JP6829165B2 - Monitoring system and monitoring method - Google Patents

Description

The present invention relates to a monitoring system and a monitoring method, and relates to a monitoring system and a monitoring method for monitoring an area where a vehicle enters a platform such as a railroad.

A monitoring system using image processing is known for ensuring the safety of passengers and the like on a station platform (see, for example, Patent Documents 1 and 2). In the technique disclosed in Patent Document 1, a disturbance in home monitoring and a fallen person are distinguished, and only the fallen person is accurately detected and issued. In addition, the technology disclosed in Patent Document 2 minimizes the confusion associated with displaying images of different platforms, eliminates the need for detection means for determining the status of platforms and trains, and provides a system that is simple in configuration and easy to install. Proposed.

Japanese Unexamined Patent Publication No. 2011-166243 Japanese Unexamined Patent Publication No. 2012-86754

By the way, in the detection processing by image processing, it is necessary for the technician to manually adjust the setting of the image processing detection area, the tuning of the image processing parameters according to the local environment, the camera setting, etc. before the system operation. It was very voluminous, costly and time consuming. If the detection accuracy did not meet the customer's request even after the start of operation, the technician had to go to the site again to make adjustments, and another technology was required. That is, regarding the detection accuracy, it is required that the technician periodically discriminates on the spot based on the image processing result, and another technique is required in this respect as well. From another point of view, when a dangerous behavior is detected by image processing, an alarm is often output and the station staff often sees the video to make a final decision, and there is a need for technology that accumulates that information and uses it for risk prediction. Was being done.

The present invention has been made in view of such a situation, and an object of the present invention is to solve the above problems.

The present invention is a surveillance system including a surveillance camera that captures a platform on which a vehicle enters as a surveillance area, and a data processing device that performs image processing on the video captured by the surveillance camera to determine a warning level. The data processing device identifies a person included in the video of the surveillance area, accumulates appearance points and disappearance points of the person, and is included in the surveillance area of the surveillance camera based on the accumulated results. While learning the position of the object, the action area of the person is determined, and the risky behavior detection area for determining the risky behavior with respect to the person is set.
Further, the data processing device detects the characteristics of the vehicle that has entered the platform by image processing, accumulates the detected characteristics in association with the time information, and collates with the operation information of the vehicle to match the characteristics of the vehicle. It may be reflected in the detection result.
In addition, the data processing device has a function of acquiring audio data output to the platform, and is a person having a certain speed or higher from the amount of movement of the person between image frames in the risky behavior detection area on the platform. If it is determined that the action is a dangerous behavior and the acquired voice data matches the predetermined reference data, the warning level may be increased for the person recognized as the dangerous behavior after the voice data.
Further, the data processing device records a video in which the dangerous behavior is recorded in association with the occurrence position, the occurrence time, and the warning level information of the dangerous behavior, and the appearance frequency of the dangerous behavior is equal to or higher than a predetermined time zone. In this case, a display output calling attention may be performed in the predetermined time zone.
The present invention is a monitoring method for performing data processing for determining a warning level by performing image processing on an image captured by a surveillance camera that captures a platform on which a vehicle enters as a monitoring area, and the image of the monitoring area. The process of identifying the person included in the above, accumulating the appearance points and disappearance points of the person, and learning the position of the object included in the surveillance area of the surveillance camera based on the accumulated results, and the behavior of the person. The process of determining the area and setting the risky behavior detection area for determining the risky behavior with respect to the person, the feature of the vehicle entering the platform is detected by image processing, and the detected feature is associated with the time information. The process of accumulating and collating with the operation information of the vehicle and reflecting it in the detection result of the characteristics of the vehicle and the image in which the dangerous behavior is recorded are associated with the occurrence position, the occurrence time and the warning level information of the dangerous behavior. It is provided with a step of recording the risky behavior and a step of outputting a display to call attention in the predetermined time zone when the appearance frequency of the dangerous behavior is equal to or higher than the predetermined time zone.

According to the present invention, when a platform on which a vehicle enters is monitored by image processing as a monitoring area, it is possible to realize a technique that realizes good detection accuracy and improved maintainability.

