JP6895417B2 - Special signal detector - Google Patents

Description

The present invention relates to a special signal detection device that detects light emission in a special signal light emitter.

In a railway signal, which is a device for transmitting train operation information to a train driver, the signal is transmitted by, for example, the driver visually confirming whether the colored light is on or off. For this reason, in order to confirm whether or not the railway signal is approved for viewing so that the driver does not overlook it, for example, it is known that an infrared light emitter is attached to the railway signal and the infrared light emitted from the infrared light emitter is photographed by an infrared video camera. (See Patent Document 1). In Patent Document 1, the railway signal is a railway colored light type signal, a sign, or a special signal light emitter. That is, the special signal light emitter is included in one aspect of the railway signal.

Further, it is also known that a disconnection is detected in the internal structure so that an existing cable can be used as it is in a special signal light emitter or the like in confirming whether or not the special signal light emitter is visually approved (see Patent Document 2).

However, as in Patent Document 1, in order to use an infrared light emitter, it is necessary to make repairs such as attaching an infrared light emitter to an existing device such as a traffic light that emits light, and the repair time and labor are enormous. There is a problem that it becomes a thing. Further, also in the above-mentioned cited document 2, it is considered necessary to newly provide a structure for detecting disconnection.

Further, when two special signal light emitters are captured at one time, if the blinking cycle between the two special signal light emitters is deviated by half a cycle, the emission brightness as a whole becomes uniform and the blinking operation is performed. May not be captured accurately.

Japanese Patent No. 4925987 Japanese Unexamined Patent Publication No. 2015-178357

The present invention has been made in view of the above points, and an object of the present invention is to provide a special signal detection device capable of easily and surely detecting light emission in a special signal light emitter.

Special signal detection apparatus for achieving the above object, and extracts an image pickup unit that captures a continuous image, the partial image composed of a plurality of frames obtained by dividing the continuous image for each image region, the amplitude data for the frequency of the luminance image It is provided with a processing unit and a determination unit for determining the presence or absence of light emission in a special signal light emitter that blinks at a predetermined cycle based on the extraction result of a partial image.

In the special signal detection device, the continuous image acquired by the imaging unit is extracted with the amplitude data with respect to the frequency of the brightness, so that the special signal light emitter blinks in the captured image at a predetermined cycle. It is possible to accurately grasp whether or not an operation is included. In this case, by making a judgment based on the frequency, it is possible to absorb the influence of backlight and image shaking, in particular, at the time of imaging, so that the robustness to the external environment can be made high. Further, in this case, by setting the processing target in the image processing unit to a partial image composed of a plurality of frames obtained by dividing the continuous image into each image area, for example, two special signal light emitters that blink differently for half a cycle are simultaneously generated. Even in the case where the images have been taken and the blinking operations of each special signal light emitter cancel each other out, it is possible to capture only one of these, and a more reliable special signal light emitter. Light emission can be detected. Further, in this case, the special signal light emitter to be imaged does not need to be provided with, for example, an infrared light emitter or a structure for detecting disconnection, and desired detection can be performed with a simple configuration.

In a specific aspect of the present invention, the image processing unit extracts data by performing a Fourier transform process on the entire partial image. In this case, the special signal light emitter can be detected by performing the Fourier transform process on the entire partial image.

In another aspect of the present invention, the image processing unit has an image segmentation processing unit that divides a continuous image into a plurality of image regions to create a plurality of partial images, and for each partial image created by the image segmentation processing unit. Extract the amplitude data to. In this case, it is possible to detect the light emission for each partial image obtained by dividing.

In yet another aspect of the present invention, the determination unit determines the presence or absence of light emission in the special signal light emitter for each partial image created by the image segmentation processing unit. In this case, the special signal light emitter can be determined for each partial image obtained by dividing.

In yet another aspect of the present invention, when the image processing unit determines that there is no blinking in the special signal light emitter in the determination result of the determination unit based on the entire continuous image, the image processing unit determines a plurality of partial images by the image segmentation processing unit. Create. In this case, when the blinking of the special signal light emitter is not detected by the detection based on the whole continuous image, a partial image can be created and the special signal light emitter can be detected based on the partial image.

In yet another aspect of the present invention, the image processing unit determines that the special signal light emitter is in the lit state and not in the blinking state based on the wavelength band characteristic of the light in the judgment result of the judgment unit based on the entire continuous image. In this case, the image segmentation processing unit creates a plurality of partial images. In this case, when the state of the special signal light emitter is unknown in the detection based on the entire continuous image, a partial image can be created and the special signal light emitter can be detected based on the partial image.

In yet another aspect of the present invention, the image processing unit determines that the partial image is in a blinking state even after extracting amplitude data for a plurality of partial images created by the image segmentation processing unit a predetermined number of times. Finish the creation. In this case, the final judgment can be made after extracting the amplitude data of the partial image a predetermined number of times.

In still another aspect of the present invention, the image processing unit is a partial image in which the special signal light emitter is determined to be in the extinguished state in the judgment result of the judgment unit among the plurality of partial images created by the image segmentation processing unit. No further processing is required for. In this case, a part of the processing can be omitted, and the processing can be simplified.

In yet another aspect of the present invention, the image processing unit changes the method of extracting a partial image according to the determination result of the determination unit. In this case, the extraction method can be changed to perform new detection, and by extension, a new judgment regarding the special signal light emitter can be made.

In yet another aspect of the present invention, the determination unit determines whether or not to change the partial image extraction method according to the change over time regarding the extraction result of the amplitude data in the image processing unit. In this case, whether or not to change the extraction method according to the judgment such as a temporary change in brightness due to the influence of utility poles or trees existing near the railroad track from the change over time regarding the extraction result. By deciding whether or not, more accurate detection becomes possible.

In yet another aspect of the present invention, the determination unit emits a special signal that emits light when amplitude data having peaks at different timings is extracted from one partial image obtained by extracting different image regions and another partial image. Judge that there are multiple light emitters. In this case, it is detected for a plurality of special signal light emitters.

In yet another aspect of the present invention, the notification unit is provided to notify when it is determined that the special signal light emitter emits light in the determination result of the determination unit. In this case, the occurrence of an abnormal situation due to the operation of the special signal light emitter can be notified on the side of the special signal detection device by a method different from the transmission by the special signal light emitter.

