Information processing device, information processing method, program, and information processing system

Abstract

To provide a technology that enables highly accurate determination of a state of object.SOLUTION: There is provided an information processing device comprising: a reflection state determination unit that determines, on the basis of a first detection result in a determination area of a reflection wave detected by a sensor at a first point in time, a first reflection state in the determination area at the first point in time, and determines, on the basis of a second detection result in the determination area of a reflection wave detected by the sensor at a second point in time that is earlier than the first point in time, a second reflection state in the determination area at the second point in time; and an object state determination unit that determines the state of an object on the basis of the first reflection state and the second reflection state.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, a program, and an information processing system. [Background technology]

[0002] In recent years, a technology for determining the state of an object based on data obtained by a sensor has become known. There are various examples of the object and the state. For example, if the object is a train, examples of the state include the train being present, not present, or moving. Furthermore, examples of the movement of the train include the train entering, leaving, or passing.

[0003] For example, there is known a technique for determining whether a train is on a track. As an example, Non-Patent Document 1 discloses a technique for determining whether a train is on a track based on the detection state of a line sensor installed above a station platform so that the stopping position of the lead car falls within the measurement range, and the detection state of a 2D (dimensional) laser-type sensor installed near the track so that the vicinity of the wheels of a train stopped on the station platform falls within the measurement range. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Nankai Electric Railway, Omron Social Solutions, "Towards the practical application of laser-based fall detection systems," Cybernetics, Vol. 28-No. 2, 2023 Summary of the Invention [Problem to be solved by the invention]

[0005] However, it is desirable to determine the state of an object with higher accuracy.

[0006] Therefore, the present invention has been made in consideration of the above problems, and an object of the present invention is to provide a technique that can determine the state of an object with higher accuracy. [Means for solving the problem]

[0007] In order to solve the above problem, according to one aspect of the present invention, an information processing device is provided, which includes a reflection state determination unit that determines a first reflection state in a determination area at a first time based on a first detection result in the determination area of a reflected wave detected by a sensor at the first time, and determines a second reflection state in the determination area at a second time based on a second detection result in the determination area of a reflected wave detected by the sensor at a second time that is earlier than the first time, and an object state determination unit that determines the state of an object based on the first reflection state and the second reflection state.

[0008] The object state determination unit may determine whether the object is present on a railroad line, not present on a railroad line, or moving, as the state of the object.

[0009] The judgment area may include one or more judgment sections, and the object state judgment unit may determine whether the state of the object is moving, present on the line, or not present on the line based on whether or not there is a judgment section in the one or more judgment sections in which the first reflection state and the second reflection state are different.

[0010] The object state determination unit may determine whether the object state is on the line or not based on the first reflection state in the one or more judgment sections when there is no judgment section in which the first reflection state and the second reflection state are different in the one or more judgment sections.

[0011] The object state determination unit may determine that the object state is not on the line if the second reflection state is a low reflection state in all of the one or more determination sections, and may determine that the object state is on the line if there is a determination section in the one or more determination sections in which the second reflection state is a high reflection state.

[0012] The reflection state determination unit may determine, for each of the one or more determination sections, whether the first reflection state is a high reflection state or a low reflection state depending on whether the magnitude of the first detection result is equal to or greater than a threshold value, and may determine whether the second reflection state is a high reflection state or a low reflection state depending on whether the magnitude of the second detection result is equal to or greater than a threshold value.

[0013] The first reflection state may be a first bit string in which the reflection state in each of the one or more judgment intervals at the first time is arranged, and the second reflection state may be a second bit string in which the reflection state in each of the one or more judgment intervals at the second time is arranged, and the object state determination unit may determine the state of the object by a predetermined logical operation based on the first bit string and the second bit string.

[0014] The predetermined logical operation may include at least one of a logical sum, a logical product, and an exclusive logical sum.

[0015] The judgment area may include one or more judgment intervals, and the one or more judgment intervals may be arranged in random positions.

[0016] The judgment area may include a plurality of judgment sections, and the plurality of judgment sections may be arranged in a vertical direction, a horizontal direction, or an oblique direction between the vertical and horizontal directions.

[0017] The reflected wave may be an electromagnetic wave or an acoustic wave.

[0018] The object state determination unit may control the display unit so that the state of the object is displayed by the display unit.

[0019] In addition, according to another aspect of the present invention, in order to solve the above-mentioned problem, there is provided an information processing method executed by a computer, which includes: determining a first reflection state in a judgment area at a first time based on a first detection result in the judgment area of a reflected wave detected by a sensor at the first time; determining a second reflection state in the judgment area at a second time based on a second detection result in the judgment area of a reflected wave detected by the sensor at a second time that is a time earlier than the first time; and determining a state of an object based on the first reflection state and the second reflection state.

[0020] In addition, according to another aspect of the present invention, in order to solve the above problem, a program is provided that causes a computer to function as a reflection state determination unit that determines a first reflection state in a determination area at a first time based on a first detection result in the determination area of a reflected wave detected by a sensor at the first time, and that determines a second reflection state in the determination area at a second time based on a second detection result in the determination area of a reflected wave detected by the sensor at a second time that is earlier than the first time, and an object state determination unit that determines the state of an object based on the first reflection state and the second reflection state.