It is a block diagram of the monitoring system which concerns on embodiment. It is a figure which showed the appearance point and vanishing point of passengers detected by an image processing apparatus which concerns on embodiment. It is a figure which showed the flow line information of a passenger, a risky behavior detection area and a priority detection area which concerns on embodiment. It is a figure which showed the movement vector of the passenger which concerns on embodiment. It is a figure which showed the screen composition image of the priority detection area which concerns on embodiment. It is a figure which plotted and showed the thing with a high warning level among the detected dangerous behaviors which concern on embodiment. It is a figure which showed the recorded image with the detection frame which concerns on embodiment.

Next, an embodiment for carrying out the present invention (hereinafter, simply referred to as “embodiment”) will be specifically described with reference to the drawings. The outline of this embodiment is as follows. That is, the object shape / object position peculiar to the railway monitoring system such as station platforms and vehicles detected by image processing and the behavior of passengers (appearance point / vanishing point and dangerous behavior) are learned in association with each other. As a result, the dangerous behavior detection area is automatically set and the detection accuracy is improved. Hereinafter, a specific description will be given.

FIG. 1 is a configuration diagram of the monitoring system 101 of the present embodiment. The monitoring system 101 includes a home monitoring device 20, a data processing device 30, a terminal device 40, and a monitoring PC (service company) 16, which are connected by a network line such as LAN 6 or a public line 15 to form a railway home. To monitor. Further, the monitoring system 101 is network-connected to the NTP server 12 and the operation management server 17 (operation management system) that manages train operation, and appropriately acquires and uses desired information from those servers.

The home monitoring device 20 is a device mainly installed on a railway platform, and includes a plurality of surveillance cameras 1, a plurality of home monitors 2 for conductors, a sound collecting device 3, an image encoder 4, and a network switch 5. To be equipped. The number of the surveillance camera 1, the conductor home monitor 2, and the sound collecting device 3 is not particularly limited, and is appropriately set according to the size of the platform to be installed and the like.

The images of the surveillance camera 1 installed on the home are aggregated by the image encoder 4 via the home monitor 2 for the conductor. Similarly, the audio data acquired by the sound collector 3 is also aggregated in the image encoder 4. The image encoder 4 encodes the aggregated video and audio data and then distributes the aggregated video and audio data from the network switch 5 to the data processing device 30 (image processing device 8) via the LAN 6.

The data processing device 30 includes an image generation device 7, an image processing device 8, an audio processing device 9, a system management server 10, and a video recording device 11. Although different device configurations are shown here, all or a part of them may be integrally configured. For example, the image generation device 7 and the image processing device 8 may be provided as one because they perform similar processing as an image processing function.

The image processing device 8 accumulates the data acquired from the home monitoring device 20 and performs various processes. As one of such processes, the image processing device 8 automatically learns and registers the dangerous behavior detection area from the accumulated behaviors of passengers.

Further, the image processing device 8 cuts out the priority detection area from the image and sends it to the image generation device 7. Further, the image processing device 8 has a function of controlling the surveillance camera 1, and various camera parameters such as an image level and a gamma characteristic are set and controlled automatically or by user operation.

The image generation device 7 performs optimization processing on these images and feeds them back to the image processing device 8.

The image processing device 8 detects dangerous behavior of passengers based on the feedback from the image generation device 7, and sends the information to the system management server 10.

The image processing device 8 marks the information of the detection target, the dangerous behavior detection area, and the priority detection area on the image, and distributes the image to the image recording device 11. The video recording device 11 records and holds the delivered video.

The priority detection area is expected to differ depending on the vehicle type. Therefore, the image processing device 8 can improve the accuracy of the priority detection area (image cutout position) by using the timetable information acquired from the operation management server 17 and the time information acquired from the NTP server 12. Become.

The voice processing device 9 performs voice recognition based on the sounds of the home announcement, the horn, and the like acquired by the sound collecting device 3, and sends the recognition result information to the image processing device 8. The image processing device 8 utilizes the recognition result in the above-mentioned detection of dangerous behavior of passengers.

The system management server 10 distributes warning information to the client PC 13 of the terminal device 40 and the tablet terminal 14 carried by the station staff to call attention to the station staff and the like.

The monitoring PC 16 of the service company can confirm various detection accuracy of the image processing device 8 by periodically viewing the recorded video of the video recording device 11.

