Information processing device, information processing method, and program

Abstract

To provide a technology capable of improving the accuracy of determining an area in which an object is present while reducing labor imposed on a user.SOLUTION: An information processing device includes: a sensor data acquisition unit that acquires sensor data obtained by a sensor; and a determination unit that, based on a reference function serving as a reference for determining an area in which a representative position of an object region is present and the sensor data, determines whether the representative position is present in a first area or present in a second area.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] In recent years, a technology for detecting an object based on data obtained by a sensor (hereinafter also referred to as "sensor data") has become known (see, for example, Patent Document 1). The object detection results can be used in various situations. For example, a technology for determining whether an object exists within a pre-set area (hereinafter also referred to as "detection area") based on the object detection results is known. For example, in such a technology, a person is mainly considered as the object.

[0003] More specifically, this technology uses multiple distance sensors installed along the edge of a station platform to track an object, and determines that the object has fallen from the station platform based on the detection that the tracked object has disappeared from the detection area. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5647458 Summary of the Invention [Problem to be solved by the invention]

[0005] However, detecting that an object has disappeared from the detection area does not necessarily mean that the object has fallen from the station platform. Therefore, if the system determines that the object has fallen from the station platform just because it has detected that the object has disappeared from the detection area without understanding the circumstances surrounding the object's disappearance, the accuracy of the determination will not improve.

[0006] Furthermore, setting the detection area requires a lot of effort from the user. In particular, when the station platform is curved, it is not possible to set the detection area for multiple distance sensors installed at the edge of the station platform at once, and it becomes necessary to set the detection area for each distance sensor, which means that setting the detection area requires a lot of effort from the user.

[0007] Therefore, the present invention has been made in consideration of the above problems, and an object of the present invention is to provide a technology that can improve the accuracy of determining the area where an object exists while reducing the effort required of the user. [Means for solving the problem]

[0008] In order to solve the above problem, according to one aspect of the present invention, there is provided an information processing device comprising: a sensor data acquisition unit that acquires sensor data obtained by a sensor; a reference function that serves as a criterion for determining an area in which a representative position of an object area exists; and a determination unit that determines whether the representative position exists in a first area or a second area based on the sensor data.

[0009] The information processing device may include a processing area extraction unit that extracts the sensor data within a predetermined processing area, and the determination unit may determine whether the representative position is located in the first area or the second area based on the reference function and the sensor data.

[0010] The processing area may include a first processing area in a sensor coordinate system corresponding to an area located above a predetermined horizontal plane perpendicular to the vertical direction in real space, and a second processing area in the sensor coordinate system corresponding to an area located below the predetermined horizontal plane.

[0011] The sensor coordinate space or the sensor coordinate plane may be divided into two areas by a figure corresponding to the base function, and the first processing area may be present in one of the two areas, and the second processing area may be present in the other area.

[0012] The determination unit may include an object detection unit that detects the object area based on the sensor data and detects the representative position of the object area, and an area determination unit that determines whether the representative position is located in the first area or the second area based on the representative position and the reference function.

[0013] The area determination unit may acquire an output value output from the criterion function in response to inputting the representative position as an input value into the criterion function, and determine whether the representative position is located in the first area or the second area based on the output value.

[0014] The object detection unit may detect a first representative position of a first object area at a first time and a second representative position of a second object area at a second time after the first time, the determination unit may include an object tracking unit that calculates a distance between the first representative position and the second representative position and associates the first representative position with the second representative position if the distance is smaller than a threshold, and the determination unit may include a movement determination unit that determines whether the same object has moved between the first area and the second area based on whether the associated first representative position and the second representative position are in the same area or different areas.

[0015] When the movement determination unit determines that the associated first representative position and the second representative position are located in different areas, the movement determination unit may determine whether the same object has moved between the first area and the second area based on whether a difference between a first statistical processing result for the representative position of the object area of ​​the same object before the first time and a second statistical processing result for the representative position of the object area of ​​the same object after the second time is greater than a predetermined value.

[0016] Coordinate axes are set along the vertical direction in real space, and the first statistical processing result may be an average value of coordinates on the coordinate axes of representative positions of object regions of the same object before the first time, and the second statistical processing result may be an average value of coordinates on the coordinate axes of representative positions of object regions of the same object after the second time.

[0017] The object detection unit detects a first representative position of a first object region at a first time and a second representative position of a second object region at a second time after the first time, and the determination unit includes an object tracking unit that calculates a distance between the first representative position and the second representative position and, if the distance is smaller than a threshold, associates the first representative position with the second representative position, wherein coordinate axes are set along the vertical direction in real space, and the determination unit may include a movement determination unit that determines whether the same object has moved between the first area and the second area based on the coordinates on the coordinate axes of the first representative position and the coordinates on the coordinate axes of the second representative position, which are associated as representative positions of the object regions of the same object, in a sensor coordinate system based on the sensor.

[0018] The movement determination unit may determine whether the same object has moved between the first area and the second area based on whether a difference between the coordinate of the first representative position on the coordinate axis and the coordinate of the second representative position on the coordinate axis is greater than a predetermined value.

[0019] The basis function may be determined by approximation based on position information input by a user, position information obtained by a GNSS sensor or a laser scanner.

[0020] The second area may include a third area and a fourth area, and the determination unit may determine whether the representative position is located in the third area or the fourth area based on another criterion function obtained by adding a constant to the criterion function and the sensor data.

[0021] The approximation may be a polynomial approximation, and the reference function may be a function expressed using a polynomial determined by the polynomial approximation.

[0022] The criterion function may be determined by approximation based on position information input by the user.

[0023] The reference function may be determined by converting position information obtained by a GNSS sensor or a laser scanner into position information in a sensor coordinate system based on the sensor, and then approximating the position information in the sensor coordinate system.

[0024] In addition, according to another aspect of the present invention to solve the above problem, there is provided an information processing method executed by a computer, which includes acquiring sensor data obtained by a sensor, a reference function serving as a standard for determining an area in which a representative position of an object area exists, and determining whether the representative position exists in a first area or a second area based on the sensor data.