[0021] In addition, according to another aspect of the present invention, in order to solve the above problem, an information processing system is provided, comprising: a sensor that detects reflected waves in a judgment area at a first time to obtain a first detection result, and that detects reflected waves in the judgment area at a second time that is earlier than the first time to obtain a second detection result; a reflection state determination unit that determines a first reflection state in the judgment area at the first time based on the first detection result, and determines a second reflection state in the judgment area at the second time based on the second detection result; and an object state determination unit that determines the state of an object based on the first reflection state and the second reflection state. [Effects of the Invention]

[0022] As described above, the present invention provides a technique that makes it possible to determine the state of an object with higher accuracy. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a block diagram illustrating an example of a functional configuration of an information processing system according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram in which the determination section K0 to K(N-1) is superimposed on a frame F1 detected when the train is not present on the track. [Figure 3] FIG. 10 is a diagram in which the determination section K0 to K(N-1) is superimposed on a frame F2 detected when the train is on the rail. [Figure 4] 3 is a flowchart showing an example of operation of the train state determination device 10 according to the embodiment of the present invention. [Figure 5] 3 is a flowchart showing an example of operation of the train state determination device 10 according to the embodiment of the present invention. [Figure 6] 3 is a flowchart showing an example of operation of the train state determination device 10 according to the embodiment of the present invention. [Figure 7] FIG. 10 is a diagram showing an example of a change in the reflection state bit over time when the train is moving. [Figure 8]FIG. 10 is a diagram showing an example of the change over time in the reflection state bit when the train is on the track. [Figure 9] FIG. 10 is a diagram showing an example of the change over time in the reflection state bit when the train is not present on the track. [Figure 10] 1 is a diagram showing a hardware configuration of an information processing device 900 as an example of a train state determination device 10 according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant explanations will be omitted.

[0025] <0.Background> First, the background of the embodiment of the present invention will be described.

[0026] In recent years, technology has become known for determining the state of an object based on data obtained by a sensor. In this specification, it is mainly assumed that the object whose state is to be determined is a train. However, the object whose state is to be determined does not have to be limited to a train. For example, the object whose state is to be determined may be an airplane, a car (such as a truck), or a ride at an amusement park. In this case, the stopping location of each object (for example, an airport, a truck collection and distribution center, a ride stop, etc.) may be substituted for a station platform.

[0027] In addition, in this specification, it is assumed that the state of an object is a train being present on the line, not being present on the line, or moving. Examples of train movement include a train entering a line, leaving a line, or passing through. However, the state of an object does not have to be limited to a train being present on the line, not being present on the line, or moving.

[0028] In this specification, "on track" can mean a state in which a part or all of a train is present within the sensor's measurement range and the train is stopped. On the other hand, in this specification, "not on track" can mean a state in which a part or all of a train is not present within the sensor's measurement range. Here, the expression "part of a train" is used because a train is not always made up of a single vehicle, but can be made up of multiple vehicles connected together, and therefore it is assumed that the entire train will not fit within the sensor's measurement range.

[0029] In this specification, "moving" may mean that part or all of the train is within the sensor's measurement range and the train is moving. "Arriving" may mean that the train is in the "moving" state and is moving just before it stops at a station. "Outgoing" may mean that the train is in the "moving" state and is moving just after it departs from a station. "Outgoing" may mean that the train is in the "moving" state and is passing through a station without stopping at the station.

[0030] For example, there is known a technique for determining whether a train is on a line. As an example, Non-Patent Document 1 discloses a technique for determining whether a train is on a line based on the detection state of a line sensor installed above a station platform (hereinafter also simply referred to as "platform") so that the stopping position of the lead car falls within the measurement range, and the detection state of a 2D laser-type sensor installed near the track so that the vicinity of the wheels of a train stopping at the station falls within the measurement range.

[0031] However, it is desirable to determine the state of a train with higher accuracy. Therefore, this specification mainly proposes a technique that enables the state of a train to be determined with higher accuracy.

[0032] More specifically, the stopping position of the lead car of a train may differ depending on the train. For example, the stopping position of the lead car may change depending on the number of cars in the train. Alternatively, the stopping position of the lead car may change depending on the type of train. It would be very time-consuming to provide a sensor for each of the possible stopping positions.

[0033] Therefore, this specification mainly proposes a technology that determines the reflection state in a determination section based on the detection result of reflected waves in the determination section by a sensor, and determines the state of the train based on the reflection state. As a result, if the determination section is set at the stopping position of at least the lead car, it becomes possible to determine the state of the train with high accuracy even if a sensor is not installed at each and every stopping position.

[0034] The background of the embodiments of the present invention has been described above.

[0035] <1. Details of the embodiment> Next, details of the embodiment of the present invention will be described.

[0036] [1-1. Example of information processing system configuration] First, an example of the functional configuration of an information processing system according to an embodiment of the present invention will be described. Fig. 1 is a block diagram showing an example of the functional configuration of an information processing system according to an embodiment of the present invention. As shown in Fig. 1, the information processing system 1 according to an embodiment of the present invention includes a train state determination device 10, a laser sensor 110, and a display unit 180. The train state determination device 10, the laser sensor 110, and the display unit 180 may be connected via a network.