FIG. 2 is a diagram showing appearance points and vanishing points of passengers detected by the image processing device 8. The appearance point is indicated by "○" and the vanishing point is indicated by "×". FIG. 2A shows a home image A1 in which the detected passenger (hereinafter, “detected passenger”) A2 and the vehicle A5 that has entered the platform are included in the platform unit A3. A yellow line A4 is indicated by a broken line on the home portion A3. Further, it is shown that the vehicle number A8 is provided on the front surface of the vehicle A5, and the vehicle door A6 and the vehicle side light A7 are provided on the side surface.

FIG. 2B shows an appearance point / vanishing point plot image A9 at the time of boarding, and an appearance point A10 when a passenger gets on the vehicle A5 and a vanishing point A11 when the passenger gets in and disappears are plotted. FIG. 2C shows the appearance point / vanishing point plot image A12 at the time of getting off, and the appearance point A13 when the passenger gets off the vehicle A5 and the vanishing point A14 where the getting off passenger disappears from the image are plotted. There is.

The image processing device 8 detects a moving object based on background subtraction in the image captured by the surveillance camera 1, and determines that the image is a person (detection passenger A2) based on the shape and size. The point at which a person is first detected is set as the appearance point, and then the point at which the same person is continuously detected and disappears is managed as the vanishing point.

When getting on a train, the appearance point is near stairs, escalators, elevators, etc., and the vanishing point is often the vehicle door. When getting off the train, the vanishing point is the vehicle door, and the vanishing point is the escalator, elevator. In many cases, it is in the vicinity.

FIG. 3 shows the accumulated flow line information of passengers and the dangerous behavior detection area and the priority detection area generated by the image processing device.

FIG. 3A is a home image B1 to which a flow line (trajectory) B2 showing the movement of passengers is added. FIG. 3B is a generated image B3 generated by the image generator 7, which is a dangerous behavior detection area B4, a yellow line B5, a vehicle side dangerous behavior detection area B6, a vehicle door B7, a vehicle side light B8, and a vehicle number. B9 is shown.

The image processing device 8 accumulates information on the appearance point, vanishing point, and flow line of passengers, and is a risky behavior detection area for detecting dangerous behavior in an area where passengers entering and exiting the vehicle door move on the platform. Register as B4 (that is, the image processing target area). By excluding areas other than the dangerous behavior detection area B4 from the image processing target area for dangerous behavior detection, it is possible to suppress the influence of disturbances such as trains and sunlight on image processing (false positives, etc.). It becomes.

The image processing device 8 registers the position of the vehicle door B7 from the accumulated appearance points and vanishing points on the vehicle side. Further, the image processing device 8 detects the blinking of the vehicle side light when the vehicle door is opened and closed, and registers the position of the vehicle side light B8. Further, the image processing device 8 detects the vehicle number B9 at the head of the vehicle and registers the position of the vehicle number B9. The image processing device 8 can collate the difference in the position information depending on the vehicle type with the registered time information and timetable information, specify the vehicle type, and improve the accuracy of the position.

FIG. 4 is a diagram showing a movement vector of passengers. In the home image C1, as the movement vector of passengers, the movement vector of walking passengers (walking passenger movement vector C2) and the movement vector of passengers running outside the yellow line C5 (off-line traveler). The movement vector C3) and the movement vector of passengers running within the yellow line C5 (in-line traveler movement vector C4) are shown.

The image processing device 8 calculates the speed of the passengers heading for the vehicle door C6 from the movement distance of the person between the frames from the above-mentioned movement vector, and determines that the passengers having a certain speed or higher are dangerous behaviors (rush ride). ..

Further, when the voice processing device 9 notifies the voice information such as "the door will close soon" or "the departure melody", there is a concern that the door may be pinched. Therefore, the image processing device 8 raises the warning level. Perform processing.

The voice processing device 9 has reference data for voice information used for adjusting the warning level, compares the reference data with the acquired voice information, and determines that the warning level is the same. adjust.

As warning levels, for example, pedestrians at normal times are "low level", pedestrians at normal times are "medium level", pedestrians just before closing the door are "medium level", and pedestrians just before closing the door are "high level". The pedestrian just before the door is closed and the pedestrian inside or near the yellow line C5 is defined as the "highest level". By notifying the station staff of these warning level information, it is possible to inform the degree of danger and prevent accidents. When displaying the notification on the client PC 13 or the tablet terminal 14, it is desirable that the color of the target, the frame surrounding the target, etc. are different according to the warning level so that the warning level can be easily determined. ..