In yet another aspect of the present invention, the notification unit is a voice unit that issues an alarm. In this case, when an abnormal situation occurs due to the operation of the special signal light emitter, the special signal detection device can notify by voice by an alarm.

It is a conceptual diagram for demonstrating the outline of the example of the special signal detection apparatus which concerns on 1st Embodiment. It is a front view which shows an example about the appearance of a special signal light emitter. It is a block diagram for demonstrating one configuration example of a special signal detection apparatus. It is a conceptual diagram which shows the extraction of the partial image which consists of a plurality of frames which divided the continuous image into each image area. (A) is a conceptual diagram of an image composed of a plurality of frames to be processed, and (B) is data showing amplitude data with respect to frequency for brightness obtained from a processing result of an image composed of a plurality of frames. Is. (A) is an image diagram conceptually showing an example of how a plurality of special signal light emitters are included in one image, and (B) and (C) are images in which a plurality of special signal light emitters are simultaneously present. It is a conceptual plan view for demonstrating an example about the situation which is imaged. (A) to (C) are graphs for conceptually explaining the state of the cycle shift when the two special signal light emitters blink. It is a graph for conceptually explaining the difference in the extraction of amplitude data due to the deviation of the period between two blinking special signal light emitters. (A) and (B) are image diagrams conceptually showing an example of how a continuous image is divided for each image region in a situation where a plurality of special signal light emitters are simultaneously imaged. It is a flowchart for demonstrating an example about the operation of a special signal detection apparatus. It is a conceptual diagram which shows an example of the image processing in the special signal detection apparatus which concerns on 2nd Embodiment. It is a flowchart for demonstrating an example about the operation of a special signal detection apparatus. (A) is a conceptual diagram showing an example of image processing in the special signal detection device according to the third embodiment, and (B) and (C) are conceptual diagrams for explaining one modified example. It is a conceptual diagram for demonstrating still another modification. (A) to (C) are graphs for conceptually explaining the difference in the change with time regarding the operation detection of the special signal light emitter.

[First Embodiment]
Hereinafter, an example of the special signal detection device according to the embodiment of the present invention will be described with reference to FIG. 1 and the like. FIG. 1 is a conceptual diagram for explaining an outline of an example of the special signal detection device 100 according to the present embodiment. In FIG. 1, a railroad train TR or a train TR equipped with the special signal detection device 100 is shown. It shows the state of the special signal generation system SG on the ground side including the special signal light emitting device 200 (hereinafter, the special signal light emitting device is also simply referred to as a special fire) installed beside the railroad track RR, which is a dedicated traveling path. .. In particular, here, when the special signal light emitter 200 installed beside the track RR on which the train TR travels blinks a red light indicating the occurrence of an abnormal situation, this is a special signal mounted on the train TR. The state of the case of confirmation in the detection device 100 is shown schematically.

As a premise of the above configuration, in the illustrated example, first, the special signal detection device 100 mounted on the train TR is installed in front of the moving body of the train TR in the traveling direction indicated by the arrow A1. More specifically, as shown in a partially enlarged manner, the special signal detection device 100 includes, for example, an imaging unit 10 composed of a camera or the like, and is used to notify the inside of the train TR (particularly the driver). The notification unit IP includes a voice unit 30 and a display unit 40 composed of a speaker, a monitor, and the like, and also includes a management device MC for controlling these in an integrated manner. The special signal detection device 100 arranges the image pickup unit 10 toward the front in the traveling direction of the train TR to capture the special signal light emitter 200 in front of the train TR, and manages the image data of the special signal light emitter 200 in the image pickup unit 10. By processing in the MC, it is confirmed whether or not a blinking operation indicating the occurrence of an abnormal situation is performed, and if necessary, the notification unit IP notifies the inside of the vehicle based on the confirmation result.

As shown in the drawing, the imaging unit 10 here is provided with a wavelength filter FI on the front side for taking in light. The wavelength filter FI has transmission characteristics corresponding to the wavelength band of the light emitted by the special signal light emitter 200. As a result, the light component from the special signal light emitter 200 can be reliably taken in, while the other components can be blocked by the wavelength filter FI. That is, by providing the wavelength filter FI, the extraction of the wavelength band of the light to be the target of the image data acquired by the imaging unit 10 becomes remarkable.

Here, as described above, FIG. 1 illustrates not only the above-mentioned special signal detection device 100 but also the ground-side special signal generation system SG including the special signal light emitter 200. Here, as an example, the special signal generation system SG is provided at the railroad crossing CR, and has a special signal light emitter 200 that is activated by pressing the emergency button EB in addition to the emergency button EB linked to the railroad crossing CR. It is composed. In this case, for example, as shown in the figure, when a vehicle VE such as an automobile is stuck in the railroad crossing CR and the emergency button EB is pressed, the special signal light emitter 200 starts a predetermined blinking operation by red light, thereby causing the railroad crossing. An emergency situation is notified by a blinking display on the train TR approaching the CR.

Here, regarding the notification of the occurrence of an emergency due to the blinking operation of the special signal light emitter 200, even if the special signal light emitter 200 is operating normally, for example, the special signal light emitter 200 installed outdoors and the train TR If it is difficult to check with the naked eye because the position of and is backlit, or if it is difficult to image the front due to severe vibration due to running, in the train TR, the image data of human eyes or the camera itself There is a possibility that the operation of the special signal light emitter 200 cannot be accurately captured only by itself. Further, in the first place, the special signal light emitter 200 is extinguished during normal operation, which is the case of most train operations, and blinks only when an abnormality occurs very rarely, so that it blinks normally. Even if the driver makes an action, it is possible that the driver is paying attention to various other actions and inadvertently overlooks it.

In contrast to the above, the special signal detection device 100 of the present embodiment is made strong against the external environment such as backlight and vibration, that is, highly robust, in consideration of the above circumstances, and the special signal by the driver. It also has a configuration for suppressing oversight of the operation of the light emitter 200.

Hereinafter, as a premise for explaining the special signal detection device 100 of the present embodiment, first, the structure and the like of the special signal light emitter 200 will be described with reference to FIG. In the example here, the special signal light emitter 200 is installed near the railroad crossing, but it is also installed in various places where an abnormal situation may occur, such as a place where there is a risk of rockfall. Has been done.

As shown in FIG. 2 as an example of the appearance, the special signal light emitter 200 here is used at a railroad crossing or the like by causing a large number of linear LED light sources LS arranged on the front surface 200a to emit red light and blinking. Information such as the occurrence of an abnormality is given to the driver and others. That is, the special signal light emitter 200 is installed on the side of the track so that the front surface 200a is directed to the special signal detection device 100 (see FIG. 1 and the like) arranged on the train TR.