[0037] (Laser Sensor 110) The laser sensor 110 is installed on or near the platform. For example, the laser sensor 110 is located above the platform so that it can measure a wide range. The laser sensor 110 has a function of detecting reflected waves from objects in response to irradiated waves within a preset measurement range. For example, the detection result of the reflected waves is obtained as a set of points (hereinafter also referred to as a "point cloud") indicating the three-dimensional coordinates of the reflection positions. In this case, the number of points constituting the point cloud may correspond to the magnitude of the detection result of the reflected waves.

[0038] More specifically, the laser sensor 110 detects a point cloud from the measurement range at predetermined time intervals (e.g., every second) by scanning the measurement range. In the following description, the point cloud detected from the measurement range by one scan is also referred to as a "frame."

[0039] In the following description, the latest frame detected by the laser sensor 110 (a point cloud detected at the current time) is also referred to as the "current frame." Furthermore, the frame detected by the laser sensor 110 one frame before the current frame (a point cloud detected at a previous time that is a time before the current time) is also referred to as the "previous frame." However, the previous frame may be a frame that is two or more frames before the current frame. The current time is an example of a first time, and the previous time is an example of a second time.

[0040] The laser sensor 110 is an example of a sensor. Therefore, the laser sensor 110 may be replaced with a sensor other than the laser sensor 110. The laser sensor 110 may also be referred to as a "LiDAR (Light Detection And Ranging) sensor."

[0041] Note that examples of sensors other than the laser sensor 110 include radar. While the laser sensor 110 uses laser light (e.g., ultraviolet light, visible light, near-infrared light, etc.) as an irradiating wave, radar uses electromagnetic waves (e.g., millimeter waves, etc.) with a shorter wavelength than that of laser light as an irradiating wave. Alternatively, in addition to sensors that use electromagnetic waves as irradiating waves, sonar that uses sound waves as irradiating waves may also be used instead of the laser sensor 110.

[0042] (Train state determination device 10) The train state determination device 10 can be realized by a computer. As shown in Fig. 1, the train state determination device 10 includes a point cloud acquisition unit 120, a determination section storage unit 130, a determination section setting unit 140, a reflection threshold storage unit 150, a reflection state determination unit 160, and a train state determination unit 170. Details of these components included in the train state determination device 10 will be described later.

[0043] For example, the point cloud acquisition unit 120, the judgment section setting unit 140, the reflection state judgment unit 160, and the train state judgment unit 170 may be realized by a control unit (not shown). On the other hand, the judgment section storage unit 130 and the reflection threshold storage unit 150 may be realized by a storage unit (not shown).

[0044] The control unit (not shown) includes a CPU (Central Processing Unit) and the like, and its functions can be realized by the CPU expanding a program stored in a non-volatile storage device into RAM (Random Access Memory) and executing it. In this case, a computer-readable recording medium on which the program is recorded can also be provided. Alternatively, the control unit (not shown) can be configured with dedicated hardware or a combination of multiple pieces of hardware.

[0045] The storage unit (not shown) is a storage device capable of storing programs and data for operating the control unit (not shown). The storage unit (not shown) can also temporarily store various data required in the operation of the control unit (not shown). For example, the storage device may be a non-volatile storage device.

[0046] (Display section 180) The display unit 180 is configured by a display. For example, the display unit 180 displays the train status under the control of the train status determination device 10. The location where the display unit 180 is provided is not particularly limited. For example, the display unit 180 may be provided on a platform, in a station office where station staff are present, or in a monitoring center where staff are present who monitor the train operation status.

[0047] (Point cloud acquisition unit 120) The point cloud acquisition unit 120 acquires a point cloud detected by the laser sensor 110. For example, the point cloud acquisition unit 120 acquires a point cloud detected by the laser sensor 110 at a previous time. Furthermore, the point cloud acquisition unit 120 acquires a point cloud detected by the laser sensor 110 at the current time.

[0048] (Determination section storage unit 130) The determination section storage unit 130 stores in advance parameters for defining N determination sections (N is an integer equal to or greater than 1). In the following description, the N determination sections are also referred to as determination sections K0 to K(N-1). Each of the determination sections K0 to K(N-1) is a unit of area where the reflectivity state is determined, and the determination sections K0 to K(N-1) correspond to a determination area. The determination sections K0 to K(N-1) will be described with reference to FIGS. 2 and 3.

[0049] Fig. 2 is a diagram in which the determination section K0 to K(N-1) is superimposed on a frame F1 detected when the train is not present on the track. Fig. 3 is a diagram in which the determination section K0 to K(N-1) is superimposed on a frame F2 detected when the train is present on the track. In the examples shown in Figs. 2 and 3, the white circles are points that make up the point cloud detected by the laser sensor 110.

[0050] As shown in Figure 2, when the train is not present on the tracks, the point cloud is located below frame F1. The lower side of frame F1 corresponds to the location where the tracks are present, and the determination section K0 to K(N-1) does not exist below frame F1. On the other hand, as shown in Figure 3, when the train is present on the tracks, the point cloud is located not only below frame F2 but also in the center of frame F2. The determination section K0 to K(N-1) exists in the center of frame F2.

