectrum data based on a received radio signal, determining whether the radio signal satisfies predetermined conditions, thereby deciding whether to visualize the spectrum data, converting the generated spectrum data into a spectrum image based on the decision, and performing signal detection processing based on the converted spectrum image.

[0080] Furthermore, a signal detection method executed by an information processing device such as the signal detection device 300 described above is a method in which the information processing device such as the signal detection device 300 generates spectrum data based on a received radio signal, determines whether the radio signal satisfies a predetermined condition, and thereby decides whether to visualize the spectrum data, converts the generated spectrum data into a spectrum image based on the decision, and performs signal detection processing based on the converted spectrum image.

[0081] Even if the invention is a program having the above-mentioned configuration, or a computer-readable recording medium having the program recorded thereon, or a signal detection method, it has the same functions and effects as the above-mentioned signal detection device 300, and therefore can achieve the above-mentioned object of the present invention.

[0082] <Additional Notes> A part or all of the above-described embodiments can be described as follows: The signal detection device and the like according to the present invention will be outlined below. However, the present invention is not limited to the following configuration.

[0083] (Appendix 1) a generation unit that generates spectrum data based on a received radio signal; a determination unit that determines whether or not the spectrum data is to be visualized by determining whether or not the wireless signal satisfies a predetermined condition; an imaging unit that converts the spectrum data generated by the generation unit into a spectrum image based on the determination by the determination unit; a detection unit that performs signal detection processing based on the spectrum image converted by the imaging unit; have Signal detection device. (Appendix 2) a calculation unit that calculates a received power for each frequency bin in the spectrum data generated by the generation unit, The determination unit determines whether the received power for each frequency bin calculated by the calculation unit satisfies a predetermined condition. 2. The signal detection device of claim 1. (Appendix 3) The determination unit determines whether or not a fluctuation amount of received power in the spectrum data between frames satisfies a predetermined condition. 3. The signal detection device of claim 2. (Appendix 4) a determination unit that determines a threshold based on the received power for each frequency bin calculated by the calculation unit, The determination unit determines whether a predetermined condition is satisfied based on the threshold determined by the determination unit and the received power for each frequency bin calculated by the calculation unit. 4. A signal detection device according to claim 2 or 3. (Appendix 5) The determination unit determines whether a frequency bin exists in which the amount of fluctuation in received power in the spectrum data between frames is equal to or greater than the threshold value, thereby determining whether a predetermined condition is met. 5. The signal detection device of claim 4. (Appendix 6) The determination unit determines the threshold value based on spectrum data of a plurality of frames generated from a radio signal received for a predetermined period of time. 6. The signal detection device according to claim 4 or 5. (Appendix 7) The determination unit determines the threshold value based on a cumulative distribution function of fluctuations in received power generated from a wireless signal received for a predetermined period of time. 10. A signal detection device according to any one of claims 4 to 6. (Appendix 8) a dividing unit that divides the spectrum data generated by the generating unit, The determining unit determines whether or not the divided areas divided by the dividing unit satisfy a predetermined condition, thereby determining whether or not to image the divided areas. 8. A signal detection device according to any one of claims 1 to 7. (Appendix 9) The information processing device generating spectrum data based on the received radio signals; determining whether the spectrum data is to be imaged by determining whether the wireless signal satisfies a predetermined condition; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. Signal detection methods. (Appendix 10) In the information processing device, generating spectrum data based on the received radio signals; determining whether the spectrum data is to be imaged by determining whether the wireless signal satisfies a predetermined condition; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. A program to realize the processing.

[0084] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0085] 100 Signal detection device 110 Communication I / F section 120 Storage section 121 trained models 122 Radio Signal Information 123 Image Information 124 Output Information 125 Programs 130 Processing unit 131 Receiving unit 132 Spectrum Generation Unit 133 Power calculation section 134 Threshold determination unit 135 Judgment section 136 Imaging Department 137 Area estimation part 138 Estimated value conversion section 139 Output Section 140 Division 200 Radio wave sensor 300 Signal detection device 301 CPU 302 ROM 303 RAM 304 Programs 305 Storage device 306 Drive Device 307 Communication Interface 308 Input / Output Interface 309 Bus 310 Recording Media 311 Communication Network 321 Generation part 322 Judgment section 323 Imaging Department 324 Detector

Claims

1. a generation unit that generates spectrum data based on a received radio signal; a determination unit that determines whether the spectrum data generated from the radio signal satisfies a predetermined condition, thereby determining whether to visualize the spectrum data; an imaging unit that converts the spectrum data generated by the generation unit into a spectrum image based on the determination by the determination unit; a detection unit that performs signal detection processing based on the spectrum image converted by the imaging unit; have Signal detection device.

2. a calculation unit that calculates a received power for each frequency bin in the spectrum data generated by the generation unit, The determination unit determines whether the received power for each frequency bin calculated by the calculation unit satisfies a predetermined condition. The signal detection device according to claim 1 .

3. The determination unit determines whether or not a fluctuation amount of received power in the spectrum data between frames satisfies a predetermined condition. The signal detection device according to claim 2 .

4. a determination unit that determines a threshold based on the received power for each frequency bin calculated by the calculation unit, The determination unit determines whether a predetermined condition is satisfied based on the threshold determined by the determination unit and the received power for each frequency bin calculated by the calculation unit. The signal detection device according to claim 2 or 3.

5. The determination unit determines whether a frequency bin exists in which the amount of fluctuation in received power in the spectrum data between frames is equal to or greater than the threshold value, thereby determining whether a predetermined condition is met.

5. The signal detection device according to claim 4.

6. The determination unit determines the threshold value based on spectrum data of a plurality of frames generated from a radio signal received for a predetermined period of time.

6. The signal detection device according to claim 4 or claim 5.

7. The determination unit determines the threshold value based on a cumulative distribution function of a fluctuation amount of received power for each frequency bin generated from a radio signal received for a predetermined time.

7. A signal detection device according to claim 4, wherein the signal detection device is a signal detection device having a plurality of electrodes.

8. a dividing unit that divides the spectrum data generated by the generating unit, The determining unit determines whether or not the divided areas divided by the dividing unit satisfy a predetermined condition, thereby determining whether or not to image the divided areas. A signal detection device according to any one of claims 1 to 7.

9. The information processing device generating spectrum data based on the received radio signals; determining whether the spectrum data generated from the radio signal satisfies a predetermined condition, thereby determining whether to visualize the spectrum data; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. Signal detection methods.

10. In the information processing device, generating spectrum data based on the received radio signals; determining whether the spectrum data generated from the radio signal satisfies a predetermined condition, thereby determining whether to visualize the spectrum data; converting the generated spectral data into a spectral image based on the determination; A signal detection process is performed based on the converted spectrum image. A program to realize the processing.

Images