On the contrary, when the voice information immediately before the train entry such as "the train is coming soon" or "the entry melody" is notified, the image processing device 8 protrudes from the yellow line C5, and the warning level is given to the person who has fallen home. Determines to be "high level" and notifies the station staff (more specifically, the client PC 13, the tablet terminal 14, etc.). In addition to the above-mentioned voice information, train departure information and arrival information can also be performed by inputting a physical condition signal from the operation management server 17 into the monitoring system 101.

FIG. 5 is a diagram showing a screen composite image of the priority detection area. The priority detection area exclusion background image D5 and the extraction priority detection area image D6 are generated from the home image D1 before composition. Further, the composite image D7 is generated by synthesizing the priority detection area exclusion background image D5 and the extraction priority detection area image D6.

As shown in the figure, the pre-synthesis home image D1 includes a home portion D2, a vehicle side light D3, and a vehicle number D4, and is recognized as a priority detection area.

The image processing device 8 extracts the home unit D2, the vehicle side light D3, and the vehicle number D4, which are priority detection areas, and transmits them to the image generation device 7. At the time of transmission, the image processing device 8 also transmits the background image excluding the priority detection area (here, the home unit D2, the vehicle side light D3, and the vehicle number D4) to the image generation device 7.

The image generator 7 individually contrast-corrects each of the priority detection areas (here, the home portion D2, the vehicle side light D3, and the vehicle number D4) so as to obtain an optimum image without overexposure or underexposure. , Performs image correction processing such as image level correction.

The image generation device 8 synthesizes the image of the priority detection area after correction and the background image to generate one image (that is, the composite image D7) and feeds it back to the image processing device 8. The image processing device 8 can improve the detection accuracy of the image processing by performing image processing again based on the composite image D7 from the image generation device 7. That is, the priority detection area is subjected to image processing that facilitates image recognition.

FIG. 6 is a diagram plotting the detected dangerous behaviors having a high warning level. In the home image E1 of FIG. 6A, a detection point having a high warning level (high warning level detection point E2) is shown. FIG. 6B shows a graph (high warning level detection point accumulation graph E4) in which detection points having a high warning level are accumulated in the coordinate conversion home image E3 in which the home image is converted into plane coordinates.

The image processing device 8 converts the image range as shown in FIG. 6A into two-dimensional coordinates to obtain the coordinate-converted home image E3 shown in FIG. 6B, and further, the position information of the detection point having a high warning level. (Two-dimensional coordinate information and time information) are accumulated with the passage of time to obtain a high warning level detection point accumulation graph E4. This makes it possible to analyze the tendency of the location and time of dangerous behavior with a high warning level, and to notify the user of the monitoring system 101 of the location and time when the dangerous behavior is predicted to occur in the future.

Specifically, the image processing device 8 accumulates information on past dangerous behaviors at a predetermined place at a predetermined time or day of the week, and when the frequency exceeds a predetermined frequency, dangerous behaviors occur in that area during that time period. Then, it predicts that it will alert the observer. Any method may be used to call attention, but for example, on a monitoring monitor (conductor home monitor 2, tablet terminal 14, client PC 13, etc.), a predetermined mark or frame is displayed at a place where dangerous behavior is predicted. To do.

FIG. 7 shows a recorded image with a detection frame. The home image F1 shows the risky behavior detection area outside the yellow line F8, the risky behavior detection area frame F2 (for example, displayed in a green frame), and the risky behavior detection area frame inside the yellow line F8. Frame F3 (for example, displayed in red frame), car side light frame F4 (for example, displayed in yellow frame), vehicle number frame F5 (for example, displayed in black frame), normal passenger F6 (for example, displayed in black frame), Passenger F7 (for example, displayed in a red frame) detected as a dangerous behavior is shown. It is displayed in different colors according to the type of frame and warning level.

The image processing device 8 generates an image that is color-coded and frame-displayed in this way, and distributes the image to the image recording device 11. The video recording device 11 records the video together with the time information. Further, the video recording device 11 adds warning level information to the header portion of the recorded video data. As a result, it becomes efficient to search the video in which the dangerous behavior is recorded after the fact according to the level.