[0051] In the following explanation, it is mainly assumed that each of the judgment intervals K0 to K(N-1) has a rectangular parallelepiped shape, and parameters are expressed by pj1(xj1, yj1, zj1) and pj2(xj2, yj2, zj2), which are the coordinates of both ends of one diagonal line of each of the judgment intervals K0 to K(N-1), where j=0, 1, . . . , N-1. As an example, FIG. 2 shows p01(x01, y01, z01) and p02(x02, y02, z02) as parameters of the judgment interval K0.

[0052] In the following description, the combination of pj1(xj1, yj1, zj1) and pj2(xj2, yj2, zj2) will also be referred to as cube[j]. The determination interval storage unit 130 stores the number N of determination intervals in advance.

[0053] The shape of each of the determination intervals K0 to K(N-1) does not have to be a rectangular parallelepiped. The following description mainly assumes that the determination intervals K0 to K(N-1) are the same size, but the sizes of the determination intervals K0 to K(N-1) do not have to be the same. The following description mainly assumes that the determination intervals K0 to K(N-1) are arranged at equal intervals, but the determination intervals K0 to K(N-1) do not have to be arranged at equal intervals.

[0054] (Determination section setting unit 140) The judgment interval setting unit 140 sets judgment intervals K0 to K(N-1) by acquiring the number N of judgment intervals and a parameter cube[j] (where j=0, 1, . . . , N-1) for defining the judgment intervals from the judgment interval storage unit 130.

[0055] (Reflection threshold storage unit 150) The reflection threshold storage unit 150 stores in advance a threshold value (hereinafter also referred to as a "reflection threshold value") used to determine the reflection state in each of the determination intervals K0 to K(N-1). In the following description, it is mainly assumed that a common reflection threshold value is used to determine the reflection state in each of the determination intervals K0 to K(N-1). However, a different reflection threshold value may be used for each determination interval. In the following description, the reflection threshold value is also referred to as "ref_th".

[0056] (Reflection state determination unit 160) The reflection state determination unit 160 determines the reflection state (second reflection state) in the determination section K0 to K(N-1) at the previous time based on the point cloud (second detection result) in the determination section K0 to K(N-1) detected at the previous time. More specifically, for each of the determination sections K0 to K(N-1) detected at the previous time, the reflection state determination unit 160 determines whether the reflection state in the determination section at the previous time was a high reflection state or a low reflection state depending on whether the number of points constituting the point cloud in the determination section was equal to or greater than a reflection threshold value.

[0057] Furthermore, the reflection state determination unit 160 determines the reflection state (first reflection state) in the determination section K0 to K(N-1) at the current time based on the point cloud (first detection result) in the determination section K0 to K(N-1) detected at the current time. More specifically, for each of the determination sections K0 to K(N-1) detected at the current time, the reflection state determination unit 160 determines whether the reflection state in the determination section at the current time is a high reflection state or a low reflection state depending on whether the number of points constituting the point cloud in the determination section is equal to or greater than a reflection threshold.

[0058] In the following explanation, we mainly assume that the reflection state in the judgment intervals K0 to K(N-1) at the previous time is represented by a bit string (second bit string) in which the reflection state in each of the N judgment intervals at the previous time is arranged.

[0059] In addition, in the following explanation, it is mainly assumed that the reflection state in the judgment interval K0 to K(N-1) at the current time is represented by a bit string (first bit string) in which the reflection states in each of the judgment intervals K0 to K(N-1) at the current time are arranged.

[0060] In the following explanation, it is mainly assumed that the bit indicating a high reflection state is set to 1 and the bit indicating a low reflection state is set to 0 in the reflection state in the judgment interval K0 to K(N-1) at the previous time and the reflection state in the judgment interval K0 to K(N-1) at the current time. However, the values set in the bits indicating a high reflection state and the values set in the bits indicating a low reflection state do not have to be limited.

[0061] (Train state determination unit 170) The train state determination unit 170 determines the state of the train based on the reflection state in the determination section K0 to K(N-1) at the current time and the reflection state in the determination section K0 to K(N-1) at the previous time. In this way, by determining the state of the train based on the reflection state for each determination section, it is possible to determine the state of the train with higher accuracy while reducing the effort of installing sensors at each of the train's stopping positions along all routes.

[0062] For example, the train state determination unit 170 may determine the train state as being present on the track, not present on the track, or moving.

[0063] First, when the train state is moving, it is considered that there is a determination section within the determination section K0 to K(N-1) where the reflection state at the current time is different from the reflection state at the previous time. Therefore, the train state determination unit 170 may determine whether the train state is moving, present on the track, or not present on the track based on whether there is a determination section within the determination section K0 to K(N-1) where the reflection state at the current time is different from the reflection state at the previous time.

[0064] On the other hand, when the train is present or absent, it is considered that there is no judgment section within the judgment section K0 to K(N-1) where the reflection state at the current time differs from the reflection state at the previous time. However, when the train is absent, it is considered that the reflection state of the entire judgment section K0 to K(N-1) at the current time is a low reflection state.