[0025] In addition, according to another aspect of the present invention, in order to solve the above problem, there is provided a program that causes a computer to function as a sensor data acquisition unit that acquires sensor data obtained by a sensor, a reference function that serves as a standard for determining an area in which a representative position of an object area exists, and a determination unit that determines whether the representative position exists in a first area or a second area based on the sensor data. [Effects of the Invention]

[0026] As described above, according to the present invention, a technique is provided that can improve the accuracy of determining an area where an object exists while reducing the effort required of the user. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a block diagram showing an example of the functional configuration of a criterion function determining device 1 according to a first embodiment of the present invention. [Figure 2] 1 is a block diagram showing an example of a functional configuration of an area determination device 2 according to a first embodiment of the present invention. [Figure 3] 10 is a flowchart showing an example of the operation of the basis function determining device 1 at the basis function determining stage. [Figure 4] FIG. 10 is a diagram showing an example of an input point cloud obtained in the criterion function determination stage. [Figure 5] FIG. 10 is a diagram illustrating an example of an approximation curve corresponding to a criterion function. [Figure 6] FIG. 10 is a diagram illustrating an example of an approximation curve in a sensor coordinate system. [Figure 7] 10 is a flowchart showing an example of the operation of the area determination device 2 in the area determination stage. [Figure 8] FIG. 10 is a block diagram showing an example of a functional configuration of an area determination device 3 according to a second embodiment of the present invention. [Figure 9] 10 is a flowchart showing an example of the operation of the area determination device 3 in the area determination stage. [Figure 10] 10 is a flowchart showing an example of the operation of the area determination device 3 in the area determination stage. [Figure 11] 10 is a diagram showing an example of a processing area identified by a processing area cutout unit 200. FIG. [Figure 12] FIG. 10 is a diagram for explaining a case where the same object falls from the platform side area to the track side area. [Figure 13] FIG. 10 is a diagram illustrating a first modified example. [Figure 14] FIG. 10 is a diagram illustrating a second modified example. [Figure 15] FIG. 10 is a diagram illustrating a third modified example. [Figure 16] 1 is a diagram showing a hardware configuration of an information processing device 900 as an example of an area determination device 2 according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] 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.

[0029] <1. First embodiment> First, details of the first embodiment of the present invention will be described. The information processing system according to the first embodiment of the present invention includes a laser sensor 10 (FIGS. 1 and 2), a basis function determination device 1 (FIG. 1), and an area determination device 2 (FIG. 2).

[0030] In the first embodiment of the present invention, it is mainly assumed that the object (hereinafter also referred to as "target object") whose position is determined by the area determination device 2 is a person. However, the target object is not limited to a person. For example, the target object may be a moving object other than a person (e.g., a car, a ship, a non-human animal, a robot, etc.).

[0031] In the first embodiment of the present invention, a basis function determination device 1 determines a basis function that serves as a basis for determining an area in which a target object exists, and an area determination device 2 determines an area in which the target object exists based on the basis function. A reference position is used to determine the basis function.

[0032] In the first embodiment of the present invention, it is mainly assumed that the reference position is the edge position (hereinafter simply referred to as "platform edge position") of a railway station platform (hereinafter simply referred to as "platform"). When the reference position is the platform edge position, it can be determined whether the target object is located in the platform side area or the track side area. However, as will be explained later, the reference position is not limited to the platform edge position.

[0033] In the first embodiment of the present invention, it is mainly assumed that the basis function determination device 1 and the area determination device 2 are realized by different devices. However, the basis function determination device 1 and the area determination device 2 may be realized by the same device.

[0034] [1-1. Configuration example of the basis function determination device 1] Fig. 1 is a block diagram showing an example of the functional configuration of a criterion function determination device 1 according to a first embodiment of the present invention. As shown in Fig. 1, the criterion function determination device 1 according to the first embodiment of the present invention includes a point cloud acquisition unit 20, an input point cloud storage unit 30, a home edge position acquisition unit 40, a criterion function determination unit 50, and a criterion function storage unit 60. The criterion function determination device 1 is also connected to a laser sensor 10 and an area determination device 2. First, the laser sensor 10 will be described, and then an example of the functional configuration of the criterion function determination device 1 will be described with reference to Fig. 1.

[0035] (Laser Sensor 10) The laser sensor 10 is a sensor that emits laser light and measures the three-dimensional position of an object as sensor data based on the reflected light. For example, the laser sensor 10 may be installed in a position (e.g., on the platform or around the platform) where it can measure the target object and the platform edge. The laser sensor may also be referred to as a LiDAR (Laser Imaging Detection and Ranging) sensor.

[0036] The laser sensor 10 corresponds to an example of a sensor that obtains the three-dimensional position of an object as sensor data. Therefore, various sensors other than a laser sensor (e.g., a distance measurement sensor) may be used instead of the laser sensor 10. For example, the sensor may be a radar (e.g., a millimeter-wave radar) that uses electromagnetic waves instead of laser light. Alternatively, the sensor may be a sonar that uses sound waves instead of laser light. Hereinafter, the sensor data obtained by the laser sensor 10 will also be referred to as "point cloud data" or "point cloud."

[0037] (Basis function determination device 1) The basis function determination device 1 is an information processing device realized by a computer. For example, the point cloud acquisition unit 20, the home edge position acquisition unit 40, and the basis function determination unit 50 can be realized by a control unit (not shown). On the other hand, the input point cloud storage unit 30 and the basis function storage unit 60 can be realized by a storage unit (not shown).

[0038] 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.

[0039] 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.

[0040] (Point cloud acquisition unit 20) The point cloud acquisition unit 20 acquires point cloud data (second sensor data) obtained by the laser sensor 10 as an input point cloud from the laser sensor 10. The point cloud acquisition unit 20 outputs the input point cloud acquired from the laser sensor 10 to the input point cloud storage unit 30.

[0041] (Input point cloud storage unit 30) The input point cloud storage unit 30 stores the input point cloud output from the point cloud acquisition unit 20. The input point cloud storage unit 30 also outputs the input point cloud to the platform edge position acquisition unit 40.

[0042] (Platform edge position acquisition unit 40) The platform edge position acquisition unit 40 acquires the platform edge position. The platform edge position acquisition unit 40 may acquire the platform edge position in any manner. As an example, the platform edge position acquisition unit 40 may display an input point cloud on a predetermined display using a point cloud display application or the like, and acquire as the platform edge position a position input by the user to a predetermined input device based on the input point cloud displayed on the display. Alternatively, as will be described later, the platform edge position acquisition unit 40 may acquire the platform edge position automatically, without relying on manual input by the user. The platform edge position acquisition unit 40 outputs the platform edge position to the basis function determination unit 50.

[0043] (Criterion function determination unit 50) The criterion function determination unit 50 determines the criterion function based on the home edge position. For example, the criterion function determination unit 50 may determine the criterion function by approximation based on the home edge position. The following describes a case where the approximation performed by the criterion function determination unit 50 is polynomial approximation. In this case, the criterion function may be a function expressed using a polynomial determined by polynomial approximation. In other words, the criterion function may be expressed by polynomial coefficients, which are coefficients of each dimension forming the polynomial.

[0044] In this specification, the term "polynomial" is not limited to a polynomial having multiple terms, but may include a polynomial having one term. Furthermore, in this specification, the term "polynomial" may be an expression whose highest degree is zero-dimensional or one or more dimensions. The criterion function determination unit 50 outputs the determined criterion function to the criterion function storage unit 60.

[0045] (Criterion function storage unit 60) The criterion function storage unit 60 stores the criterion function output from the criterion function determination unit 50. The criterion function stored by the criterion function storage unit 60 is output to a criterion function setting unit 120 included in the area determination device 2.

[0046] An example of the functional configuration of the criterion function determining device 1 according to the first embodiment of the present invention has been described above.