As an example of the blinking operation of the special signal light emitter 200, here, it is assumed that the blinking operation is performed about 500 times per minute. In other words, the frequency for the blinking operation of the special signal light emitter 200 is about 8.3 Hz. This frequency of 8.3 Hz can be considered to be a frequency peculiar to the special signal light emitter 200 indicating the blinking operation of the special signal light emitter 200. Hereinafter, this frequency of 8.3 Hz is referred to as a special blinking frequency. The blinking operation as described above is common to all the special signal light emitters 200. That is, when two or more special signal light emitters 200 are present, each of the special signal light emitters 200 blinks with a frequency of 8.3 Hz as a special blinking frequency.

As described above, the special signal light emitter 200 blinks red, that is, light in a specific frequency band at a fixed specific cycle as an operation for notifying the occurrence of an abnormality. Therefore, in the present embodiment, paying attention to the fact that the light emitting operation of the special signal light emitter 200 is a blinking operation by light in a predetermined wavelength band at a predetermined cycle as described above, the image pickup unit of the special signal detection device 100 The red component is extracted from the image data acquired in No. 10, and the red lighting is detected from the difference between the current frame and the previous frame for the frames constituting each frame of the continuous moving image. That is, when it is detected in the acquired image data that the red lighting has a constant frame cycle, the special signal detection device 100 determines that the special signal light emitter 200 emits light, and the sound unit which is a speaker. The alarm is sounded from 30. Further, as will be described in detail with reference to FIG. 4 and the like, in the image processing in the special signal detection device 100, the target image data is divided into each image area, and a partial image composed of a plurality of divided frames (hereinafter referred to as a partial image). , Simply referred to as a continuous partial image), the frequency of the blinking operation described above, that is, the frequency related to the change in brightness is processed.

Further, as a method for detecting the blinking cycle of the special signal light emitter 200 as described above, the Fourier transform is used here. The Fourier transform here is a method of converting the time-series data acquired by the imaging unit 10 into the size of each frequency component. For example, the brightness of the entire continuous partial image extracted from the continuous image acquired by the imaging unit 10. By performing a Fourier transform on each of a plurality of frames, the blinking cycle of the special signal light emitter 200 can be detected. That is, by performing the Fourier transform process, the period, that is, the frequency of the blinking operation of the special signal light emitter 200 is captured, and the operation of the special signal light emitter 200 can be reliably detected. In other words, when the frequency characteristics related to the brightness in each partial image are extracted by performing the Fourier transform process on the continuous partial image, the special signal light emitter 200 performs the blinking operation depending on whether or not the special blinking frequency exists. It is determined whether or not the light is emitted.

Further, as a result of the above analysis, when it is determined that the special signal light emitter 200 has light emission that blinks, the notification unit IP notifies the notification. That is, on the special signal detection device 100 side, the driver can be notified by a method different from the transmission by the special signal light emitter 200.

Hereinafter, with reference to the block diagram of FIG. 3, the configuration of the special signal detection device 100 and the functions of each part constituting the special signal detection device 100 will be described.

As shown in the figure and as described above with reference to FIG. 1, the special signal detection device 100 includes an imaging unit 10, a management device MC, and a notification unit IP. Of these, as shown in the figure, the management device MC includes an image processing unit 20 that performs various image processing, a storage device 50 that stores various data, and a control unit 60 that controls the operation of each unit. The notification unit IP includes a voice unit 30 and a display unit 40 as shown in the figure and as described above.

Among the special signal detection devices 100, first, the image pickup unit 10 is composed of a camera or the like, and can capture a moving image, that is, a continuous image, and transmits the image data acquired by the imaging to the management device MC. As a continuous image here, it is possible to record a moving image at, for example, about 30 fps. Therefore, in the case of the light emitting operation of the special signal light emitter 200 that blinks at about 8.3 Hz, one blinking operation can be captured in about several frames.

Next, in the management device MC, the image processing unit 20 is composed of, for example, a GPU or the like, and performs various processing on the continuous image acquired by the imaging unit 10. In particular, here, the image processing unit 20 has an image segmentation processing unit 20d that divides the continuous image acquired by the imaging unit 10 into a plurality of image regions to create a plurality of partial images. As an example conceptually shown in FIG. 4, the image segmentation processing unit 20d divides a continuous image composed of a plurality of frame GIs acquired by the imaging unit 10 into four regions 1 to 4, and each of the plurality of frame GIds Four partial images (continuous partial images) 1 to 4 composed of the above are created. Returning to FIG. 3, the image processing unit 20 further performs a Fourier transform process on the continuous frame GId (see FIG. 4), that is, the image data arranged in the time series, in accordance with the instruction from the control unit 60 described later. Specifically, a fast Fourier transform (FFT) process is performed. As a result, the amplitude data with respect to the frequency for the brightness in each continuous partial image is extracted. This makes it possible to detect whether or not there is a change in brightness at a frequency corresponding to the blinking operation of the special signal light emitter 200 described above.

Next, among the management devices MC, the storage device 50 is composed of, for example, a storage device or the like, and stores various data or the like. That is, the storage device 50 functions as a recording device that stores various image data such as data acquired by the imaging unit 10 and data processed by the image processing unit 20, and also emits light from, for example, the special signal light emitter 200. The data of the blinking cycle (blinking frequency) in the above, and various programs such as a program for performing the fast Fourier transform (FFT) processing in the image processing unit 20 are stored. Further, in the present embodiment, the data of the continuous partial image generated by the image segmentation processing, which is one of the target data, is created in the image segmentation processing unit 20d, so that the portion of the storage device 50 It is sequentially stored in the image storage unit 50d. In addition, for example, the storage device 50 captures the arrangement position of the special signal light emitter 200 on the line, the position where each special signal light emitter 200 can be visually recognized, and the imaging unit 10 determined according to the position. Data or the like about the starting position or the like may be stored. That is, when the arrangement position of the special signal light emitter 200 and the like are known, it is conceivable to use these to determine the operation start timing and end timing of the special signal detection device 100.

