JP6587268B1 - Platform risk determination program and system - Google Patents

Abstract

[PROBLEMS] To detect in advance the degree of danger due to contact with a train and prevent an accident. In a platform risk determination program for determining a risk in a platform, reference image information photographed in the platform, and for reference of a train to the platform at the time of capturing the reference image information An association level acquisition step for acquiring in advance three or more levels of association between the combination of the approach information and the risk level in the platform for the combination, and when newly determining the risk level on the platform, The information acquisition step refers to the information acquisition step of acquiring image information by capturing an image, and acquiring the approach information of the train to the platform at the time of shooting, and the association degree acquired in the association degree acquisition step, and the information acquisition step Image information acquired via the train approach Based on the distribution, to determine the risk of the platform. [Selection] Figure 3

Description

  The present invention relates to a platform risk determination program and system for determining the risk in a station platform.

  Conventionally, accidents due to contact with trains on station platforms have become a problem. Since there are many routes where home doors have not been installed, it is necessary to detect in advance the risk of contact with a train on the station platform and prevent accidents. It is necessary to perform such a risk automatically and with high accuracy.

JP 2017-91008 A

  In the technology disclosed in Patent Document 1 described above, it is described that the number of people staying in the station premises is estimated by artificial intelligence, but there is no description about determining the risk level in the station premises using artificial intelligence. .

  Therefore, the present invention has been devised in view of the above-mentioned problems, and its purpose is to detect in advance the degree of danger due to contact with a train on the station platform and prevent accidents in advance. Therefore, it is an object of the present invention to provide a platform risk determination program and system for automatically determining the risk in a station platform using artificial intelligence.

The present invention relates to a platform risk determination program for determining a risk in a platform of a station, for reference image information photographed in the platform, and reference for climate and weather at the time of photographing the reference image information . An association level acquisition step of acquiring in advance three or more levels of association between the combination of weather information and the level of danger in the platform for the combination, and when newly determining the level of risk in the platform, The information acquisition step refers to the information acquisition step of acquiring the weather information related to the climate and the weather at the time of shooting, and the association degree acquired in the association degree acquisition step. based on the image information and the weather information acquired through, A platform risk determination program characterized by executing the determination step of determining the risk of the serial platform computer.

The present invention relates to a platform risk determination system for determining a risk in a platform of a station, for reference image information photographed in the platform, and reference for climate and weather at the time of photographing the reference image information . An association level acquisition means for acquiring in advance three or more levels of association between the combination of the weather information and the risk level in the platform for the combination, and when newly determining the risk level in the platform, Image information is acquired by taking a picture of the image, and information acquisition means for acquiring weather information related to the climate and weather at the time of shooting is referred to, and the association degree acquired by the association degree acquisition means, and the information acquisition is performed. based on the image information obtained through the means and weather information, said platform A platform risk determination system characterized in that it comprises a determining means for determining the risk of.

  In order to detect in advance the risk of contact with a train on the station platform and prevent accidents, the risk in the station platform can be automatically determined using artificial intelligence.

It is a block diagram which shows the whole structure of the platform risk classification system by which the platform risk determination program to which this invention is applied is mounted. It is a figure which shows the specific structural example of a discrimination device. It is a figure for demonstrating operation | movement in the platform risk determination program to which this invention is applied. It is a figure which shows the example which set the 3 or more steps correlation of the combination with reference home information, and the risk in the platform with respect to the said combination. Furthermore, it is a figure which shows the example which set the 3 or more step correlation of the combination with reference arrangement | positioning information, and the risk in the platform with respect to the said combination. Furthermore, it is a figure which shows the example which set the 3 or more steps correlation of the combination with reference time slot | zone information, and the risk in the platform with respect to the said combination. Furthermore, it is a figure which shows the example which set the 3 or more steps correlation of the combination with reference passenger flow line information, and the danger level in the platform with respect to the said combination.

  Hereinafter, a platform risk determination program to which the present invention is applied will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram showing an overall configuration of a platform risk determination system 1 in which a platform risk determination program to which the present invention is applied is installed. The platform risk determination system 1 includes an information acquisition unit 9, a determination device 2 connected to the information acquisition unit 9, and a database 3 connected to the determination device 2.

  The information acquisition unit 9 is a device for a person who uses this system to input various commands and information, and specifically includes a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device that can detect sound such as a microphone and convert it into text information. The information acquisition unit 9 may be configured as an imaging device that can capture an image such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper medium document. Moreover, the information acquisition part 9 may be integrated with the discrimination | determination apparatus 2 mentioned later. The information acquisition unit 9 outputs the detected information to the determination device 2.