[0047] [1-2. Configuration example of area determination device 2] Fig. 2 is a block diagram showing an example of the functional configuration of an area determination device 2 according to a first embodiment of the present invention. As shown in Fig. 2, the area determination device 2 according to the first embodiment of the present invention includes a determination unit 71, a point cloud acquisition unit 80, an input point cloud storage unit 90, a background point cloud storage unit 100, and a basis function setting unit 120. The determination unit 71 includes an object detection unit 110 and an area determination unit 130. The area determination device 2 is also connected to a laser sensor 10, a display unit 140, and a basis function determination device 1. First, an example of the functional configuration of the area determination device 2 will be described with reference to Fig. 2, and then the display unit 140 will be described.

[0048] (Area determination device 2) The area determination device 2 is an information processing device realized by a computer. For example, the determination unit 71, the point cloud acquisition unit 80, and the basis function setting unit 120 may be realized by a control unit (not shown). On the other hand, the input point cloud storage unit 90 and the background point cloud storage unit 100 may be realized by a storage unit (not shown).

[0049] 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.

[0050] 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.

[0051] (Point cloud acquisition unit 80) The point cloud acquisition unit 80 acquires point cloud data (third sensor data) obtained by the laser sensor 10 as a background point cloud from the laser sensor 10 in a state where no target object is present in the measurement range of the laser sensor 10. The point cloud acquisition unit 80 outputs the background point cloud acquired from the laser sensor 10 to the background point cloud storage unit 100.

[0052] The point cloud acquisition unit 80 outputs the background point cloud to the background point cloud storage unit 100, and then acquires point cloud data (first sensor data) obtained by the laser sensor 10 as an input point cloud from the laser sensor 10. The point cloud acquisition unit 80 outputs the input point cloud acquired from the laser sensor 10 to the input point cloud storage unit 90.

[0053] (Input point cloud storage unit 90) The input point cloud storage unit 90 stores the input point cloud output from the point cloud acquisition unit 80. The input point cloud storage unit 90 also outputs the input point cloud to the object detection unit 110.

[0054] (Background point cloud storage unit 100) The background point cloud storage unit 100 stores the background point cloud output from the point cloud acquisition unit 80. The background point cloud storage unit 100 also outputs the background point cloud to the object detection unit 110.

[0055] (Judgment section 71) The determination unit 71 determines whether the representative position of an area including the target object (hereinafter also referred to as the "object area") is located in a first area or a second area based on the input point cloud output from the input point cloud storage unit 90 and the criterion function set by the criterion function setting unit 120. Hereinafter, the first area will also be referred to as the "platform side area," and the second area will also be referred to as the "track side area." The criterion function is a function that serves as a criterion for determining the area in which the representative position of the object area is located.

[0056] More specifically, the determination unit 71 determines whether the representative position of the object area is located in the platform side area or the track side area, based on the background point cloud output from the background point cloud storage unit 100, the input point cloud output from the input point cloud storage unit 90, and the criterion function set by the criterion function setting unit 120. The determination unit 71 outputs the determination result to the display unit 140.

[0057] (Object detection unit 110) The object detection unit 110 detects an object region based on the input point cloud output from the input point cloud storage unit 90. More specifically, the object detection unit 110 detects an object region based on the background point cloud output from the background point cloud storage unit 100 and the input point cloud output from the input point cloud storage unit 90. The object detection unit 110 detects a representative position of the object region from the detected object region. For example, the representative position of the object region may be the center position of the object region. The object detection unit 110 outputs the representative position of the object region to the area determination unit 130.

[0058] (Criteria function setting unit 120) The criterion function setting unit 120 sets the criterion function. More specifically, the criterion function setting unit 120 may set the criterion function by acquiring the criterion function output from the criterion function storage unit 60. The criterion function setting unit 120 outputs the set criterion function to the area determination unit 130.

[0059] (Area determination unit 130) Based on the representative position of the object region and the criterion function, the area determination unit 130 determines whether the representative position of the object region is located in the platform area or the trackside area. More specifically, the area determination unit 130 obtains an output value output from the criterion function in response to inputting the representative position of the object region as an input value into the criterion function. Then, based on the output value, the area determination unit 130 determines whether the representative position of the object region is located in the platform area or the trackside area, and obtains an area determination result.

[0060] Area determination unit 130 outputs the area determination result to display unit 140. This controls the display of the area determination result by display unit 140. For example, if a person visually recognizes the area determination result that the representative position of the object region is a trackside area, they can take some kind of action against the target object.

[0061] (Display section 140) Display unit 140 displays the determination result output from area determination unit 130. For example, display unit 140 may include a lamp and illuminate the lamp to display the determination result that the representative position of the object region is within the trackside area. Alternatively, display unit 140 may include a display and display a predetermined color (e.g., red) on the display to display the determination result that the representative position of the object region is within the trackside area.

[0062] The location where the display unit 140 is provided is not particularly limited. For example, the display unit 140 may be provided on a platform. Alternatively, the display unit 140 may be provided in a station office where station staff are present. Alternatively, the display unit 140 may be provided in a monitoring center where staff who monitor the train operation status are present.

[0063] An example of the functional configuration of the area determination device 2 according to the first embodiment of the present invention has been described above.

[0064] [1-3. Example of operation related to the criterion function determination stage] Next, an example of operation of the information processing system according to the first embodiment of the present invention will be described. The example of operation of the information processing system is divided into a first stage and a second stage that is performed after the first stage. The first stage is a criterion function determination stage. The second stage is an area determination stage. First, an example of operation of the criterion function determination device 1 in the criterion function determination stage will be described with reference to Figs. 3 to 6 (and also Fig. 1 as appropriate).

[0065] 3 is a flowchart showing an example of the operation of the criterion function determination device 1 in the criterion function determination stage. As shown in Fig. 3, in the criterion function determination stage, the point cloud acquisition unit 20 acquires point cloud data obtained by the laser sensor 10 from the laser sensor 10 as an input point cloud (step A1). The point cloud acquisition unit 20 outputs the input point cloud acquired from the laser sensor 10 to the input point cloud storage unit 30. The input point cloud storage unit 30 stores the input point cloud output from the point cloud acquisition unit 20. Then, the input point cloud storage unit 30 outputs the input point cloud to the home edge position acquisition unit 40.

[0066] Fig. 4 is a diagram showing an example of an input point cloud acquired in the basis function determination stage. As shown in Fig. 4, a coordinate system based on the laser sensor 10 (hereinafter also referred to as the "sensor coordinate system") is expressed by the x-axis, y-axis, and z-axis. The input point cloud measured by the laser sensor 10 is expressed by the x-coordinate, y-coordinate, and z-coordinate.

[0067] 4, the first car T1, the second car T2, the third car T3, and the fourth car T4 of the train, as well as the platform H1, are located within the measurement range of the laser sensor 10, and the positions of the surfaces of each car are obtained as an input point cloud. However, the train located within the measurement range of the laser sensor 10 does not have to be four cars. Alternatively, there does not have to be a train located within the measurement range of the laser sensor 10.