[0065] Therefore, if there is no judgment section among the judgment sections K0 to K(N-1) in which the reflection state at the current time is different from the reflection state at the previous time, the train state judgment unit 170 may judge whether the state of the object is on the line or not on the line based on the reflection state of the judgment section K0 to K(N-1) at the current time.

[0066] More specifically, the train state determination unit 170 may determine that the train state is not on the track if there is no determination section among the determination sections K0 to K(N-1) in which the reflection state at the current time is different from the reflection state at the previous time, and if all of the reflection states in the determination sections K0 to K(N-1) at the current time are low reflection states.

[0067] On the other hand, the train state determination unit 170 may determine that the train state is on track if there is no determination section within the determination section K0 to K(N-1) where the reflection state at the current time is different from the reflection state at the previous time, and if there is a determination section with a high reflection state among the reflection states of the determination section K0 to K(N-1) at the current time.

[0068] As described above, the reflection state in the determination section K0 to K(N-1) at the previous time can be expressed by a bit string. The reflection state in the determination section K0 to K(N-1) at the current time can also be expressed by a bit string. The train state determination unit 170 can then determine the train state by performing a predetermined logical operation based on these two bit strings.

[0069] In the following description, it is mainly assumed that an exclusive OR (XOR operation) is used as the predetermined logical operation. However, the predetermined logical operation does not have to be limited to an exclusive OR. For example, a logical sum (OR operation) or a logical product (AND operation) may be used as the predetermined logical operation. Alternatively, a combination of two or more of an exclusive OR, a logical sum, and a logical product may be used as the predetermined logical operation.

[0070] Then, the train state determination unit 170 controls the display unit 180 so that the train state is displayed by the display unit 180. This allows station staff, monitors, etc. to understand the train state.

[0071] An example of the functional configuration of the information processing system 1 according to the embodiment of the present invention has been described above.

[0072] [1-2. Operation example of train state determination device 10] Next, an example of the operation of the train state determination device 10 according to the embodiment of the present invention will be described with reference to FIGS. 4 to 9 (and also with reference to FIGS. 1 to 3 as appropriate).

[0073] 4 to 6 are flowcharts showing an example of the operation of the train state determination device 10 according to the embodiment of the present invention. As shown in Fig. 4, the determination section setting unit 140 acquires the number of determination sections N from the determination section storage unit 130 (step A1). In addition, the determination section setting unit 140 acquires parameters cube[0] to cube[N-1] for defining the determination sections K0 to K(N-1) from the determination section storage unit 130 (step A2).

[0074] Furthermore, the reflection state determination unit 160 acquires the reflection threshold value ref_th from the reflection threshold storage unit 150 (step A3). The reflection state determination unit 160 also sets initial values for pre_bit[0] to pre_bit[N-1], which represent the reflection state in the determination interval K0 to K(N-1) at the previous time (step A4). The initial values may be any value. For example, the initial value may be 0 (zero).

[0075] The point cloud acquisition unit 120 acquires a point cloud (current frame) at the current time detected by the laser sensor 110 (step A5). For example, if the number of points constituting the point cloud is M, the point cloud at the current time can be expressed as point[0] to point[M-1] = {q0(x, y, z), q1(x, y, z), , q(M-1)(x, y, z)}. As shown in Fig. 5, the reflection state determination unit 160 sets 0 (zero) as the initial value of a determination section counter j (step A6).

[0076] The reflection state determination unit 160 determines whether the determination section counter j is less than the number of determination sections N (step A7). If the reflection state determination unit 160 determines that the determination section counter j is less than the number of determination sections N ("YES" in step A7), it counts the number of points included in the determination section K0 to K(N-1) defined by the parameters cube[0] to cube[N-1] from the point group q0(x, y, z), q1(x, y, z), . . . , q(M-1)(x, y, z) at the current time.

[0077] The reflection state determination unit 160 assigns the points included in the determination section K0 to K(N-1) to the array cube_cnt[0] to cube_cnt[N-1] (step A8). Then, the reflection state determination unit 160 determines whether cube_cnt[j] is equal to or greater than the reflection threshold value ref_th (step A9).

[0078] If the reflection state determination unit 160 determines that cube_cnt[j] is equal to or greater than the reflection threshold value ref_th ("YES" in step A9), it sets the reflection state bit[j] for the determination section Kj at the current time to 1 (high reflection state) (step A10), increments the determination section counter j (step A12), and transitions to step A7. On the other hand, if the reflection state determination unit 160 determines that cube_cnt[j] is less than the reflection threshold value ref_th ("NO" in step A9), it sets the reflection state bit[j] for the determination section Kj at the current time to 0 (low reflection state) (step A11), increments the determination section counter j (step A12), and transitions to step A7.

[0079] If the reflection state determination unit 160 determines that the determination section counter j is equal to or greater than the number of determination sections N ("NO" in step A7), it calculates an exclusive OR XOR(pre_bit, bit) based on the reflection state bit in the determination section K0 to K(N-1) at the current time and the reflection state pre_bit in the determination section K0 to K(N-1) at the previous time, as shown in Fig. 6. Then, the reflection state determination unit 160 assigns the exclusive OR XOR(pre_bit, bit) to the bit string bit_y (step A13).