  The database 3 stores information on the danger level in the platform, such as accidents that have occurred on the platform of the station before, or cases that did not lead to an accident but had a high risk level. The database 3 includes reference image information previously captured by a camera that actually constitutes the information acquisition unit 9, reference reference information of a train to the platform at the time of capturing the reference image information, and a reference home regarding the platform structure. By analyzing the structural information, the reference arrangement information regarding the arrangement situation of station staff on the platform, the congestion situation of the time zone at the time of shooting of the reference image information, the reference time zone information indicating the shooting environment, and the reference image information Reference passenger flow line information and the like from which flow lines are extracted are stored.

  The discriminating device 2 is composed of electronic devices such as a personal computer (PC), for example. In addition to the PC, the discriminating device 2 can be embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, and a wearable terminal. It may be made. The user can determine the risk level of the platform by obtaining a search solution by the determination device 2.

  FIG. 2 shows a specific configuration example of the discrimination device 2. The discrimination device 2 performs wired communication or wireless communication with a control unit 24 for controlling the discrimination device 2 as a whole, and an operation unit 25 for inputting various control commands via operation buttons, a keyboard, and the like. A communication unit 26 for making a determination, a determination unit 27 for making various determinations, and a storage unit 28 for storing a program for performing a search to be executed, represented by a hard disk or the like, are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected to a display unit 23 as a monitor for actually displaying information.

  The control unit 24 is a so-called central control unit for controlling each component mounted in the determination device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 in accordance with an operation via the operation unit 25.

  The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input from the user, the operation unit 25 notifies the control unit 24 of this. Upon receiving this notification, the control unit 24 executes a desired processing operation in cooperation with each component including the determination unit 27. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

  The determination unit 27 is responsible for various determinations related to the risk level of the platform. The determination unit 27 reads various information stored in the storage unit 28 as necessary information and various information stored in the database 3 when executing the estimation operation. This determination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

  The display unit 23 includes a graphic controller that creates a display image based on control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD).

  When the storage unit 28 is composed of a hard disk, based on the control by the control unit 24, predetermined information is written to each address and is read out as necessary. The storage unit 28 stores a program for executing the present invention. This program is read by the control unit 24 and executed.

  The operation in the platform risk determination system 1 having the above-described configuration will be described.

  In the platform risk determination system 1, for example, as shown in FIG. 3, it is assumed that a combination of reference image information and reference approach information is formed. Reference image information is an image of various parts of the platform taken by a camera installed on the platform, for example, an image of a platform where passengers are sparse, or an image of a person running on a crowded platform There are various things such as images that are crowded to a level where passengers are likely to fall from the platform.

  In the example of FIG. 3, for example, the reference image information includes reference image information P11 to P13 obtained by photographing the platform for each place or each time series with a camera installed on the platform, and reference train information as reference approach information. As the time when the vehicle is approaching the platform, it is assumed that “30 seconds after the 7th home”, “15 seconds after the 5th home”, etc.

  As input data, such reference image information and reference approach information are arranged side by side. The intermediate node shown in FIG. 3 is a combination of the reference image information as the input data and the reference approach information. Each intermediate node is further connected to an output. In this output, the risk in the platform as an output solution is displayed as a percentage.

Each combination (intermediate node) of the reference image information and the reference approach information is associated with each other through three or more degrees of association with the risk in the platform as the output solution. The reference image information and the reference approach information are arranged on the left side through the association degree, and the risk levels in the respective platforms are arranged on the right side through the association degree. The degree of association indicates the degree of risk and the degree of relevance of the reference image information and the reference approach information arranged on the left side. In other words, the degree of association is an index indicating to which risk level each reference image information and reference approach information are likely to be linked, and is most determined from the reference image information and the reference approach information. It shows the accuracy in selecting a certain risk level. In the example of FIG. 3, w13 to w22 are shown as the association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1 below. The closer to 10 points, the higher the degree of relevance between each combination as an intermediate node and the risk level in the platform as an output. On the contrary, the closer to one point, the lower the degree of association between each combination as an intermediate node and the degree of danger in the platform as an output.

The discriminating apparatus 2 obtains in advance three or more levels of association w13 to w22 shown in FIG. In other words, the discriminating device 2 accumulates reference image information, reference approach information, and data indicating how much the risk level is in that case, and analyzes these in determining the actual risk level. By analyzing, the relevance shown in FIG. 3 is created.
For example, it is assumed that the reference image information P11 is an image in a state where passengers are staying in the platform at rush hour. If the reference approach information at the time of image capture is that the train arrives at “No. 1 home after 45 seconds”, whether or not an accident occurred in the previous data, and an accident occurred even if it did not happen It is extracted whether or not the degree of danger is not strange. These data may be extracted from past accident data stored at a railway company or each station, or from data of a scene that is near. The digitization of the risk level may be obtained by visualizing the reference image information by a plurality of people and counting questionnaire surveys on the risk level.