[0068] The platform edge position acquisition unit 40 sets counter j to 1 (step A2). If counter j is equal to or less than a predetermined threshold n ("YES" in step A3), the platform edge position acquisition unit 40 acquires the platform edge position aj(xj, yj) (step A4). The threshold n is an integer equal to or greater than 1.

[0069] The platform edge position may include a z-coordinate. However, in the following, to simplify the calculations, the platform edge position is assumed to be a position on the xy plane, and the explanation will proceed without including a z-coordinate for the platform edge position. Furthermore, three-dimensional coordinates (x, y, z) and two-dimensional coordinates (x, y) may be used appropriately to represent the positions of the input point cloud.

[0070] The platform edge position acquisition unit 40 may acquire the platform edge position aj(xj,yj) in any manner. As an example, the platform edge position acquisition unit 40 may display an input point cloud on a predetermined display using a point cloud display application or the like, and acquire the platform edge position aj(xj,yj) input by the user to a predetermined input device based on the input point cloud displayed on the display. Alternatively, as will be described later, the platform edge position acquisition unit 40 may automatically acquire the platform edge position aj(xj,yj) without manual input by the user.

[0071] The home edge position acquisition unit 40 increments the counter j by 1 (step A5) and proceeds to step A3. If the counter j is greater than the predetermined threshold n ("NO" in step A3), the home edge position acquisition unit 40 proceeds to step A6.

[0072] 4 shows the platform edge position a1(x1, y1), platform edge position a2(x2, y2), platform edge position a3(x3, y3), ..., platform edge position aj-1(xj-1, yj-1), platform edge position aj(xj, yj), ..., platform edge position an-1(xn-1, yn-1), and platform edge position an(xn, yn) acquired by the platform edge position acquisition unit 40. The platform edge position acquisition unit 40 outputs a1(x1, y1) to an(xn, yn) to the criterion function determination unit 50.

[0073] The criterion function determination unit 50 determines the criterion function y=f(x) based on the home edge positions a1(x1,y1) to an(xn,yn). For example, the criterion function determination unit 50 may determine the criterion function y=f(x) by polynomial approximation based on the home edge positions a1(x1,y1) to an(xn,yn) (step A6). The criterion function can be expressed by polynomial coefficients, which are coefficients of each dimension that form the polynomial.

[0074] More specifically, the criterion function determination unit 50 may determine the criterion function y=f(x) along the platform edge based on the platform edge positions a1(x1, y1) to an(xn, yn). For example, when the polynomial to be approximated is a quadratic expression, the criterion function y=f(x) is determined as shown in equation (1).

[0075] y=f(x)=ax 2 +bx+c···(1)

[0076] FIG. 5 is a diagram showing an example of an approximation curve corresponding to a reference function. Referring to FIG. 5, home edge positions a1(x1, y1) to an(xn, yn) are shown. Also, an approximation curve f(x, y)=y-(ax) corresponding to a reference function y=f(x) approximated to a quadratic equation based on the home edge positions a1(x1, y1) to an(xn, yn) is shown. 2 +bx+c)=0. Note that the approximate curve is an example of a figure corresponding to the criterion function. Therefore, the approximate curve corresponding to the criterion function may be replaced with another figure (for example, an approximate straight line, an approximate plane, or an approximate curved surface).

[0077] The basis function determination unit 50 determines the basis function y=f(x)=ax 2 +bx+c is output to the criterion function storage unit 60. Specifically, the criterion function determination unit 50 may output the polynomial coefficients (a, b, c) to the criterion function storage unit 60 (step A7).

[0078] The criterion function storage unit 60 stores the criterion function output from the criterion function determination unit 50. Specifically, the criterion function storage unit 60 may store the polynomial coefficients (a, b, c) output from the criterion function determination unit 50. The criterion function stored by the criterion function storage unit 60 is output to a criterion function setting unit 120 included in the area determination device 2.

[0079] FIG. 6 is a diagram showing an example of an approximation curve in a sensor coordinate system. Referring to FIG. 6, a laser sensor 10 is shown, and an xyz coordinate system, which is a sensor coordinate system based on the laser sensor 10, is shown. In addition, an approximation curve f(x, y)=y-(ax) corresponding to a reference function y=f(x) is shown in the xyz coordinate system, which is the sensor coordinate system. 2 +bx+c)=0. Also shown are a platform H1 in the real space and a train running surface L1 in the real space.

[0080] As shown in Fig. 6, the z-axis of the sensor coordinate system may be set along the vertical direction in real space. In this case, the x-axis and y-axis of the sensor coordinate system are set along the horizontal direction in real space and are orthogonal to the z-axis of the sensor coordinate system. Furthermore, the x-axis and y-axis of the sensor coordinate system are orthogonal to each other.

[0081] In the following description, it is mainly assumed that the sensor coordinate system is preset so that the upward direction of the vertical direction in real space is the +z direction, as shown in Fig. 6. However, the +z direction does not have to be the upward direction of the vertical direction in real space. For example, the sensor coordinate system may be preset so that the downward direction of the vertical direction in real space is the +z direction.

[0082] An example of the operation of the basis function determining device 1 in the basis function determining stage has been described above with reference to FIGS. 3 to 6 (and also with reference to FIG. 1 as appropriate).

[0083] [1-4. Example of operation related to the area determination stage] Next, an example of the operation of the area determination device 2 in the area determination step will be described with reference to Fig. 7 (and also with reference to Figs. 2 and 6 as appropriate). As described above, the area determination step is performed after the criterion function determination step.

[0084] Fig. 7 is a flowchart showing an example of the operation of the area determination device 2 in the area determination stage. As shown in Fig. 7, in the area determination stage, the criterion function setting unit 120 sets the criterion function by acquiring the criterion function output from the criterion function storage unit 60. More specifically, the criterion function determination unit 50 sets the criterion function by acquiring polynomial coefficients (a, b, c) from the criterion function storage unit 60 (step B1).

[0085] Next, the point cloud acquisition unit 80 acquires the point cloud data obtained by the laser sensor 10 as a background point cloud from the laser sensor 10 in a state where no target object is present in the measurement range of the laser sensor 10 (step B2). Here, it is assumed that a train, which is an object other than the target object, is present in the measurement range of the laser sensor 10. In other words, it is assumed that the background point cloud includes point cloud data corresponding to both the train and the platform.

[0086] The point cloud acquisition unit 80 outputs the background point cloud acquired from the laser sensor 10 to the background point cloud storage unit 100. Then, the background point cloud storage unit 100 stores the background point cloud output from the point cloud acquisition unit 80. The background point cloud storage unit 100 outputs the background point cloud to the object detection unit 110.

[0087] The object detection unit 110 acquires the input point cloud output from the input point cloud storage unit 90 (step B3). Then, the object detection unit 110 extracts, as a difference point cloud, a point cloud that is not included in the background point cloud from the input point cloud by performing background subtraction based on the background point cloud output from the background point cloud storage unit 100 and the input point cloud output from the input point cloud storage unit 90 (step B4). For example, a method using an Octree module of the Point Cloud Library (PCL) can be applied to extract the difference point cloud.