Next, among the management devices MC, the control unit 60 is composed of, for example, a CPU or the like, and controls the operation of each unit constituting the special signal detection device 100 in an integrated manner. That is, necessary data and programs are appropriately read from the storage device 50 according to the processing, and various commands are issued. Further, here, it functions as a determination unit for determining the presence or absence of light emission in the special signal light emitter 200 that blinks at a predetermined cycle based on the extraction result by the fast Fourier transform (FFT) for image analysis in the image processing unit 20. To do. That is, as a determination unit, the control unit 60 emits light from the special signal light emitter 200 for each partial image created by the image segmentation processing unit 20d based on the image data stored in the partial image storage unit 50d (particularly). Whether or not there is a blinking operation) is judged.

Next, of the notification unit IP, the voice unit 30 is composed of a speaker or the like. The voice unit 30 can notify the driver of the occurrence of an abnormality by hearing, for example, by issuing an alarm at a volume sufficiently audible in the driver's seat. For normal driving, by notifying the driver who is performing various operations and confirmations of the occurrence of an abnormality by hearing, it is possible to make it easier to notice and reduce the possibility of oversight.

Finally, of the notification unit IP, the display unit 40 is composed of a monitor or the like. The display unit 40 is arranged at a position in the driver's seat where it is easy for the driver to catch the eye, and displays characters and symbols, or displays various blinking / lighting displays, so that the display can be displayed by light emission from the special signal light emitter 200. Separately, it is possible to visually notify the driver of the occurrence of an abnormality in the driver's seat.

Hereinafter, the Fast Fourier Transform (FFT) for image analysis in the image processing unit 20 will be described with reference to FIG. FIG. 5A is a conceptual diagram of a continuous partial image to be processed by the image processing unit 20, and in the illustration, a state in which each frame GId constituting the continuous partial image is sequentially arranged in chronological order is conceptual. It is shown in. Here, a plurality of frame GIds arranged in these time series are taken out, and fast Fourier transform (FFT) is performed on these to convert the time series data into the size of each frequency component.

Further, FIG. 5B is a curve for an example of data showing the frequency related to the brightness obtained from the processing result by the image processing unit 20 for the plurality of frame GIds constituting the continuous partial image illustrated in FIG. 5A. (Line) It is shown in the graph of C1. In FIG. 5B, the horizontal axis represents frequency and the vertical axis represents amplitude, that is, the degree of luminance change repeated at each frequency. As shown by circled in the illustrated curve C1, when a peak occurs at or near the special blinking frequency of 8.3 Hz, the brightness changes at the frequency of 8.3 Hz, that is, in the special signal light emitter 200. It can be considered that the blinking motion is occurring. Therefore, when the result shown by the curve C1 in FIG. 5B is obtained, the control unit 60 as the determination unit determines that the special signal light emitter 200 has a blinking light emission, and according to the determination result. , The notification unit IP is made to perform the operation of notifying that an abnormality has occurred in the front. If a peak such as the curve C1 does not occur, the control unit 60 determines that the special signal light emitter 200 does not emit light. It should be noted that even when a railroad crossing alarm or the like that causes a periodic blinking operation other than the light emission in the special signal light emitter 200 is also captured in the image, the special blinking frequency as described above Since they are blinking at different frequencies, they do not produce a peak corresponding to the idiopathic blinking frequency.

In the above, the number of frames required to enable the processing by the Fast Fourier Transform (FFT) for the plurality of frames constituting the continuous partial image is determined by the relationship between the special blinking frequency and the frame rate. As in the above example, when the special blinking frequency is about 8.3 Hz (blinking about 500 times per minute) and the moving image imaging by the imaging unit 10 is processed at a frame rate of about 30 fps, FIG. Assuming that the minimum number of blinks (blinking cycle) of the special signal light emitter 200 required to acquire data as in (B) once is about 2 to 3 times, image data for several to a dozen frames can be obtained. You will need it. That is, the data necessary for the determination can be obtained by performing the fast Fourier transform (FFT) on the frame GIds for several frames to a dozen frames. In general, the imaging unit 10 can capture more detailed brightness changes as the number of frame rates increases, that is, as it captures fine movements. From the above consideration, the special blinking frequency is about 8.3 Hz ( If the imaging unit 10 has a moving image imaging capability of about 30 fps, it can be said that sufficient data can be obtained.

Here, when detecting the special signal light emitter 200, for example, as conceptually shown in FIG. 6 (A), a plurality of special signal light emitters 200 (special signal A, special fire) in one whole image constituting a continuous image. It is conceivable that B) exists. Such a situation occurs, for example, when two or more railroad crossing CRs are close to each other on a straight track, or on a curved track where it is difficult to see ahead, as illustrated in FIGS. 6 (B) and 6 (C). This can occur when a plurality of special signal light emitters 200 are installed in advance.

In the above case, if it is attempted to detect the blinking operation of the special signal light emitter 200 using the special blinking frequency by the processing by the fast Fourier transform (FFT) for the entire continuous image, for example, the special A, When each of B operates, the change in brightness may be difficult to be captured or may not be captured depending on the degree of deviation of the blinking cycle between the special A and the special B. The special A and the special B emit light having the same wavelength band characteristics at the same special blinking frequency. Therefore, on the special signal detection device 100 side, it is not possible to distinguish which component is derived from, that is, in the above case, the special signal detection device 100 is divided into the component derived from the special signal A and the special signal B. Only the blinking motion of the light combined with the derived component can be captured. Therefore, in particular, when the special issue A and the special issue B blink at the timing in which they are reversed, there is a possibility that the blinking operation cannot be captured even if the blinking operation is performed. On the other hand, in the present embodiment, it is possible to avoid such a situation as much as possible by performing various processing on the continuous partial image obtained by dividing the continuous image into each image area instead of the entire continuous image.

Hereinafter, first, referring to the graphs of FIGS. 7 (A) to 7 (C), there are two special signal light emitters 200 (special A, special B), and when they blink, they are special. The change in the blinking cycle as a whole due to the change in the degree of deviation of the cycle between A and the special B will be described.

First, FIG. 7A conceptually shows the state of the cycle shift when there is no shift in the blinking cycle between the two special fires A and B. The horizontal axis of the graph shows time, and the vertical axis shows lighting / extinguishing. On this, the curve QA1 shown by the solid line in the figure shows the timing of lighting and blinking of the special issue A, that is, the state of the blinking cycle of the special issue A. Similarly, the curve QB1 shown by the broken line shows the state of the blinking cycle of the special B. The curve QC1 shows the state of the blinking cycle in which the operations of the special A and the special B are combined. In this case, the blinking cycle shown in the curve QC1 coincides with the blinking cycle of the special A and the special B. Therefore, even if the entire image is detected by performing the above-mentioned fast Fourier transform or the like without performing image segmentation, the blinking operation is captured as a result by capturing the blinking cycle shown in the curve QC1. be able to. However, it is not always possible to capture the existence of two special signal light emitters 200 (special A and special B).