By periodically viewing the recorded video with the above frame from the monitoring PC 16 of the service company of the monitoring system 101, the normality of the object detected by the image processing device 8 can be confirmed, and the detection accuracy is measured. can do. When it is determined that the detection result by the image processing device 8 is incorrect due to false detection or the like, the learning process is corrected by inputting correct information to the image processing device 8.

Further, the service company sets a certain threshold value for the detection accuracy by operating the monitoring PC 16 or the like, and notifies the user of the monitoring system 101 of the start of operation when it is confirmed that the detection accuracy exceeds the threshold value. For example, for an important alarm such as a fallen person detection, the threshold value can be set according to the detection target by raising the threshold value of the detection accuracy.

As described above, according to the monitoring system 101 of the present embodiment, the object shape / object position peculiar to the monitoring system for railways such as station platforms and vehicles detected by image processing and the behavior of passengers (appearance point / disappearance point and dangerous behavior). By associating and learning about the above, the risky behavior detection area can be automatically set and the detection accuracy can be improved. Further, at the same time, the visibility can be improved by identifying the priority detection area (home unit, vehicle door, vehicle side light, vehicle number, etc.) on the image and performing image processing independently for each. Further, the service company of the monitoring PC 16 can remotely monitor the learning effect of the image processing device 8 to determine whether or not the operation can be started.

The features of the monitoring system 101 are summarized as follows.
The monitoring system 101 accurately identifies the positions of vehicle doors, stairs, escalators, etc. in the image by accumulating and learning information on appearance points and vanishing points from the flow lines of passengers detected by image processing.

In addition, the monitoring system 101 automatically determines the action area of the passenger from the flow line of the passenger, and automatically sets the risky behavior detection area for image processing the dangerous behavior of the passenger. It is also possible to reduce false alarms by limiting the detection area in the video and removing the parts that change on the video such as trains.

Further, the monitoring system 101 generates a background image by extracting moving objects such as passengers and trains that change with time and eliminating them. The features of the home (yellow line, home boundary) are determined by image processing from the background image.

In addition, the monitoring system 101 detects the characteristics (shape, color, door position, number of doors, vehicle side light position, vehicle number in front of the vehicle) of the vehicle entering the platform by image processing. The door position is determined from the accumulated information of the vanishing points on the vehicle side of passengers. The vehicle number is determined by extracting high-brightness character information from the camera image of the front of the vehicle. By collating the accumulated information with the time information and the timetable information, the detection accuracy will be improved over time.

In addition, the monitoring system 101 measures the speed from the amount of movement of passengers between image frames, and determines that a person at a certain speed or higher runs in and gets on (dangerous behavior). For example, by incorporating the information that is voice-recognized by the voice processing device 9 into the system for sounds immediately before the door is closed, such as "the door will close soon" and "departure melody", the rush ride detected after that is at the warning level. Is determined to be high and the station staff is notified. In addition to the above-mentioned voice information, the departure condition signal from the operation system side may be incorporated into the system as the information indicating that the door is about to close.

Further, the monitoring system 101 determines that the warning level of dangerous behavior (yellow line protrusion) is high when the yellow line protrusion of passengers detected by image processing and the horn ringing detected by voice processing are simultaneously detected. To do.

In addition, the monitoring system 101 detects dangerous behavior (yellow) after the sound processing device 9 detects sounds immediately before the train enters, such as "a train is coming soon" or "entrance melody". The line sticks out and the person who has fallen on the platform) judges that the warning level is high and notifies the station staff. As the information for notifying that the train is entering the train, in addition to the above-mentioned voice information, the entry condition signal from the operation system side may be incorporated into the system.

Further, the monitoring system 101 adds warning level information to the header portion of the recorded video data, so that the video in which the dangerous behavior is recorded is searched after the fact according to the level.

In addition, the monitoring system 101 accumulates dangerous behavior information (rushing in, yellow line sticking out, home fall) and detection time information (month, day, hour, minute, second), and analyzes the tendency of time and place to determine the future danger occurrence time. Predict the location of occurrence. Prediction can be made based on whether past risky behavior has exceeded a predetermined frequency.

In addition, the monitoring system 101 partially cuts out the image of the priority detection area (home part, vehicle door, vehicle side light, vehicle number) on the image, and converts each image into an optimum image without overexposure or underexposure. By combining these with the background image to generate one image, it is possible to improve the visibility and the detection accuracy.