  This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P11 and “45 seconds after the first home”, whether or not an accident actually occurred or was there a high risk that the accident did not occur? Analyzes whether or not from past data. The higher the number of cases in which an accident has occurred, the higher the degree of association that leads to high-risk output, and the lower the number of cases in which an accident has occurred, the higher the degree of association that leads to low-risk output. For example, in the example of the intermediate node 61a, the output is linked to an output of 90% risk and 30% risk. However, since the risk is extremely high from the previous case, w13 linkage that leads to 90% risk. The degree of association of w14, which leads to a degree of risk of 30%, is set to 2 points.

  Further, the association degree shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned relevance. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

  In the example of the association degree shown in FIG. 3, the node 61 b is a node having a combination of the reference approach information “2 minutes after the third home” with respect to the reference image information P <b> 11 and has an association degree of 60% risk. Is w15, and the relevance of 0% risk is w16. The node 61c is a node having a combination of reference approach information “30 seconds after the 7th home” and “15 seconds after the 5th home” with respect to the reference image information P12. Is w17, and the degree of association of the risk 70% is w18.

  Such association is the learned data in terms of artificial intelligence. After creating such learned data, when the risk level is actually newly determined on the platform, the risk level is determined using the learned data described above. In such a case, the image information is newly acquired and the approach information is acquired.

  The newly acquired image information is taken by the camera by the information acquisition unit 9 described above. This photographing is the same as the platform photographed for obtaining the reference image information described above. Further, the shooting conditions are not required until the shooting conditions (shooting angle, angle of view, resolution) for obtaining the above-described reference image information are all the same.

  The approach information may be acquired directly from train operation data managed by a railway company. The actual number of minutes after which a train arrives on a certain platform is based on the current time, train schedule, delay information, climate, weather, and the like. From this information, it is calculated how many minutes the train will actually arrive on the platform. Further, the approach information may be acquired based on whether or not the train has passed the 50m point in front of the platform. In other words, if the sensor detects that the train has passed 50m before the platform, it determines that the train is approaching. If not, it determines that the train is not approaching yet. This may be included in the approach information.

  Based on the image information newly acquired in this way and the approach information of the train, the degree of risk at the time when the image information and the approach information are actually acquired is obtained. In such a case, the association degree shown in FIG. 3 (Table 1) acquired in advance is referred to. For example, if the newly acquired image information is the same as or similar to P12, and the approach information obtained at the time of acquisition is “15 seconds after home 5”, The node 61d is associated with a degree of risk, and the node 61d is associated with a “risk degree 60%” with w19 and a “risk degree 70%” with an association degree w20. In such a case, “risk level 60%” having the highest relevance is selected as the optimal solution. However, it is not essential to select a solution with the highest degree of association as an optimal solution, and “risk degree 70%” where the association itself is recognized although the association degree is low may be selected as the optimum solution. In addition to this, it is of course possible to select an output solution that is not connected to an arrow, and any other solution may be selected as long as it is based on the degree of association.

  Table 2 below shows examples of the association degrees w1 to w12 extending from the input.

  The intermediate node 61 may be selected based on the association degrees w1 to w12 extending from this input. That is, the weighting in the selection of the intermediate node 61 may be increased as the association degrees w1 to w12 are increased. However, the association degrees w1 to w12 may all be the same value, and all the weights in the selection of the intermediate node 61 may be the same.

  In FIG. 4, in addition to the reference image information and the reference approach information described above, a combination of reference home information and a degree of association of three or more levels of the risk in the platform with respect to the combination is set. An example is shown.

  The reference home information is information related to the platform structure. The platform structure includes all information and data related to the platform structure, such as the width and size of the platform, the shape, the arrangement of stairs, the length of the gap between the train and the platform, the number of people accommodated, and the height. Such reference home information utilizes information stored in advance in a server or the like for each electric railway company or for each station.

  In this case, as shown in FIG. 4, the association degree is expressed as a set of combinations of the reference image information, the reference approach information, and the reference home information as nodes 61a to 61e of the intermediate nodes as described above. Will be.