[0080] The train state determination unit 170 determines the state of the train based on the exclusive OR bit_y. An example of the correspondence between the exclusive OR bit_y and the train state will now be described. Specifically, it is assumed here that the number of determination sections N is 9.

[0081] FIG. 7 is a diagram showing an example of changes in the reflection state bit over time when the train is moving. Referring to FIG. 7, the reflection state bits [0] to [8] at time t1, the reflection state bits [0] to [8] at time t2, and the reflection state bits [0] to [8] at time t3 are shown. The reflection state of hatched bits [] is 1 (high reflection state), and the reflection state of unhatched bits [] is 0 (low reflection state). Time t1 is the time before time t2, and time t2 is the time before time t3. Car T1 is the front car of the train, and car T2 is the rear car of the train.

[0082] As time passes from time t1 to time t3, vehicles T1 and T2 move from right to left on the paper. At this time, at time t1, reflection state bits [0] to [3] are 0 (low reflection state), and reflection state bits [4] to [8] are 1 (high reflection state). Therefore, the reflection state bits at time t1 are "000011111".

[0083] At time t2, the reflection state bits [0] to [1], [8] are 0 (low reflection state), and the reflection state bits [2] to [7] are 1 (high reflection state). Therefore, the reflection state bits at time t2 are "001111110". For example, if the previous time is t1 and the current time is t2, the exclusive OR of the reflection state bits at the previous time t1 and the reflection state bits at the current time t2 is calculated as "001100001".

[0084] At time t3, the reflection state bits [0] to [5] are 1 (high reflection state), and the reflection state bits [6] to [8] are 0 (low reflection state). Therefore, the reflection state bits at time t3 are "111111000." For example, if the previous time is t2 and the current time is t3, the exclusive OR of the reflection state bits at the previous time t2 and the reflection state bits at the current time t3 is calculated as "110000110."

[0085] In this way, when the train is moving, the exclusive OR based on the reflection state at the previous time and the reflection state at the current time contains a bit that is 1. In other words, when the train is moving, the exclusive OR based on the reflection state at the previous time and the reflection state at the current time does not become "000000000."

[0086] FIG. 8 is a diagram showing an example of the change over time of the reflection status bit when the train is on the track.

[0087] 8, as time passes from time t1 to time t3, vehicles T1 and T2 do not move. Therefore, from time t1 to t3, the reflection state bits [0] to [1], [8] are all 0 (low reflection state), and the reflection state bits [2] to [7] are all 1 (high reflection state). Therefore, the reflection state bits from time t1 to t3 are "001111110".

[0088] For example, if the previous time is t1 and the current time is t2, the exclusive OR of the reflection state bit at the previous time t1 and the reflection state bit at the current time t2 is calculated as "000000000." Similarly, if the previous time is t2 and the current time is t3, the exclusive OR of the reflection state bit at the previous time t2 and the reflection state bit at the current time t3 is calculated as "000000000."

[0089] In this way, when the train is on the rail, there is no bit that becomes 1 in the exclusive OR based on the reflection state at the previous time and the reflection state at the current time. In other words, when the train is on the rail, the exclusive OR based on the reflection state at the previous time and the reflection state at the current time becomes "000000000." However, when the train is on the rail, the reflection state bit itself does not become "000000000" at any of times t1 to t3.

[0090] FIG. 9 is a diagram showing an example of the change over time of the reflection status bit when the train is not present on the track.

[0091] 9, as time passes from time t1 to time t3, no trains are present. Therefore, at all times from t1 to t3, the reflection state bits [0] to [1] and [8] are 0 (low reflection state). Therefore, the reflection state bits at times t1 to t3 are "000000000."

[0092] For example, if the previous time is t1 and the current time is t2, the exclusive OR of the reflection state bit at the previous time t1 and the reflection state bit at the current time t2 is calculated as "000000000." Similarly, if the previous time is t2 and the current time is t3, the exclusive OR of the reflection state bit at the previous time t2 and the reflection state bit at the current time t3 is calculated as "000000000."

[0093] In this way, when the train is not present on the line, there is no bit that becomes 1 in the exclusive OR based on the reflection state at the previous time and the reflection state at the current time. In other words, when the train is not present on the line, the exclusive OR based on the reflection state at the previous time and the reflection state at the current time is "000000000." However, when the train is not present on the line, unlike when the train is present on the line, the reflection state bit itself is "000000000" at all of times t1 to t3.

[0094] Returning to Figure 6, the explanation will be continued. The train state determination unit 170 determines whether the exclusive OR bit_y is other than 0 (step A13). If the train state determination unit 170 determines that the exclusive OR bit_y is other than 0 ("YES" in step A13), it assigns "moving" to the variable "status" that stores the train state, and proceeds to step A19. On the other hand, if the train state determination unit 170 determines that the exclusive OR bit_y is 0 ("NO" in step A13), it determines whether the reflection state bit at the current time is 0 (step A16).