In addition, the monitoring system 101 measures the image level of the partially cut out priority detection area (home part, vehicle door, vehicle side light, vehicle number) so that the optimum image without overexposure or underexposure is obtained. Various camera parameters such as video level and gamma characteristics are automatically set and controlled for the surveillance camera 1.

Further, the monitoring system 101 transmits the detection result information of the dangerous behavior detection area (home part, track part) and the priority detection area (home part, vehicle door, vehicle side light, vehicle number) and the dangerous behavior detection result information to the public line 15. By periodically transmitting to the service company of this system (more specifically, its monitoring PC16) via the system, the learning effect of image processing is periodically measured, and the service company judges whether the detection result is good or bad. By feeding back to this system, it is possible to further improve the learning effect. When the detection accuracy exceeds a certain threshold, the system operation start is determined. If the detection accuracy (that is, its threshold value) is increased, the system configuration and applications may become sophisticated and introduction may become difficult. However, by loosening the threshold value setting so that the detection accuracy is widened on the safe side, the monitoring system This will lead to the promotion of the introduction of 101.

The present invention has been described above based on the embodiments. This embodiment is an example, and it will be understood by those skilled in the art that various modifications are possible for the combination of each of these components, and that such modifications are also within the scope of the present invention. For example, in the present embodiment, a railway monitoring system is assumed, but the present invention is not limited to this, and can be applied to, for example, platform monitoring of a bus rapid transit (BRT).

1 Surveillance camera 2 Home monitor for conductor 3 Sound collector 4 Image encoder 5 Network switch 6 LAN
7 Image generator 8 Image processing device 9 Audio processing device 10 System management server 11 Video recording device 12 NTP server 13 Client PC
14 Tablet terminal 15 Public line 16 Monitoring PC
17 Operation management server 20 Home monitoring device 30 Data processing device 40 Terminal device 101 Monitoring system

Claims (5)

It is a surveillance system including a surveillance camera that photographs the platform on which the vehicle enters as a surveillance area, and a data processing device that performs image processing on the video captured by the surveillance camera to determine the warning level.
The data processing device is
A person included in the video of the surveillance area is identified, the appearance points and disappearance points of the person are accumulated, and based on the accumulated results, the position of the object included in the surveillance area of the surveillance camera is learned and the position of the object is learned. A monitoring system characterized in that a dangerous behavior detection area for determining a person's action area and determining a dangerous behavior with respect to the person is set. The data processing device detects the characteristics of the vehicle that has entered the platform by image processing, accumulates the detected characteristics in association with the time information, and collates with the operation information of the vehicle to detect the characteristics of the vehicle. The monitoring system according to claim 1, wherein the monitoring system is reflected in the above. The data processing device is
It has a function to acquire audio data output to the platform.
When it is determined that the movement of a person at a certain speed or higher is a dangerous behavior based on the amount of movement of the person between image frames in the dangerous behavior detection area on the platform, and the acquired voice data matches the predetermined reference data. The monitoring system according to claim 1 or 2, wherein the warning level is raised for a person who is recognized as a dangerous behavior after the voice data. The data processing device records an image in which the dangerous behavior is recorded in association with the occurrence position, occurrence time, and warning level information of the dangerous behavior.
The monitoring system according to any one of claims 1 to 3, wherein when the frequency of appearance of the dangerous behavior is equal to or higher than a predetermined time zone, a display output calling attention is performed in the predetermined time zone. This is a monitoring method that performs data processing to determine the warning level by performing image processing on the video captured by the surveillance camera that shoots the platform on which the vehicle enters as the monitoring area.
A process of identifying a person included in the video of the surveillance area, accumulating appearance points and vanishing points of the person, and learning the position of an object included in the surveillance area of the surveillance camera based on the accumulated results. ,
The process of determining the action area of the person and setting the risky behavior detection area for determining the dangerous behavior of the person, and
A process of detecting the characteristics of the vehicle that has entered the platform by image processing, accumulating the detected characteristics in association with time information, collating with the operation information of the vehicle, and reflecting the characteristics in the detection result of the vehicle.
A process of recording a video in which the dangerous behavior is recorded in association with the occurrence position, occurrence time, and warning level information of the dangerous behavior, and
A step of performing a display output to call attention in the predetermined time zone when the appearance frequency of the dangerous behavior is equal to or higher than the predetermined time zone.
A monitoring method characterized by providing.

Images