  For example, in FIG. 4, the node 61c has the relevance w3 for the reference image information P12, the relevance w7 for the reference approach information “30 seconds after the 7th home”, and “platform structure” as the reference home information. “β” is associated with the association degree w11. Similarly, in the node 61e, the reference image information P13 has the association degree w5, the reference approach information “30 seconds after the 7th home” has the association degree w8, and the reference platform information “platform structure α” is the association. It is related at degree w10.

  Similarly, when such an association degree is set, based on newly acquired image information, train approach information, and home specifying information for specifying the platform, the image information is actually newly added. And the degree of danger at the time when the approach information is acquired. The home specifying information here is used to specify the platform for which the risk level is actually obtained is what number of the station at which station, and is linked to the reference home information described above. In other words, if the platform is known as the number of platform of what station, what kind of platform structure can be specified, and the platform is linked to the reference home information.

  In obtaining this risk level, the association degree shown in FIG. 4 acquired in advance is referred to. For example, if the acquired image is the same as or similar to the reference image information P12 and the approach information “30 seconds after the 7th home” and the home identification information can identify the platform structure β, The node 61c is associated with the combination, and the node 61c is associated with the association degree w17 with a risk level of 30% and with the association degree w18. As a result of such association, the risk level at the time when the image information and the approach information are actually newly acquired is obtained based on w17 and w18.

  In FIG. 5, in addition to the above-described reference image information and reference approach information, a combination of reference arrangement information and a degree of association of three or more levels of the risk in the platform for the combination are set. An example is shown.

  The reference arrangement information is information related to the arrangement status of station staff on the platform. The reference arrangement information may be acquired from, for example, data of a schedule table regarding the arrangement status of station staff managed for each electric railway company or each station, or time shift data. Further, the arrangement information for reference may be acquired by sequentially acquiring the image and the position information of the station staff through the camera installed on the platform and extracting the arrangement state.

  In such a case, as shown in FIG. 5, the association degree is expressed as a set of combinations of the reference image information, the reference approach information, and the reference arrangement information as nodes 61a to 61e of the intermediate nodes as described above. Will be.

  For example, in FIG. 5, the node 61c indicates that the reference image information P12 has an association degree w3 and the reference approach information “30 seconds after the 7th home” has an association degree w7. "Form Q" is associated with the association degree w11. Similarly, in the node 61e, the reference image information P13 has the association degree w5, the reference approach information “30 seconds after the 7th home” has the association degree w8, and the “station staff arrangement form P” as the reference arrangement information is They are linked with a link level of w10.

  Similarly, when such association is set, the newly acquired image information, the train approach information, and the station staff arrangement status at the time of acquiring the image information and the approach information are further acquired. To do. You may make it acquire the arrangement | positioning condition of the station staff at the said time from the data of a schedule table | surface, or time shift data. In such a case, the station staff arrangement status is acquired by comparing the time axis in the time shift data with the current time. Further, the current arrangement state may be sequentially extracted from the station staff image and position information through a camera installed on the platform.

  In obtaining this risk level, the association degree shown in FIG. 5 acquired in advance is referred to. For example, if the acquired image is the same as or similar to the reference image information P12, the approach information is “30 seconds after the 7th home”, and the station staff arrangement form is the arrangement form Q, the combination is a node 61c is associated with this node 61c, and the degree of risk 30% is associated with the association degree w17, and the degree of risk 70% is associated with the association degree w18. As a result of such association, the risk level at the time when the image information and the approach information are actually newly acquired is obtained based on w17 and w18.

  In FIG. 6, in addition to the reference image information and the reference approach information described above, a combination of reference time zone information and a degree of relevance of three or more levels of the risk in the platform for the combination are set. An example is shown.

  The reference time zone information indicates the congestion situation and the shooting environment in the platform in a certain time zone (for example, it may be a temporary point or a time span from what hour to what hour to what hour). It is. The congestion situation within the platform varies depending on the time of day. By observing this congestion situation in time series, the congestion situation for each time zone can be acquired. The congestion state may be digitized by measuring the number of passengers per unit area, density, and the like through image analysis, for example. The shooting environment means any factor that affects the shooting with the camera. For example, if the platform is outdoors, the various factors that affect the camera's image capture, such as brightness and sunlight direction, change depending on the time of day, but these data can be measured in time series. A shooting environment for each time zone can be obtained.

  In such a case, as shown in FIG. 6, the association degree is obtained by combining a set of combinations of reference image information, reference approach information, and reference time zone information as intermediate nodes 61 a to 61 e as described above. It will be expressed.