[0088] In order to improve the extraction accuracy of the difference point cloud, it is desirable to extract the difference point cloud expressed in three-dimensional coordinates based on the background point cloud expressed in three-dimensional coordinates and the input point cloud expressed in three-dimensional coordinates. However, the difference point cloud expressed in two-dimensional coordinates may also be extracted based on the background point cloud expressed in two-dimensional coordinates and the input point cloud expressed in two-dimensional coordinates.

[0089] The object detection unit 110 performs clustering on the extracted difference point clouds to extract clusters of the point clouds (step B5). For example, a method using the Kdtree module of the Point Cloud Library (PCL) can be applied to the clustering. Note that here, it is mainly assumed that the point clouds included in the clusters are represented by three-dimensional coordinates. However, the point clouds included in the clusters may also be represented by two-dimensional coordinates.

[0090] The object detection unit 110 defines the extracted cluster as a detected object point cloud, and detects an area having a predetermined shape containing the detected object point cloud as an object region (step B6). Here, it is assumed that the detected object point cloud and the object region are each expressed by three-dimensional coordinates. In this case, the object region may have a rectangular shape on a two-dimensional plane perpendicular to the z axis, with the base as the rectangular prism shape and the height direction along the z axis. FIG. 6 shows an object region in the shape of a quadrangular prism with vertices p1 and p2 as diagonals. Such an object region may be circumscribed around a person, as an example of a target object.

[0091] Alternatively, the detected object point cloud and the object region may each be expressed by two-dimensional coordinates. In this case, the predetermined shape may be a rectangular shape on a two-dimensional plane perpendicular to the z-axis. That is, object detection unit 110 may detect a rectangular region including the detected object point cloud (for example, a rectangular region circumscribing the detected object point cloud) as the object region.

[0092] The object detection unit 110 detects a representative position A(xa, ya, za) of the object region (step B7). For example, FIG. 6 shows an example in which the object detection unit 110 detects the center position of a quadrangular prism-shaped object region with vertices p1 and p2 as diagonals as the representative position A(xa, ya, za) of the object region. Similarly, FIG. 6 shows a representative position B(xb, yb, zb) after the representative position A has moved due to the movement of a person, an example of a target object. The object detection unit 110 outputs the representative position A(xa, ya, za) of the object region to the area determination unit 130.

[0093] The criterion function setting unit 120 sets the criterion function by acquiring the criterion function output from the criterion function storage unit 60. More specifically, the criterion function setting unit 120 acquires the polynomial coefficients (a, b, c) output from the criterion function storage unit 60, and sets the criterion function f(x, y)=y-(ax 2 The criterion function setting unit 120 sets the criterion function f(x, y)=y-(ax 2 +bx+c) to the area determination unit 130.

[0094] The area determination unit 130 receives the two-dimensional coordinates (xa, ya) of the representative position A of the object area as input values ​​and calculates a criterion function f(x, y)=y-(ax 2 In response to the input to the reference function f(x, y), the output value f(xa, ya) output from the reference function f(x, y) is calculated (step B8). As a result, the area determination unit 130 obtains the output value f(xa, ya). Based on the output value f(xa, ya), the area determination unit 130 determines whether the representative position A of the object region is located in the platform side area or the track side area, and obtains the area determination result.

[0095] For example, the area determination unit 130 determines whether the output value f(xa, ya) is equal to or greater than 0 (zero) to obtain the area determination result (step B9).

[0096] If the area determination unit 130 determines that the output value f(xa, ya) is 0 or greater ("YES" in step B9), it determines that the representative position A of the object region is in the trackside area, and sets the flag indicating the area determination result to 1 (= the value indicating the trackside area) (step B10). On the other hand, if the area determination unit 130 determines that the output value f(xa, ya) is less than 0 ("NO" in step B9), it determines that the representative position A of the object region is in the platform side area, and sets the flag indicating the area determination result to 0 (= the value indicating the platform side area) (step B11).

[0097] Area determination unit 130 outputs the area determination result to display unit 140 (step B12). Display unit 140 displays the area determination result output from area determination unit 130. For example, if a person visually recognizes the area determination result that the representative position of the object region is in the trackside area, they can take some kind of action against the target object.

[0098] An example of the operation of the area determination device 2 in the area determination stage has been described above with reference to FIG. 7 (and also with reference to FIGS. 2 and 6 as appropriate).

[0099] [1-5. Effects of the embodiment] As described above, according to the first embodiment of the present invention, an area determination device 2 is provided, which includes a point cloud acquisition unit 80 that acquires point cloud data obtained by the laser sensor 10, a reference function that serves as a criterion for determining an area in which a representative position of an object area exists, and a determination unit 71 that determines whether the representative position of the object area exists in a track-side area or a platform-side area based on the point cloud data.

[0100] With this configuration, the area in which the representative position of the object region exists is determined based on a preset basis function and point cloud data, which reduces the effort required for the user to set the detection area. Furthermore, with this configuration, the area in which the representative position of the object region currently exists can be directly determined, which makes it possible to improve the accuracy of determining the representative position of the object region.

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

[0102] 2. Second embodiment Next, the second embodiment of the present invention will be described in detail.

[0103] Like the information processing system according to the first embodiment of the present invention, the information processing system according to the second embodiment of the present invention includes a basis function determination device 1 and a laser sensor 10. On the other hand, the information processing system according to the second embodiment of the present invention differs from the information processing system according to the first embodiment of the present invention in that it includes an area determination device 3 (FIG. 8) instead of the area determination device 2 (FIG. 2).

[0104] Therefore, in the following description, the area determination device 3 provided in the information processing system according to the second embodiment of the present invention will be mainly described, and detailed descriptions of the basis function determination device 1 and the laser sensor 10 will be omitted.

[0105] [1-2. Configuration example of area determination device 3] Fig. 8 is a block diagram showing an example of the functional configuration of an area determination device 3 according to a second embodiment of the present invention. As shown in Fig. 8, the area determination device 3 according to the second embodiment of the present invention, like the area determination device 2 according to the first embodiment of the present invention, includes a point cloud acquisition unit 80, a background point cloud storage unit 100, and a criterion function setting unit 120. On the other hand, the area determination device 3 according to the second embodiment of the present invention differs from the area determination device 2 according to the first embodiment of the present invention in that it includes a determination unit 72 instead of the determination unit 71, and in that it includes a processing area cutout unit 200, a detection storage unit 210, and an area storage unit 240.

[0106] Therefore, in the following explanation, we will mainly explain the judgment unit 72, processing area cutout unit 200, detection memory unit 210, and area memory unit 240 related to the second embodiment of the present invention, and omit detailed explanations of the point cloud acquisition unit 80, background point cloud memory unit 100, and reference function setting unit 120.

[0107] (Area determination device 3) The area determination device 3 is an information processing device realized by a computer. For example, the determination unit 72 and the processing area cutout unit 200 can be realized by a control unit (not shown). On the other hand, the detection storage unit 210 and the area storage unit 240 can be realized by a storage unit (not shown).