On the other hand, for example, in FIG. 7B, as shown in the curves QA1 and QB1, when the blinking cycle of the special issue A and the blinking cycle of the special issue B deviate by 1/4 cycle, they are shown in the curve QC1. As described above, there is a difference between the lighting time and the extinguishing time, which makes it difficult to detect the change in brightness. That is, as compared with the case of FIG. 7A, it becomes difficult to capture the peak value using the special blinking frequency, and for example, the level value (FFT level) detected in the processing by the fast Fourier transform (FFT) becomes lower. It is thought that it will appear by. In particular, in FIG. 7C, as shown in the curves QA1 and QB1, the blinking cycle of the special issue A and the blinking cycle of the special issue B are shifted by 1/2 cycle, and the timing of lighting and extinguishing is the special issue A and the special issue B. If it is reversed with and, it means that one of them is always lit. That is, as shown in the curve QC1, the combination of these makes the emission brightness uniform and does not show the blinking operation.

Hereinafter, the difference in the extraction of the amplitude data due to the difference in the period between the two blinking special signal light emitters 200 (special A and B) will be conceptually described with reference to the graph of FIG. In FIG. 8, the horizontal axis is the period shift between the special A and the special B, and the vertical axis is the FFT level detected in the process by the fast Fourier transform (FFT). Further, the maximum FFT level detected for one special signal light emitter 200 is set to 100%. In FIG. 8, the change in the FFT level detected with the deviation of the period between the two idiopathic A and the idiopathic B in the above cases is shown as a curve QQ. It is known that the curve QQ is a sine curve (cosine). Therefore, as illustrated in FIG. 7 (A), when there is no cycle shift between the two special signal A and the special B, the maximum FFT level is 200%, but the two special signal light emitters 200 blink. The closer the deviation of the operation is to 1/2 cycle, the more difficult it becomes to capture the blinking operation. It is considered that the detection becomes difficult if the deviation is more than 1/4 cycle.

In response to the above, in the present embodiment, as described above, after creating a continuous partial image in which the continuous image is divided for each image region, analysis is performed for each continuous partial image. For example, as shown in FIG. 9A, the entire continuous image is divided into four regions 1 to 4. In this case, for example, as shown in FIG. 9 (B) corresponding to FIG. 6 (A), the special signal A and the special B, which are the two special signal light emitters 200, can be captured in different image regions. Specifically, in the case of the illustration, by performing the processing on the continuous partial image corresponding to the region 1, the peak value or the like caused by the idiopathic A is extracted, and the continuous partial image corresponding to the region 4 is processed. , It is considered that the peak value and the like caused by the idiopathic B are extracted. On the other hand, in areas 2 and 3, it is considered that the blinking operation is not detected.

In the above illustration, for the sake of explanation, the special A and the special B are drawn as if they are contained in the area 1 and the area 4 as in-focus images, but they are actually composed of a camera or the like. Due to the light-collecting ability of the imaging unit 10 and the like, the component light caused by the special A and the special B is not only irradiated to the light receiving elements corresponding to the regions 1 and 4, but also the light receiving elements corresponding to other regions. Can also be received. However, for example, it is considered that the component light of the idiopathic A captured in the region 1 is overwhelmingly larger than the component light of the idiopathic A captured in the other region, while the component light of the idiopathic B is overwhelmingly less. Therefore, as a result of being extracted by the above-mentioned various processes, as described above, the operation of the special issue A is captured in the region 1, and the operation of the special issue B is captured in the region 4. That is, it is possible to accurately capture the blinking operation of each of the two special fires A and B.

Hereinafter, an example of the operation of the special signal detection device 100 will be described with reference to the flowchart of FIG. Here, as described above, the four regions 1 to 4 divided by the image segmentation processing unit 20d of the special signal detection device 100 are sequentially processed.

Specifically, first, the control unit 60 of the special signal detection device 100 reads out the image of the area 1 (area number N = 1) from the partial image storage unit 50d (step S101), and performs image processing on the image of the area 1. It is input to the unit 20 (step S102), the brightness of the entire region is calculated (step S103), and the blinking cycle in the region is detected (step S104). When the special flashing frequency (frequency 8.3 Hz), which is a frequency component of the special signal light emitter 200, is detected at or above a predetermined threshold value from the detection in step S104 (step S105: Yes), the special signal light emitter 200 Upon determining that the operation has been detected, the control unit 60 alerts the driver by the notification unit IP as the management device MC (step S106). After the processing of step S106 or in step S105, when the special blinking frequency (frequency 8.3 Hz) is not detected above the threshold value (step S105: No), the control unit 60 is in the continuous partial image to be processed. It is determined that the special signal light emitter 200 does not exist (is not projected), or even if it exists, it is in the extinguished state (turned off). The value of the area number N is increased so as to move to (step S107), and it is confirmed whether the processing for all the areas, that is, the four areas is completed (step S108). When it is determined in step S108 that the processing is not completed (step S108: No), the control unit 60 performs the processing operation from step S102 for the next area, and determines that the processing is completed. In the case (step S108: Yes), a series of processing operations is terminated.

As described above, in the special signal detection device 100 according to the present embodiment, by extracting the amplitude data with respect to the frequency with respect to the brightness of the continuous image acquired by the imaging unit 10, the special signal is generated in the captured image. It is possible to accurately grasp whether or not the light emitting operation of blinking at a predetermined cycle in the light emitting device 200 is included. In this case, by making a judgment based on the frequency, it is possible to absorb the influence of backlight and image shaking, in particular, at the time of imaging, so that the robustness to the external environment can be made high. Further, in this case, the processing target of the image processing unit 20 is a partial image (continuous partial image) composed of a plurality of frame GIds obtained by dividing the continuous image for each image area, so that, for example, two blinking differently for half a cycle. In this case, the special signal light emitters 200 (special A, special B) have been imaged at one time, and the blinking operations of each special signal light emitter (special A, special B) are canceled out. However, it is possible to capture only one of the special signal A and the special B in any of the continuous partial images, and it is possible to more reliably detect the light emission of the special signal light emitter 200. Further, in this case, the special signal light emitter 200 to be imaged by the image pickup unit 10 does not need to be provided with, for example, an infrared light emitter or a structure for detecting disconnection, and has a simple configuration. The desired detection can be achieved.