  For example, in FIG. 6, the node 61c has the relevance degree w3 for the reference image information P12, the relevance degree w7 for the reference approach information “30 seconds after the 7th home”, and the congestion status T as the reference time zone information. (For example, the vicinity of the entrance / exit of the second vehicle on the platform is between 10 o'clock and 10:10 and 5 people per area) and the shooting environment U (for example, sunlight at 10 o'clock to 10:10) In the direction of southeast, etc.) Similarly, in the node 61e, the reference image information P13 has the relevance w5, the reference approach information “30 seconds after the 7th home” has the relevance w8, and the congestion status T + the shooting environment S as the reference time zone information is They are linked with a link level of w10.

  Similarly, when such association is set, the newly acquired image information, the train approach information, the congestion situation and the shooting environment at the time of the acquisition of the image information and the approach information are also determined. The time zone information shown is further acquired. This time zone information is linked to the reference time zone information. The time zone information acquisition method is the same as that for the reference time zone information.

  In obtaining this risk level, the association level shown in FIG. 6 acquired in advance is referred to. For example, when the acquired image is the same as or similar to the reference image information P12, the access information is “30 seconds after the 7th home”, and the current time zone information is the congestion situation T and the shooting environment U, The node 61c is associated with the combination, and the node 61c is associated with the association degree w17 having a risk level of 30% and the association degree w18. As a result of such association, the risk level at the time when the image information and the approach information are actually newly acquired is obtained based on w17 and w18.

  In FIG. 7, in addition to the reference image information and the reference approach information described above, a combination of reference passenger flow line information and a degree of association of three or more levels of the risk in the platform for the combination is set. An example is shown.

  The passenger flow line information for reference is obtained by extracting the flow lines of passengers in the platform in a certain time zone (for example, it may be a temporary point or a time width from what hour to what hour to what minute). Is. In extracting the reference passenger flow line information, the customer's flow line may be detected by a well-known means by performing image analysis on the above-described reference image information. The pattern of the customer's flow line is stored in a pattern by a well-known means on the image through a vector or a diagram.

  In such a case, as shown in FIG. 7, the association degree is obtained by combining nodes 61a to 61e of the intermediate nodes in the same way as described above with a set of combinations of the reference image information, the reference approach information, and the reference passenger flow line information. Will be expressed as

  For example, in FIG. 7, the node 61c indicates that the reference image information P12 has the association degree w3, the reference approach information “30 seconds after the 7th home” has the association degree w7, and the passenger traffic line information for reference The flow line W is associated with the association degree w11. Similarly, in the node 61e, the reference image information P13 has the relevance w5, the reference approach information “30 seconds after the 7th home” has the relevance w8, and the passenger flow line V as the reference passenger flow line information is They are linked with a link level of w10.

  Similarly, when such a degree of association is set, the newly acquired image information, the train approach information, and the flow pattern of the passenger at the time when the image information and the approach information are acquired are further acquired. . The extraction of the pattern of the passenger flow line is the same as the extraction method of the reference passenger flow line information.

  In obtaining this risk level, the association degree shown in FIG. 7 acquired in advance is referred to. For example, if the acquired image is the same as or similar to the reference image information P12, the acquired approach information is “30 seconds after the 7th home”, and the current flow line of the passenger is the flow line W, The node 61c is associated with the combination, and the node 61c is associated with the association degree w17 with a risk level of 30% and with the association degree w18. As a result of such association, the risk level at the time when the image information and the approach information are actually newly acquired is obtained based on w17 and w18.

In the above-described association degree, in addition to the reference image information and the reference approach information, any combination of the reference home information, the reference arrangement information, the reference time zone information, and the reference passenger flow line information is obtained. Although the case where it is formed has been described as an example, it is not limited to this. In addition to the reference image information and the reference approach information, the association degree is associated with one or more combinations of the reference home information, the reference arrangement information, the reference time zone information, and the reference passenger flow line information. May be used.
Note that determination may be made in consideration of audio information in addition to the reference image information. The sound information is sound detected by a microphone or the like. This voice information may be detected in the same manner as when the reference image is acquired and may be associated with the association degree as an independent input parameter as the reference voice information. That is, in addition to the reference image information and the reference approach information, the association degree may be associated with a combination of the reference audio information. In such a case, voice information is acquired with a microphone in the determination of the new risk level, and the risk level is determined with reference to the association level.

  In the above-mentioned relevance, the relevance is expressed by a 10-level evaluation, but it is not limited to this, and it may be expressed by a relevance of 3 or more levels. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include two levels, that is, whether or not they are associated with each other, and those expressed with either 1 or 0.