[0108] (Processing area cutout unit 200) The processing area cutout unit 200 specifies, as a processing area, an area to be determined by the determination unit 72, based on the criterion function set by the criterion function setting unit 120. Then, the processing area cutout unit 200 acquires point cloud data within the processing area from the point cloud data acquired by the point cloud acquisition unit 80. The processing area cutout unit 200 outputs the point cloud data within the processing area to the object detection unit 110.

[0109] (Judgment unit 72) The determination unit 72 determines whether the representative position of the object area is located in the trackside area or the platform side area based on the criterion function set by the criterion function setting unit 120 and the point cloud data extracted by the processing area extraction unit 200. In this way, the point cloud data used for the determination by the determination unit 72 is limited to the point cloud data within the processing area, thereby reducing the time required for the determination by the determination unit 72.

[0110] The determination unit 72, like the determination unit 71 according to the first embodiment of the present invention, includes an object detection unit 110 and an area determination unit 130. On the other hand, the determination unit 72 differs from the determination unit 71 according to the first embodiment of the present invention in that it includes an object tracking unit 230 and a movement determination unit 250. Therefore, in the following description, the object tracking unit 230 and the movement determination unit 250 according to the second embodiment of the present invention will be mainly described, and a detailed description of the object detection unit 110 and the area determination unit 130 will be omitted.

[0111] (Detection storage unit 210) The detection storage unit 210 stores the representative position of the object region detected by the object detection unit 110 from point cloud data previously detected by the laser sensor 10 (hereinafter also referred to as "past frame") as the representative position of the object region in the past frame. In addition, the detection storage unit 210 outputs the representative position of the object region in the past frame to the object tracking unit 230.

[0112] (Object tracking unit 230) The object tracking unit 230 performs object tracking based on the representative position of the object region detected by the object detection unit 110 from the point cloud data currently detected by the laser sensor 10 (hereinafter also referred to as the "current frame") and the representative position of the object region in the past frame. The representative position of the object region in the past frame may correspond to a first object region at a first time. The representative position of the object region in the current frame may correspond to a second representative position of a second object region at a second time after the first time.

[0113] More specifically, the object tracking unit 230 calculates the distance between the representative position of the object region in the current frame and the representative position of the object region in the past frame, and if the calculated distance is smaller than a threshold, it matches the representative position of the object region in the current frame with the representative position of the object region in the past frame as the positions of the same object.

[0114] (Area storage unit 240) The area storage unit 240 stores, as a past area determination result, the determination result obtained by the area determination unit 130 as to whether the representative position of the object area in the past frame is located in the track-side area or the platform-side area. The area storage unit 240 also outputs the past area determination result to the movement determination unit 250.

[0115] (Movement determination unit 250) The movement determination unit 250 acquires past area determination results from the area storage unit 240. The movement determination unit 250 also acquires, as the current area determination result, the determination result obtained by the area determination unit 130 as to whether the representative position of the object area in the current frame is located in the track-side area or the platform-side area.

[0116] Based on the past area determination results and the current area determination results, the movement determination unit 250 determines whether the same object has moved between the track side area and the platform side area based on whether the representative position of the object area in the past frame and the representative position of the object area in the current frame, which have been associated by the object tracking unit 230 as representative positions of the object area of ​​the same object, are in the same area or different areas, and obtains an inter-area movement determination result.

[0117] Furthermore, the movement determination unit 250 outputs the inter-area movement determination result to the display unit 140. This controls the display of the inter-area movement determination result by the display unit 140. For example, a person who visually recognizes an inter-area movement determination result indicating that the representative position of the object area has moved from the platform side area to the track side area can take some kind of action regarding the target object. Note that in the following description, the movement of the same object from the track side area to the platform side area is also referred to as the "fall" of the same object from the track side area to the platform side area. Furthermore, "fall" can also be expressed as "tumble."

[0118] [1-3. Example of operation related to the area determination stage] Next, an example of the operation of the area determination device 3 in the area determination stage will be described with reference to Figures 9 to 12 (and also with reference to Figures 2 and 6 as appropriate). As described above, the area determination stage is performed after the criterion function determination stage.

[0119] 9 and 10 are flowcharts showing an example of the operation of the area determination device 3 in the area determination stage. As shown in Fig. 9, step C1 is executed, which is executed in the same manner as step B1 (Fig. 7) executed by the area determination device 2 according to the first embodiment of the present invention.

[0120] Next, the processing area cutout unit 200 specifies, as a processing area, an area to be determined by the determination unit 72, based on the criterion function set by the criterion function setting unit 120. An example of a processing area specified by the processing area cutout unit 200 will be described with reference to FIG.

[0121] FIG. 11 is a diagram showing an example of a processing area identified by the processing area cutout unit 200. In the following, as shown in FIG. 11, a case where a processing area (upper) R1 and a processing area (lower) R2 are identified as examples of processing areas will be mainly assumed. The processing area (upper) R1 may correspond to the first processing area. Furthermore, the processing area (lower) R2 may correspond to the second processing area. Furthermore, an approximate curve f(x,y)=y-(ax 2 +bx+c)=0 is shown.

[0122] The processing area (upper) R1 is located in an area in the sensor coordinate system that corresponds to an area located above a predetermined horizontal plane (for example, the surface of the platform in the real space) that is perpendicular to the vertical direction in the real space. Also, the processing area (upper) R1 is located in an area in the sensor coordinate system that corresponds to an approximate curve f(x,y)=y-(ax 2The processing area cutout unit 200 calculates the approximate curve f(x, y)=y-(ax + bx + c)=0 in the xyz coordinate system, which is the sensor coordinate system based on the laser sensor 10, by dividing the sensor coordinate space xyz (or the sensor coordinate plane xy) into two areas by f(x, y)=0. For example, the one area is an area in the sensor coordinate space xyz (or the sensor coordinate plane xy) where f(x, y)<0. More specifically, when the z coordinate in the sensor coordinate system, which corresponds to the height of the platform in the real space, is set to z0, the processing area cutout unit 200 calculates the approximate curve f(x, y)=y-(ax + bx + c)=0 in the xyz coordinate system, which is the sensor coordinate system based on the laser sensor 10, by dividing the sensor coordinate space xyz (or the sensor coordinate plane xy) into two areas by f(x, y)=0. 2 Using the approximate curve h(x, y)=x-(a, b, c)=0 as a reference, the processing area with a large z-coordinate and a small y-coordinate is specified as the processing area (upper) R1. 2 In cases where x and y are reversed, such as when z=z0, the approximate curve h(x, y)=0 is set as the reference, and the processing area with a large z coordinate and a small x coordinate can be identified as the processing area (upper) R1.