[0095] If the train state determination unit 170 determines that the reflection state bit at the current time is 0 ("YES" in step A16), it assigns "not on the track" to the variable status that stores the train state (step A17), and proceeds to step A19. On the other hand, if the train state determination unit 170 determines that the reflection state bit at the current time is not 0 ("NO" in step A16), it assigns "on the track" to the variable status that stores the train state (step A18), and proceeds to step A19.

[0096] The train state determination unit 170 copies the reflection state bit at the current time to the reflection state pre_bit at the previous time (step A19). The train state determination unit 170 outputs the train state stored in the variable status to the display unit 180 (step A20). This controls the display of the train state determined by the train state determination unit 170 by the display unit 180.

[0097] The point cloud acquisition unit 120 determines whether or not to end the processing (step A21). If the point cloud acquisition unit 120 determines to end the processing ("YES" in step A21), it ends the processing. On the other hand, if the point cloud acquisition unit 120 determines not to end the processing ("NO" in step A21), it transitions to step A5 and acquires a point cloud at the next time (next frame).

[0098] An example of the operation of the train state determination device 10 according to the embodiment of the present invention has been described above.

[0099] [1-3. Effects of the embodiment] As described above, according to the train state determination device 10 of the embodiment of the present invention, the reflection state in a determination section is determined based on the detection result of the reflected wave in the determination section by the sensor, and the state of the train is determined based on the reflection state. As a result, if the determination section is set at least at the stopping position of the lead car, it is possible to determine the state of the train with high accuracy even if a sensor is not provided at each and every stopping position.

[0100] Furthermore, as described above, the stopping position of the leading car of a train may differ depending on the train. For example, the stopping position of the leading car may change depending on the number of cars in the train. Alternatively, the stopping position of the leading car may change depending on the type of train. According to the train state determination device 10 of the embodiment of the present invention, by setting multiple determination sections, the state of the train can be determined with high accuracy even if there is a deviation in the stopping position of the leading car.

[0101] The effects of the embodiments of the present invention have been described above.

[0102] <2. Various Modifications> Next, various modified examples will be described.

[0103] It has been mentioned above that the sizes of the judgment sections K0 to K(N-1) may or may not be the same. Here, it can be said that the smaller the size of the judgment section, the more likely the reflection state in the judgment section where the lead and last cars of the train stop is to change in response to a shift in the stopping position. Conversely, it can be said that the larger the size of the judgment section, the more unlikely the reflection state in the judgment section where the lead and last cars of the train stop is to change in response to a shift in the stopping position.

[0104] In the above, it is mainly assumed that the parameter cube[j] (where j=0, 1, . . . , N-1) for defining the judgment interval is stored in advance by the judgment interval setting unit 140. However, the parameter cube[j] for defining the judgment interval does not have to be stored in advance by the judgment interval setting unit 140. In this case, the judgment interval setting unit 140 may arrange the judgment intervals K0 to K(N-1) at random positions.

[0105] In the above, it has been mainly assumed that the determination section setting unit 140 arranges the determination sections K0 to K(N-1) horizontally along the direction of train movement. However, the determination section setting unit 140 may arrange the determination sections K0 to K(N-1) vertically. Alternatively, the determination section setting unit 140 may arrange the determination sections K0 to K(N-1) in a diagonal direction between the vertical and horizontal directions.

[0106] In the above, it has been mainly assumed that each of the determination sections K0 to K(N-1) is a rectangular parallelepiped. However, it is also possible that a 2D laser sensor is used as the laser sensor 110. In such a case, each of the determination sections K0 to K(N-1) may be a rectangle, or may be any other planar shape.

[0107] In the above, it is mainly assumed that the train state determination unit 170 determines the state of the train based on the reflection state of each of the determination sections K0 to K(N-1) at the current time and the previous time. However, the train state determination unit 170 may determine the state of the train based on the reflection state of each of the determination sections K0 to K(N-1) at three or more times.

[0108] For example, the train state determination unit 170 may determine that the state of the train is moving if there is a determination section whose reflection state differs at three or more times.Alternatively, the train state determination unit 170 may determine that the state of the train is on track or not on track if there is no determination section whose reflection state differs at three or more times.In this case, the train state determination unit 170 may determine whether the state of the train is not on track or not on track depending on whether the reflection state of all of the determination sections K0 to K(N-1) at the current time is a low reflection state.

[0109] Various modifications have been described above.

[0110] <3. Hardware configuration example> Next, an example of the hardware configuration of the train state determination device 10 according to the embodiment of the present invention will be described. Below, an example of the hardware configuration of an information processing device 900 will be described as an example of the hardware configuration of the train state determination device 10 according to the embodiment of the present invention. Note that the example of the hardware configuration of the information processing device 900 described below is merely one example of the hardware configuration of the train state determination device 10. Therefore, in the hardware configuration of the train state determination device 10, unnecessary components may be deleted from the hardware configuration of the information processing device 900 described below, or new components may be added.

[0111] 10 is a diagram showing a hardware configuration of an information processing device 900 as an example of the train state determination device 10 according to an embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

[0112] The CPU 901 functions as an arithmetic processing unit and control unit, and controls the overall operation of the information processing device 900 in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, etc. These are interconnected by a host bus 904 that is composed of a CPU bus, etc.