  In addition, although the danger level demonstrated taking the case where it described by the percentage of 0 to 100% as an example, it is not limited to this. This risk level may be expressed in two stages, for example, “high risk” and “low risk”. In this case, when forming the relevance, the combination of the reference image information and the reference approach information, etc. is classified as “high risk” or “danger” when analyzing the judgment example of whether the risk is high or not. It will be analyzed and discriminated in association with the result of “low performance”. Of course, these operations may be replaced by artificial intelligence.

  According to the present invention having the above-described configuration, it is possible to easily determine the degree of risk in the platform with little effort without requiring special skill. Further, according to the present invention, it is possible to determine the degree of risk in this platform with higher accuracy than humans can perform. Furthermore, by configuring the above-mentioned association degree with artificial intelligence (such as a neural network), it is possible to further improve the discrimination accuracy by learning this.

  In addition, the present invention is characterized in that an optimum physical property and a generation mechanism are searched through the association degree set in three or more stages. The degree of association can be described by a numerical value of, for example, 0 to 100% in addition to the above five levels, but is not limited to this, and any level can be described as long as it can be described by a numerical value of three or more levels. It may be configured.

  By searching for the most probable risk based on the degree of association represented by these three or more levels, it is possible to consider the association in a situation where there are multiple possible candidates for the risk on the platform. It is also possible to search and display in descending order. If it is possible to display to the user in the order of the degree of association in this way, it is possible to preferentially display a more certain danger level, and it is possible to call attention due to an increase in the risk level.

  In particular, when the degree of danger is high, processing actions such as alerting passengers and station staff through voice, etc., or notifying the train that enters the platform that the danger is high, This can be done in advance, and passenger safety can be maintained. In addition, according to the present invention, since the detection accuracy of the danger level is high, it is only necessary to perform the operation of stopping the stop train only in the case where it is really necessary without stopping the train unnecessarily, and thus adversely affecting smooth traffic. It can also be prevented.

  In addition to this, according to the present invention, it is possible to make a determination without overlooking a discrimination result of an extremely low output such as an association degree of 1%. Note that even if the result of discrimination is extremely low, it is connected as a small sign and may be useful as the discrimination result once every tens or hundreds of times. Can be aroused.

  Furthermore, according to the present invention, there is an advantage that a search policy can be determined by a method of setting a threshold value by performing a search based on such three or more levels of association. If the threshold value is lowered, it is possible to pick up without omission even if the above-mentioned association degree is 1%, but there is a low possibility that a more appropriate discrimination result can be suitably detected, and a lot of noise may be picked up. is there. On the other hand, if the threshold value is increased, it is likely that the optimum risk level can be detected with a high probability. However, although the degree of association is usually low and it is slewed, it is suitable to appear once every tens or hundreds of times. Sometimes the solution is overlooked. It is possible to decide which to place importance on the basis of the idea on the user side and the system side, but it is possible to increase the degree of freedom in selecting points to place such emphasis.

  Furthermore, in the present invention, the association degree described above may be updated. This update may reflect information provided via a public communication network such as the Internet. In addition, when new knowledge is discovered about the relationship between input parameters and output solutions (risk levels) based on camera images uniquely captured by electric railway companies and stations, and access information uniquely acquired Depending on the knowledge, the association degree is increased or decreased.

  That is, this update is equivalent to learning in terms of artificial intelligence. It is a learning act because new data is acquired and reflected in the learned data.

  In addition, the process of first creating a learned model and the above-described updating may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning a data set of input data and output data, information corresponding to input data (reference image information, reference approach information, reference home information, reference arrangement) Information, reference time zone information, reference passenger flow line information, etc.) may be read and learned, and the degree of association associated with the output data may be self-generated therefrom.

  In addition to information based on information that can be obtained from the public communication network, this relevance update is artificially performed by the system side or user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts. Alternatively, it may be updated automatically. Artificial intelligence may be used in these update processes.

DESCRIPTION OF SYMBOLS 1 Platform danger level discrimination system 2 Discriminating device 21 Internal bus 23 Display part 24 Control part 25 Operation part 26 Communication part 27 Estimation part 28 Storage part 61 Node

Claims (13)