In the above, the special signal detection device 100 provided in the train TR illustrated in FIG. 1 may always acquire an image, divide the image, and perform the necessary detection operation. For example, the detection operation may be performed. The start timing and end timing of the above may be appropriately determined. Here, as an example, a method of determining the start timing and the end timing of the operation will be described by utilizing the fact that the installation position of the special signal light emitter 200 is predetermined.

First, as a premise, the installation positions of one or more special signal light emitters 200 installed at railroad crossings and the like along the track RR illustrated in FIG. 1 are known, and are related to the installation positions of each special signal light emitter 200. The information and the visible position of each special signal light emitter 200 according to the installation position by the driver are also known. For example, necessary information is appropriately stored in the storage device 50 and can be called by the control unit 60. And. Along with this, it is assumed that the range on the line RR that needs to be detected by the special signal detection device 100 is also predetermined. Here, as illustrated in FIG. 1, the driver's visible position (predetermined position 600 m to 800 m in front of each special signal light emitter 200) of each special signal light emitter 200, the detection start position before AA ( Detection by the special signal detection device 100 is started from XX (a predetermined position about 1 km in front of each special signal light emitter 200), and detection is performed by the special signal detection device 100 up to the installation position BB of the special signal light emitter 200. That is, the above position XX is set as the start position of detection by the special signal detection device 100, and the installation position BB of the special signal light emitter 200 is set as the end position of detection by the special signal detection device 100. Is the range in which the special signal light emitter 200 needs to be detected on the line RR.

Further, here, it is assumed that the information on the traveling position of the train TR can be acquired by, for example, an on-board device (not shown). As the position information method, various known position detection methods such as position detection using a tachometer can be used. That is, the special signal detection device 100 can receive information about the traveling position of the train TR from, for example, the train TR side.

By setting as described above, the start timing and the end timing of the detection operation by the special signal detection device 100 can be appropriately determined according to the passing position as the train TR moves.

[Second Embodiment]
Hereinafter, an example of the special signal detection device according to the second embodiment will be described with reference to FIG. The special signal detection device according to the present embodiment is a modification of the special signal detection device 100 of the first embodiment, and the management device MC provides an internal processing mechanism such as various image processing by the image processing unit 20. Except for the case of the first embodiment, it is the same as that of the first embodiment, and is common to those illustrated in FIGS.

FIG. 11 is a conceptual diagram showing an example of image processing in the special signal detection device 100 according to the present embodiment, and is a diagram corresponding to FIG. 4 referred to in the first embodiment. In the present embodiment, the management device MC detects the blinking operation of the special signal light emitter 200 also for the continuous image composed of the entire image before division. However, as described above, when the continuous image composed of the entire image before division is analyzed by FFT processing or the like, the degree of deviation in the operation timing between the plurality of special signal light emitters 200 (blinking cycle). Accurate detection may not be possible depending on the degree of deviation. Therefore, in the present embodiment, as shown in the figure, first, a continuous image composed of the entire image before division composed of a plurality of frame GIs is analyzed, and there is a possibility that accurate detection cannot be performed. When this occurs, a partial image (continuous partial image) composed of a plurality of frame GIds is created by performing division processing, and the created continuous partial image is used as an analysis target for determining detection of blinking motion. It has become.

Hereinafter, an example of the operation of the special signal detection device according to the present embodiment will be described with reference to the flowchart of FIG. Here, as described above, the special signal detection device first performs various processes on the entire image acquired by the imaging unit 10, that is, on the plurality of frame GIs in FIG. 11, prior to the division process. , The blinking cycle in the entire area is detected, and if necessary, the detection is performed based on the division process.

Specifically, first, when the control unit 60 of the special signal detection device 100 acquires a continuous image (overall image) composed of a plurality of frame GIs imaged by the image pickup unit 10 (step S201), the image is obtained. By performing the fast Fourier transform (FFT) process by the processing unit 20, the brightness of the entire region is calculated (step S202), and the blinking cycle in the entire region is detected (step S203). That is, when the special signal light emitter 200 is shown in the whole image, it is detected whether or not the special signal light emitter 200 is performing a light emitting operation (blinking operation).

When the special blinking frequency (frequency 8.3 Hz), which is a frequency component of the special signal light emitter 200, is detected (for example, detected above a predetermined threshold value) from the detection in step S203 (step S203: Yes), the special Determining that the blinking operation of the signal light emitter 200 has been detected, the control unit 60 alerts the driver by the notification unit IP as the management device MC to call attention (step S204), and the special signal light emitter. A series of processes relating to the detection of 200 is completed.

On the other hand, in step S203, when the special blinking frequency (frequency 8.3 Hz) is not detected (for example, it is not detected above the threshold value) (step S203: No), the control unit 60 further detects light in a specific wavelength band. It is determined whether or not the frequency is satisfied (step S205). That is, in each frame GI or a continuous image summarizing these, it is confirmed whether or not the light in the wavelength band of the red light used in the special signal light emitter 200 is detected at or above a predetermined threshold value.

If the light in the specific wavelength band is not detected in step S205 (step S205: No), the control unit 60 does not have (not projected) the special signal light emitter 200 in the image, or even if it exists. It is determined that the light is extinguished (turned off) (step S206), and a series of processes related to the detection of the special signal light emitter 200 is completed.

On the other hand, when light in a specific wavelength band is detected in step S205 (step S205: Yes), the control unit 60 determines from the wavelength band characteristics of the light as a determination result based on the entire continuous image described above. It is determined that the 200 may be in the lighting state and the blinking state may not be detected, and the special signal detection device 100 creates a plurality of partial images by the image division processing unit 20d (step). S207). Here, among the partial images created in step S207, those in which the light in the specific wavelength band is not detected are in the region where the special signal light emitter 200 is not included or in the state where the special signal light emitter 200 is turned off. It is determined that the image is a partial image of a certain area, and the subsequent processing is removed so as not to be unnecessary, that is, it is excluded from the processing target (step S208). After that, the partial image to be processed is subjected to a fast Fourier transform (FFT) process by the image processing unit 20, the brightness of the region is calculated (step S209), and the blinking cycle in the region is further determined. Detect (step S210). That is, it is detected whether or not the special signal light emitter 200 shown in each partial image is performing a light emitting operation (blinking operation).