[0123] Furthermore, the processing area (lower) R2 may be an area in the sensor coordinate system that corresponds to an area located below a predetermined horizontal plane that is orthogonal to the vertical direction in real space. Also, the processing area (lower) R2 may be an area in the sensor coordinate system that corresponds to an approximate curve f(x,y)=y-(ax 2 The sensor coordinate space xyz (or the sensor coordinate plane xy) is divided into two areas by f(x, y)=0, and the area exists in the other of the two areas. For example, the other area is an area in the sensor coordinate space xyz (or the sensor coordinate plane xy) that satisfies f(x, y)≧0. More specifically, the processing area cutout unit 200 calculates the approximate curve f(x, y)=y-(ax+bx+c) set at z=z0. 2 Using the approximate curve h(x, y)=x-(a, b, c)=0 as a reference, the processing area with a small z-coordinate and a large y-coordinate is identified as the processing area (lower) R2. 2In cases where x and y are reversed, such as when z=z0, the approximate curve h(x, y)=0 is set as the reference, and the processing area with the small z coordinate and the large x coordinate can be identified as the processing area (lower) R2.

[0124] 11, the processing area (upper) R1 has a length in the x-axis direction from point Q1 to point Q2 through which the approximate curve f(x, y) = 0 passes, a width w1 in the y-axis direction, and a height h1 in the z-axis direction. On the other hand, the processing area (lower) R2 has a length in the x-axis direction from point Q1 to point Q2 through which the approximate curve f(x, y) = 0 passes, a width w2 in the y-axis direction, and a height h2 in the z-axis direction.

[0125] The processing area cutout unit 200 acquires point cloud data within the processing area (upper) R1 from the point cloud data acquired by the point cloud acquisition unit 80 (step C2). Furthermore, the processing area cutout unit 200 acquires point cloud data within the processing area (lower) R2 from the point cloud data acquired by the point cloud acquisition unit 80 (step C3). The processing area cutout unit 200 outputs the acquired point cloud data to the object detection unit 110.

[0126] Next, the point cloud acquisition unit 80 acquires a preset maximum number of processing times N (step C4). In addition, the point cloud acquisition unit 80 initializes a counter j for counting the number of processing times by setting the counter j to 0 (zero) (step C5).

[0127] Subsequently, step C6 is executed, which is executed in the same manner as step B2 (FIG. 7) executed by the area determination device 2 according to the first embodiment of the present invention.

[0128] The point cloud acquisition unit 80 determines whether the counter j is smaller than the maximum number of processing times N (step C7). If the point cloud acquisition unit 80 determines that the counter j is equal to or greater than the maximum number of processing times N ("NO" in step C7), it ends its operation. On the other hand, if the point cloud acquisition unit 80 determines that the counter j is smaller than the maximum number of processing times N ("YES" in step C7), it proceeds to step C8.

[0129] Subsequently, steps C8 to C10 are executed, which are executed in the same manner as steps B3 to B5 (FIG. 7) executed by the area determination device 2 according to the first embodiment of the present invention.

[0130] Object detection unit 110 defines the extracted cluster as a detected object point group, and detects an area having a predetermined shape that includes the detected object point group as an object area. Then, object detection unit 110 detects a representative position c(j) of the object area (step C11).

[0131] For example, Fig. 11 shows an example in which object detection unit 110 detects the center position of an object region as a representative position c(1) = (x1, y1, z1) of the object region. Similarly, Fig. 11 shows the representative positions after representative position c(1) moves as a person, an example of a target object, moves, as follows: c(2) = (x2, y2, z2) and c(3) = (x3, y3, z3). Object detection unit 110 outputs the representative position c(j) of the object region to detection storage unit 210, thereby causing detection storage unit 210 to store the representative position c(j) of the object region (step C12).

[0132] Next, the object tracking unit 230 determines whether the counter j is greater than 0 (step C13). If it is determined that the counter j is equal to or less than 0 ("NO" in step C13), the operation proceeds to step C23. On the other hand, if the object tracking unit 230 determines that the counter j is greater than 0 ("YES" in step C13), it calculates the distance d between the representative position c(j) of the object region in the current frame and the representative position c(j-1) of the object region in the previous frame (step C14). For example, if the distance d is a Euclidean distance, the distance d is calculated by the following equation (2).

[0133] d(c(j),c(j-1))=sqrt((xj-x(j-1)) 2 + (yj-y(j-1)) 2 +(zj-z(j-1)) 2 )···(2)

[0134] The object tracking unit 230 determines whether the distance d is smaller than a threshold value Dmax (step C15). If it is determined that the distance d is equal to or greater than the threshold value Dmax ("NO" in step C15), the operation proceeds to step C23. On the other hand, if the object tracking unit 230 determines that the distance d is smaller than the threshold value Dmax ("YES" in step C15), the object tracking unit 230 associates the representative position c(j-1) of the object region in the past frame with the representative position c(j) of the object region in the current frame as positions of the same object (step C16).

[0135] The area determination unit 130 calculates the output value f(xj, yj) output from the criterion function f(x, y) in response to inputting the representative position c(j)=(xj, yj) of the object area in the current frame into the criterion function f(x, y) as shown in the following equation (3) (step C17).

[0136] f(xj,yj)=yj-(axj 2 +bxj+c)···(3)

[0137] The area determination unit 130 determines whether the representative position c(j) of the object region is located in the platform side area or the track side area based on the output value f(xj, yj), and obtains the area determination result. For example, the area determination unit 130 determines whether the output value f(xj, yj) is equal to or greater than 0 (zero) and obtains the area determination result (step C18).

[0138] If the area determination unit 130 determines that the output value f(xj, yj) is 0 or greater ("YES" in step C18), it determines that the representative position c(j) of the object region is in the trackside area, and sets Flag(j), which indicates the area determination result, to 1 (=value indicating the trackside area) (step C19). The area determination unit 130 stores Flag(j), which indicates the area determination result, in the area storage unit 240, and outputs it to the movement determination unit 250. Then, the operation proceeds to step C21.

[0139] On the other hand, if the area determination unit 130 determines that the output value f(xj, yj) is less than 0 ("NO" in step C18), it determines that the representative position c(j) of the object region is present in the home side area, and sets Flag(j), which indicates the area determination result, to 0 (= the value indicating the home side area) (step C20). The area determination unit 130 stores Flag(j), which indicates the area determination result, in the area storage unit 240, and outputs it to the movement determination unit 250. Then, the operation proceeds to step C23.

[0140] The movement determination unit 250 determines whether the same object has moved between the platform side area and the track side area based on whether Flag(j-1) and Flag(j) are the same.

[0141] For example, the movement determination unit 250 acquires Flag(j-1) indicating the determination result of the representative position c(j-1) of the object region in the past frame, which is associated with the representative position c(j) of the object region in the current frame, as the representative position of the same object, from the area storage unit 240. Here, a case where the same object falls from the platform side area to the track side area will be described with reference to Fig. 12.

[0142] 12 is a diagram for explaining a case where the same object falls from the platform side area to the track side area. As shown in FIG. 12, if the representative position c(j-1) of the object area is in the processing area (upper) R1, Flag(j-1) is set to 0 (= the value indicating the platform side area). On the other hand, if the representative position c(j) of the object area is in the processing area (lower) R2, Flag(j) is set to 1 (= the value indicating the track side area).