In the platform danger level determination program for determining the risk level in the station platform,
Three or more levels of association between reference image information taken in the platform, reference weather information related to climate and weather at the time of shooting the reference image information, and risk in the platform for the combination An association degree acquisition step for acquiring in advance,
When newly determining the degree of risk in the platform, the information acquisition step of acquiring image information by newly capturing an image in the platform, and acquiring weather information related to the climate and weather at the time of capturing,
Referencing the association degree acquired in the association degree acquisition step, and causing the computer to execute a determination step for determining a risk level in the platform based on the image information and the weather information acquired through the information acquisition step. A platform risk judgment program characterized by In the platform danger level determination program for determining the risk level in the station platform,
Reference image information taken in the platform, approach information for reference of the train to the platform at the time of shooting the reference image information , width, size, shape, arrangement of stairs, train and home of the platform Acquiring the degree of association by acquiring in advance three or more levels of association between the combination of the reference home structure information defined by one or more of the gap length and the number of persons accommodated, and the risk in the platform for the combination Steps,
When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, train access information to the platform at the time of the capturing is acquired , and the platform is An information acquisition step for accepting input of home identification information for identification ;
Based on the image information acquired through the information acquisition step, the approach information of the train, and the reference home structure information linked to the home identification information , referring to the association degree acquired in the association degree acquisition step. A platform risk determination program, characterized by causing a computer to execute a determination step for determining a risk level in a platform. In the platform danger level determination program for determining the risk level in the station platform,
From the reference image information photographed in the platform, the reference information of the train reference to the platform at the time of photographing the reference image information, and the schedule table data or the time shift data relating to the arrangement situation of the station staff on the platform 3 of the combination of the reference arrangement information obtained by extracting the station staff's arrangement status by sequentially acquiring the station crew's image and the position information through acquisition or the camera installed on the platform, and the risk in the platform for the combination An association degree obtaining step for obtaining an association degree at a stage or more in advance;
When a new risk level is determined on the platform, image information is acquired by newly capturing an image in the platform, train access information to the platform at the time of the capturing is acquired, and the time of capturing is acquired. The station staff's placement status on the platform is obtained from the schedule table data or time shift data on the station staff placement status by comparing these time axes with the current time, or through the camera installed on the platform. An information acquisition step for sequentially acquiring images and position information ;
Referring to the association degree acquired in the association degree acquisition step, the risk level in the platform is determined based on the image information acquired through the information acquisition step, train approach information, and station staff arrangement status. A platform risk determination program characterized by causing a computer to execute a determination step. In the platform danger level determination program for determining the risk level in the station platform,
The reference image information captured in the platform, the reference access information of the train to the platform at the time of capturing the reference image information, and the time zone shooting environment at the time of capturing the reference image information are shown. An association degree acquisition step of acquiring in advance three or more degrees of association between the combination with the reference time zone information and the risk in the platform for the combination ;
When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, train approach information to the platform at the time of the capturing is acquired , and further, the platform An information acquisition step for acquiring time zone information indicating a shooting environment in the time zone at the time of shooting ,
Discrimination that refers to the association degree acquired in the association degree acquisition step and determines the risk level in the platform based on the image information acquired through the information acquisition step, train approach information, and time zone information A platform risk determination program characterized by causing a computer to execute steps. In the platform danger level determination program for determining the risk level in the station platform,
Combination of reference image information captured in the platform, reference information of train reference to the platform at the time of capturing the reference image information, and reference audio information detected in the platform, and the combination An association degree obtaining step for obtaining in advance three or more degrees of association with the risk in the platform for
When a new risk level is determined on the platform, image information is acquired by newly capturing an image on the platform, and train approach information to the platform at the time of capturing is detected on the platform. An information acquisition step for acquiring audio information ;
A determination step for determining the degree of risk in the platform based on the image information acquired through the information acquisition step, the train approach information, and the voice information with reference to the association level acquired in the association level acquisition step. A platform risk determination program characterized by causing a computer to execute. In the association degree acquisition step, a combination of reference passenger flow line information obtained by extracting the passenger's flow line and a degree of association of three or more stages in the platform with respect to the combination is acquired in advance.
In the information acquisition step, when newly determining the degree of risk in the platform, the passenger flow line information obtained by extracting the passenger flow line is further acquired,
The platform according to any one of claims 1 to 5, wherein in the determination step, a risk level in the platform is determined based on passenger flow line information acquired through the information acquisition step. Risk classification program.   In the association degree acquisition step, the association degree of the three or more stages configured by the nodes of the neural network in artificial intelligence is acquired in advance.
The platform risk determination program according to any one of claims 1 to 6. In the platform risk classification system for determining the risk in the station platform,
Three or more levels of association between reference image information taken in the platform, reference weather information related to climate and weather at the time of shooting the reference image information, and risk in the platform for the combination An association degree acquisition means for acquiring in advance,