[0113] The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 905. It is not necessary to configure the host bus 904, bridge 905, and external bus 906 separately, and these functions may be implemented on a single bus.

[0114] The input device 908 is composed of input means such as a mouse, keyboard, touch panel, buttons, microphone, switches, and levers that allow the user to input information, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901. By operating this input device 908, the user operating the information processing device 900 can input various data to the information processing device 900 and instruct the information processing device 900 to perform processing operations.

[0115] The output device 909 includes, for example, a display device such as a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, or a lamp, and an audio output device such as a speaker.

[0116] The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, and a deletion device for deleting data recorded on the storage medium. The storage device 910 is configured, for example, with an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

[0117] The communication device 911 is, for example, a communication interface configured with a communication device for connecting to a network, etc. The communication device 911 may be compatible with either wireless communication or wired communication.

[0118] An example of the hardware configuration of the train state determination device 10 according to the embodiment of the present invention has been described above.

[0119] <4. Supplementary Information> Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention. [Explanation of symbols]

[0120] 1. Information Processing Systems 10 Train status determination device 110 Laser Sensor 120 Point cloud acquisition section 130 Judgment section memory unit 140 Judgment section setting unit 150 Reflection threshold memory 160 Reflection state determination unit 170 Train status determination unit 180 Display section

Claims

1. a reflection state determination unit that determines a first reflection state in the determination area at a first time based on a first detection result in the determination area of a reflected wave detected by a sensor at the first time, and that determines a second reflection state in the determination area at a second time based on a second detection result in the determination area of a reflected wave detected by the sensor at the second time that is a time before the first time; an object state determination unit that determines a state of an object based on the first reflection state and the second reflection state; An information processing device comprising:

2. the object state determination unit determines whether the object is present on the rail, not present on the rail, or moving as the state of the object; The information processing device according to claim 1 .

3. the judgment area includes one or more judgment sections, the object state determination unit determines whether the state of the object is moving, or whether the object is present on a rail or not, based on whether or not there is a determination section in which the first reflection state and the second reflection state are different in the one or more determination sections. The information processing device according to claim 2 .

4. the object state determination unit determines whether the state of the object is on a rail or not on a rail based on the first reflection state in the one or more determination sections when there is no determination section in which the first reflection state and the second reflection state are different in the one or more determination sections. The information processing device according to claim 3 .

5. the object state determination unit determines that the state of the object is not on a rail when the second reflectivity state is a low reflectivity state in the entire one or more determination sections, and determines that the state of the object is on a rail when there is a determination section in which the second reflectivity state is a high reflectivity state in the one or more determination sections. The information processing device according to claim 4 .

6. the reflection state determination unit determines, for each of the one or more determination sections, whether the first reflection state is a high reflection state or a low reflection state depending on whether the magnitude of the first detection result is equal to or greater than a threshold value, and determines whether the second reflection state is a high reflection state or a low reflection state depending on whether the magnitude of the second detection result is equal to or greater than a threshold value. The information processing device according to claim 5 .

7. the first reflection state is a first bit string in which reflection states in each of the one or more determination sections at the first time are arranged, the second reflection state is a second bit string in which reflection states in each of the one or more determination sections at the second time are arranged, the object state determination unit determines the state of the object by a predetermined logical operation based on the first bit string and the second bit string. The information processing device according to claim 1 .

8. the predetermined logical operation includes at least one of a logical sum, a logical product, and an exclusive logical sum; The information processing device according to claim 7 .

9. the judgment area includes one or more judgment sections, The one or more decision intervals are arranged at random positions. The information processing device according to claim 1 .

10. the judgment area includes a plurality of judgment sections, the plurality of determination sections are arranged in a vertical direction, a horizontal direction, or an oblique direction between the vertical direction and the horizontal direction; The information processing device according to claim 1 .

11. The reflected wave is an electromagnetic wave or a sound wave. The information processing device according to claim 1 .

12. The object state determination unit controlling the display unit so that the state of the object is displayed by the display unit; The information processing device according to claim 1 .

13. determining a first reflection state in the determination area at a first time based on a first detection result in the determination area of a reflected wave detected by a sensor at the first time, and determining a second reflection state in the determination area at a second time based on a second detection result in the determination area of a reflected wave detected by the sensor at the second time that is a time before the first time; determining a state of the object based on the first reflectance state and the second reflectance state; 2. A computer-implemented information processing method, comprising:

14. Computer, a reflection state determination unit that determines a first reflection state in the determination area at a first time based on a first detection result in the determination area of a reflected wave detected by a sensor at the first time, and that determines a second reflection state in the determination area at a second time based on a second detection result in the determination area of a reflected wave detected by the sensor at the second time that is a time before the first time; an object state determination unit that determines a state of an object based on the first reflection state and the second reflection state; A program that functions as a

15. a sensor that detects a reflected wave from a determination area at a first time to obtain a first detection result, and that detects a reflected wave from the determination area at a second time that is a time before the first time to obtain a second detection result; a reflection state determination unit that determines a first reflection state in the determination area at the first time based on the first detection result, and determines a second reflection state in the determination area at the second time based on the second detection result; an object state determination unit that determines a state of an object based on the first reflection state and the second reflection state; An information processing system comprising:

Images