When the special blinking frequency, which is a frequency component of the special signal light emitter 200, is detected from the detection in step S210 (step S210: Yes), the control unit 60 alerts the driver by notification (step S204). , The series of processes related to the detection of the special signal light emitter 200 is completed.

On the other hand, when the special blinking frequency is not detected in step S210 (step S210: No), the control unit 60 confirms whether or not the division process has been performed a predetermined number of times or more (step S211).

If it is determined in step S211 that the predetermined number of times has not been reached (step S211: No), the control unit 60 performs the division process from step S207. At this time, the division method may be changed to detect the special signal light emitter 200 by a new division.

On the other hand, when it is determined in step S211 that the predetermined number of times has been reached (step S211: Yes), the control unit 60 ends a series of processes related to the detection of the special signal light emitter 200. In this case, that is, when the blinking operation of the special signal light emitter 200 is not detected even though the light in a specific red light wavelength band is detected, the special signal light emitter 200 is used. It is conceivable that light derived from something other than the special signal light emitter 200 containing a component of a specific red light wavelength band to be generated is captured by the imaging unit 10.

After completing the series of processes shown in each of the above steps, the special signal detection device 100 starts the above operation with respect to the image data acquired next, and repeats the above operation until the light emission detection of the special signal light emitter is no longer necessary. ..

As described above, also in the special signal detection device according to the present embodiment, the special signal is determined not based on the image itself but on the frequency of the brightness indicating the characteristic of the blinking state extracted from the continuous image. It can absorb the effects of backlight and image shaking during imaging by the light emitter, and can be highly robust to the external environment. Then, if the required result cannot be obtained by the analysis of the entire continuous image, the continuous partial image obtained by dividing the continuous image into each image area is used as the analysis target for judgment, for example, half. Even if two special signal light emitters that blink at different cycles are imaged at once and the blinking operations of each special signal light emitter cancel each other out, one of the continuous partial images. In the above, it becomes possible to capture only one of the two special signal light emitters, and more reliable light emission detection of the special signal light emitter can be performed.

[Third Embodiment]
Hereinafter, an example of the special signal detection device according to the third embodiment will be described with reference to FIG. 13 and the like. The special signal detection device according to the present embodiment is a modification of the special signal detection device 100 or the like of the first embodiment, and is the case of the first embodiment or the like except for the method of image segmentation in the image segmentation processing unit 20d. Since it is the same as the above, other figures will be referred to as appropriate for the components, and detailed description thereof will be omitted.

FIG. 13A is a conceptual diagram showing an example of image segmentation processing in the image processing in the special signal detection device 100 according to the present embodiment. For example, in the first embodiment, as the division into the four regions 1 to 4, the division into four rectangular regions of 2 × 2 in the vertical and horizontal directions as shown as the division pattern PT1 in FIG. 13 is adopted. The division method is not limited to this, and various aspects can be considered. For example, as shown in the division pattern PT2, it is conceivable that the entire area of the rectangle is divided into areas 1 to 4 of four triangular areas separated by two diagonal lines. Further, as shown in the division pattern PT3 and the division pattern PT4, long-shaped regions divided in the vertical direction or the horizontal direction may be arranged in a row. Further, as shown by arrows AR1 to AR4, it is conceivable to give variation in the method of division by sequentially changing these division patterns. For example, in the second embodiment, in the flowchart of FIG. 12, it is conceivable to combine the above as the division pattern of a predetermined number of times in step S211. That is, the partial image extraction method can be changed according to the determination result of the control unit 60, which is the determination unit.

The area occupied by the special signal light emitter 200 projected by the image pickup unit 10 in the image is considered to be different depending on the installation environment as illustrated in FIGS. 6 (B) and 6 (C). Furthermore, the imaging situation changes every moment as the train runs. Therefore, when two or more special signal light emitters 200 appear, it is not always possible to unconditionally define what kind of division pattern is optimal to be adopted in order to sort them by region. Therefore, by preparing various division patterns, the certainty of detection is improved.

In the above, all of the four divisions are illustrated, but the present invention is not limited to this, and for example, the division patterns PTα and PTβ showing one modification in FIGS. 13 (B) and 13 (C) are divided into two. May be. Further, it is conceivable to divide the number into other numbers. Further, as shown by hatching in FIG. 14, each of the divided regions 1 to 4 may be a partially superimposed region in the original overall image. In other words, a partial image may be created by cutting out a part of the continuous image.

As described above, also in the special signal detection device according to the present embodiment, the continuous partial image obtained by dividing the continuous image for each image region is the target of the analysis for judgment, and the division pattern is changed as necessary. Therefore, for example, even if two special signal light emitters that blink differently for half a cycle are imaged at one time and the blinking operations of the special signal light emitters cancel each other out, they are continuous. In any of the partial images, it is possible to capture only one of the two special signal light emitters, and it is possible to more reliably detect the light emission of the special signal light emitter.

[Other]
The present invention is not limited to the above-described embodiment, and can be implemented in various embodiments without departing from the gist thereof.

First, in each of the above aspects, it may be determined whether or not to change the extraction method of the partial image according to the change with time regarding the extraction result of the amplitude data. 15 (A) to 15 (C) are graphs for conceptually explaining the difference in the change with time with respect to the operation detection of the special signal light emitter 200. In each figure, the horizontal axis of the graph shows the passage of time, which is the distance from the special signal detection device 100 mounted on the traveling train to the special signal light emitter 200 fixedly installed. Corresponds to showing change (gradual approach). On the other hand, the vertical axis of the graph shows the FFT level detected by the special signal detection device 100.

Of these, FIG. 15A conceptually shows a typical example of the extraction result of amplitude data when the special signal detection device 100 detects the blinking operation of one special signal light emitter 200. It is a thing. That is, in the case of the figure, since the distance from the special signal detection device 100 to the special signal light emitter 200 decreases with the passage of time, the FFT level gradually increases to the upward-sloping line (curve or straight line) CC1. ..

On the other hand, in actual measurement, it is considered that the tendency may be as shown by the line CC2 shown in FIG. 15B, for example. That is, the FFT level is temporarily lowered as compared with the line CC1 shown by the broken line, but after a while, it is assumed that the FFT level returns to the same state as in the case of FIG. 15A. This is considered to occur, for example, when a utility pole or a tree existing near a railroad track is shaded and the brightness changes temporarily. In such a case, it is considered that the blinking operation in one special signal light emitter 200 is captured as in the case of FIG. 15A.