When newly determining the degree of risk in the platform, information acquisition means for acquiring image information by newly capturing an image in the platform, and acquiring weather information on the climate and weather at the time of capturing,
A determining unit that refers to the association degree obtained by the association degree obtaining unit and discriminates the degree of risk in the platform based on the image information and the weather information obtained through the information obtaining unit. A platform risk classification system. In the platform risk classification system for determining the risk in the station platform,
  Reference image information taken in the platform, approach information for reference of the train to the platform at the time of shooting the reference image information, width, size, shape, arrangement of stairs, train and home of the platform Acquiring the degree of association by acquiring in advance three or more levels of association between the combination of the reference home structure information defined by one or more of the gap length and the number of persons accommodated, and the risk in the platform for the combination Means,
  When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, train access information to the platform at the time of the capturing is acquired, and the platform is Information acquisition means for accepting input of home identification information for identification;
  With reference to the association degree acquired by the association degree acquisition means, based on the image information acquired through the information acquisition means, train approach information, and reference home structure information linked to the home identification information, A discriminating means for discriminating the degree of danger in the platform;
  A platform risk classification system characterized by In the platform risk classification system for determining the risk in the station platform,
  From the reference image information photographed in the platform, the reference information of the train reference to the platform at the time of photographing the reference image information, and the schedule table data or the time shift data relating to the arrangement situation of the station staff on the platform 3 of the combination of the reference arrangement information obtained by extracting the station staff's arrangement status by sequentially acquiring the station crew's image and the position information through acquisition or the camera installed on the platform, and the risk in the platform for the combination An association degree acquisition means for acquiring an association degree at a stage or more in advance;
  When a new risk level is determined on the platform, image information is acquired by newly capturing an image in the platform, train access information to the platform at the time of the capturing is acquired, and the time of capturing is acquired. The station staff's placement status on the platform is obtained from the schedule table data or time shift data on the station staff placement status by comparing these time axes with the current time, or through the camera installed on the platform. Information acquisition means for sequentially acquiring images and position information;
  Referring to the association degree acquired by the association degree acquisition means, the risk level in the platform is determined based on the image information acquired through the information acquisition means, train approach information, and station staff arrangement status A discriminating means to perform
  A platform risk classification system characterized by In the platform risk classification system for determining the risk in the station platform,
  From the reference image information photographed in the platform, the reference information of the train reference to the platform at the time of photographing the reference image information, and the schedule table data or the time shift data relating to the arrangement situation of the station staff on the platform 3 of the combination of the reference arrangement information obtained by extracting the station staff's arrangement status by sequentially acquiring the station crew's image and the position information through acquisition or the camera installed on the platform, and the risk in the platform for the combination An association degree acquisition means for acquiring an association degree at a stage or more in advance;
  When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, train approach information to the platform at the time of the capturing is acquired, and the capturing is further performed. The station staff's placement status on the platform at the time is obtained from the schedule table data or time shift data on the station staff's placement status by comparing these time axes with the current time, or through the camera installed on the platform. Information acquisition means for sequentially acquiring from the image and position information,
  Referring to the association degree acquired by the association degree acquisition means, the risk level in the platform is determined based on the image information acquired through the information acquisition means, train approach information, and station staff arrangement status A discriminating means to perform
  A platform risk classification system characterized by In the platform risk classification system for determining the risk in the station platform,
  The reference image information captured in the platform, the reference access information of the train to the platform at the time of capturing the reference image information, and the time zone shooting environment at the time of capturing the reference image information are shown. A degree-of-association acquisition means for acquiring in advance three or more levels of association between the combination of the reference time zone information and the degree of risk in the platform for the combination;
  When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, and train approach information to the platform at the time of the capturing is acquired. An information acquisition means for acquiring time zone information indicating a shooting environment in the time zone at the time of shooting,
  Referring to the association degree acquired by the association degree acquisition unit, the risk level in the platform is determined based on the image information acquired through the information acquisition unit, train approach information, and time zone information. Having a discrimination means
  A platform risk discrimination system characterized by In the platform risk classification system for determining the risk in the station platform,
  Combination of reference image information captured in the platform, reference information of train reference to the platform at the time of capturing the reference image information, and reference audio information detected in the platform, and the combination A degree-of-association acquisition means for acquiring in advance three or more levels of association with the risk in the platform for
  When the risk level is newly determined on the platform, image information is acquired by newly capturing an image in the platform, and train approach information to the platform at the time of capturing is detected in the platform. Information acquisition means for acquiring audio information;
  Discrimination to determine the risk level in the platform based on the image information acquired through the information acquisition unit, train approach information, and voice information with reference to the association level acquired by the association level acquisition unit Providing means
  A platform risk classification system characterized by

Images