On the other hand, for example, the tendency may be as shown in line CC3 shown in FIG. 15 (C). That is, in FIG. 15 (C), the FFT level decreases as in the case of FIG. 15 (B), but after that, it does not return to the same state as shown in line CC1 even after a lapse of time. .. In such a case, unlike the cases of FIGS. 15 (A) and 15 (B), two or more special signal light emitters 200 are projected when the FFT level drops, and the amplitude is caused by the interference between them. It is considered that the data extraction result may be affected.

Taking the above situations into consideration, for example, when the tendency as illustrated in FIG. 15C is observed, the operation detection of the special signal light emitter 200 based on the divided images shown in each of the above embodiments is detected. It is conceivable that even if the operation detection of the plurality of special signal light emitters 200 occurs, it can be reliably captured.

In addition, the items described in each of the above-described embodiments may be appropriately combined and configured.

Further, in the above, the case where the special signal detection device 100 is mounted on the train of the railway as a moving body on the track as a dedicated running path is described, but the present invention is not limited to this, and for example, the track as a dedicated running path ( For trams that are vehicles (moving bodies) that travel on new tracks (new tracks, combined tracks), and buses that are vehicles that travel on dedicated roads as dedicated roads, the special signal light emitter 200 provided on the side of the dedicated road, etc. On the other hand, it is also possible to provide the special signal detection device 100.

Further, when a camera is provided for various detections such as for detecting the presence or absence of an obstacle in a moving body such as a train, the camera may be used as the imaging unit 10. That is, the light emission detection by the special signal light emitter 200 according to the configuration of the present application may be performed by using the image information acquired by the camera provided for various detections. For example, among the data captured by the obstacle detection camera, only the image data in the detection target section by the special signal detection device 100 may be used. Further, although the image pickup unit 10 is a camera, various ones can be applied as long as it can receive light necessary for data extraction. For example, it is conceivable that the image pickup unit 10 is composed of only a light receiving element without a lens. Be done. Further, in the above, the wavelength filter FI is provided on the front side of the imaging unit 10, but the position of the wavelength filter FI may be other than the front surface, and the wavelength filter FI may be provided at another position on the optical path in the imaging unit 10. May be good. Further, the light receiving characteristic of the light receiving element in the imaging unit 10 may correspond to the characteristic of the light from the special signal light emitter 200.

Further, for example, each part constituting the special signal detection device 100, which is partially enlarged and illustrated in FIG. 1, is incorporated into a moving body such as an existing train as a unit as a unit, for example, in a single housing. It may be possible to attach it.

10 ... Imaging unit, 20 ... Image processing unit, 20d ... Image division processing unit, 30 ... Audio unit, 40 ... Display unit, 50 ... Storage device, 50d ... Partial image storage unit, 60 ... Control unit, 100 ... Special signal detection Device, 200 ... Special signal light source, 200a ... Front, A, B ... Special signal (special signal light source), A1 ... Arrow, AA ... Predetermined position, AR1-AR4 ... Arrow, BB ... Installation position, C1 ... Curve, CC1 ~ CC3 ... line, CR ... railroad crossing, DD ... section, EB ... emergency button, FI ... wavelength filter, GI ... frame, GId ... frame, IP ... notification unit, LS ... LED light source, MC ... management device, PT1 to PT4, PTα, PTβ ... division pattern, QA1, QB1, QC1 ... curve, QQ ... curve, RR ... line, SG ... special signal generation system, TR ... train, VE ... vehicle, XX ... position

Claims (13)

It is a special signal detection device installed in trains that operate normally.
An imaging unit that captures continuous images and
An image processing unit that extracts amplitude data with respect to a luminance frequency for a partial image composed of a plurality of frames obtained by dividing the continuous image into image regions.
A special signal detection device including a determination unit for determining the presence or absence of light emission in a special signal light emitter that blinks at a predetermined cycle based on the extraction result of the partial image. The special signal detection device according to claim 1, wherein the image processing unit extracts data by performing a Fourier transform process on the entire partial image. The image processing unit has an image division processing unit that divides the continuous image into a plurality of image regions to create a plurality of the partial images, and amplitude data for each of the partial images created by the image division processing unit. The special signal detection device according to any one of claims 1 and 2. The special signal detection device according to claim 3, wherein the determination unit determines the presence or absence of light emission in the special signal light emitter for each of the partial images created by the image segmentation processing unit. The image processing unit creates a plurality of the partial images by the image segmentation processing unit when it is determined that there is no blinking in the special signal light emitter in the determination result of the determination unit based on the entire continuous image. The special signal detection device according to any one of claims 3 and 4. When the image processing unit determines in the determination result of the determination unit based on the entire continuous image that the special signal light emitter is in the lit state and not in the blinking state from the wavelength band characteristic of light, the image The special signal detection device according to any one of claims 3 and 4, wherein a plurality of the partial images are created by the division processing unit. The image processing unit ends the creation of the partial image when it is not determined that the partial image is in the blinking state even after the amplitude data extraction of the plurality of partial images created by the image segmentation processing unit is performed a predetermined number of times. The special signal detection device according to claim 6. Among the plurality of the partial images created by the image segmentation processing unit, the image processing unit refers to the partial image in which the special signal light emitter is determined to be in the extinguished state in the determination result of the determination unit. The special signal detection device according to any one of claims 6 and 7, which eliminates the need for processing. The special signal detection device according to any one of claims 1 to 8, wherein the image processing unit changes the extraction method of the partial image according to the determination result of the determination unit. The special signal detection device according to claim 9, wherein the determination unit determines whether or not to change the extraction method of the partial image according to a change with time regarding the extraction result of the amplitude data in the image processing unit. .. The determination unit determines that there are a plurality of special signal light emitters that emit light when amplitude data having peaks at different timings is extracted from one partial image obtained by extracting different image regions and the other partial image. The special signal detection device according to any one of claims 1 to 10, which is determined. The special signal detection device according to any one of claims 1 to 11, further comprising a notification unit that notifies when it is determined that the special signal light emitter emits light in the determination result of the determination unit. The special signal detection device according to claim 12, wherein the notification unit is a voice unit that issues an alarm.

Images