[0143] In step C19, Flag(j) has already been set to 1 (=value indicating the trackside area), so the movement determination unit 250 determines whether Flag(j-1) is 0 or not (step C21).

[0144] If the movement determination unit 250 determines that Flag(j-1) is not 0 ("NO" in step C21), it is assumed that the same object has not fallen from the platform side area to the track side area because Flag(j-1) and Flag(j) are the same. Therefore, the movement determination unit 250 increments counter j (step C23). Then, the operation proceeds to step C7.

[0145] On the other hand, if the movement determination unit 250 determines that Flag(j-1) is 0 ("YES" in step C21), it is assumed that the same object has fallen from the platform area to the trackside area because Flag(j-1) and Flag(j) are different. Therefore, the movement determination unit 250 determines that the object has fallen from the platform area to the trackside area (step C22).

[0146] Movement determination unit 250 outputs an inter-area movement determination result indicating that the target object has fallen from the platform side area to the track side area to display unit 140. Display unit 140 then displays the inter-area movement determination result. For example, a person who visually recognizes an inter-area movement determination result indicating that the target object has fallen from the platform side area to the track side area can take some kind of action regarding the target object.

[0147] An example of the operation of the area determination device 3 in the area determination stage has been described above with reference to FIGS. 9 to 12 (and also with reference to FIGS. 2 and 6 as appropriate).

[0148] [2-4. Effects of the embodiment] As described above, according to the second embodiment of the present invention, the same effects as those of the first embodiment of the present invention are achieved.

[0149] Furthermore, according to the second embodiment of the present invention, the area determination device 3 is provided with the processing area cutout unit 200, so that the point cloud data to be processed is limited to the interior of the processing area (upper) R1 and the processing area (lower) R2. This reduces the processing time and improves the accuracy of area determination, which indicates whether the target object is located in the platform side area or the track side area.

[0150] Furthermore, according to the second embodiment of the present invention, the area determination device 3 is equipped with an object tracking unit 230 and a movement determination unit 250, so that it can be determined with high accuracy that the same object has fallen from the platform side area to the track side area.

[0151] The area determination device 3 according to the second embodiment of the present invention may include some of the processing area cutout unit 200, the object tracking unit 230, and the movement determination unit 250. For example, the area determination device 3 according to the second embodiment of the present invention may include the processing area cutout unit 200, but may not include the object tracking unit 230 and the movement determination unit 250. Conversely, the area determination device 3 according to the second embodiment of the present invention may include the object tracking unit 230 and the movement determination unit 250, but may not include the processing area cutout unit 200.

[0152] The effects of the second embodiment of the present invention have been described above.

[0153] <3. Various Modifications> Next, various modified examples will be described.

[0154] (First Modification) FIG. 13 is a diagram for explaining a first modified example. As shown in the left diagram of FIG. 13, in the second embodiment of the present invention, it is mainly assumed that the determination unit 71 determines whether the representative position of the object region is located in the platform-side area or the track-side area based on the input point cloud output from the input point cloud storage unit 90 and the criterion function f(x, y). Hereinafter, the track-side area may include a third area and a fourth area. Hereinafter, the third area will also be referred to as a "gap area" located between the train and the platform, and the fourth area will also be referred to as a "train area." In this case, the determination unit 71 may determine whether the representative position of the object region is located in the gap area or the train area based on the input point cloud and another criterion function g(x, y) obtained by adding a constant to the criterion function f(x, y).

[0155] As shown in the left diagram of FIG. 13, the approximate curve corresponding to the other reference function is a curve g(x,y)=y-(ax) obtained by shifting the approximate curve f(x,y)=0 corresponding to the reference function f(x,y) determined by approximation by a predetermined width Δy in the positive direction of the y axis. 2 +bx+c+Δy)=0. That is, the area determination unit 130 may obtain another criterion function g(x,y) by adding a constant Δy to the criterion function f(x,y). Note that Δy may be determined in advance. For example, Δy may be determined to be approximately the same as the distance between the edge of the platform and the train.

[0156] The area determination unit 130 may calculate an output value g(xj, yj) output from another criterion function g(x, y), and determine whether the representative position c(j) of the object region is in a gap area or a train area based on the output value g(xj, yj). For example, when the area determination unit 130 determines that the output value g(xj, yj) is equal to or greater than 0, it may determine that the representative position c(j) of the object region is in a train area. On the other hand, when the area determination unit 130 determines that the output value g(xj, yj) is less than 0, it may determine that the representative position c(j) of the object region is in a gap area. At this time, as shown in the right diagram of FIG. 13, the processing area cutout unit 200 may calculate a curve g(x, y)=y-(ax 2 +bx+c+Δy) = 0 as the reference, the area with a large z coordinate and a large y coordinate is identified as the processing area (upper) R4, and the curve corresponding to the other reference function g(x, y) = y-(ax 2 If we use z-coordinate +bx+c+Δy)=0 as the reference and identify the area with a small z-coordinate and a small y-coordinate as the processing area (bottom) R3, we can determine whether an object has fallen from the train into the gap between the edge of the platform and the train.

[0157] 13 illustrates a case where the first modified example is applied to the second embodiment of the present invention. However, the first modified example may also be applied to the first embodiment of the present invention. That is, the determination unit 71 may determine whether the representative position of the object region is in a gap area or a train area based on the input point cloud and another criterion function g(x, y) obtained by changing the criterion function f(x, y). However, the processing area cutout unit 200 may not specify the processing area (upper) R4 and the processing area (lower) R3.

[0158] (Second Modification) 14 is a diagram for explaining a second modified example. In the second embodiment of the present invention, it is mainly assumed that c(j-1) and c(j) correspond to each other as representative positions of the object region of the same object, and when c(j-1) is in the platform area and c(j) is in the trackside area, it is determined that the same object has fallen from the platform area to the trackside area.

[0159] However, in the second embodiment of the present invention, the movement determination unit 250 may determine whether the same object has fallen from the platform area to the trackside area based on the z coordinates of two representative positions associated as representative positions of the object region of the same object. More specifically, the movement determination unit 250 may determine whether the same object has fallen from the platform area to the trackside area based on whether the difference between the z coordinates of two representative positions associated as representative positions of the object region of the same object is greater than a predetermined value. The z coordinate may correspond to a coordinate on a coordinate axis set along the vertical direction in real space.

[0160] These two representative positions may be the maximum and minimum values ​​among the multiple representative positions. Referring to Fig. 14, representative positions c(j-4) to c(j+4) of the object area are shown, and among these representative positions, the z coordinate of representative position c(j-4) is the maximum value (max zj), and the z coordinate of representative position c(j+4) is the minimum value (min zj). The movement determination unit 250 may determine whether the same object has fallen from the platform-side area to the track-side area based on whether the difference ΔH between the maximum and minimum values ​​is greater than a predetermined value.

[0161] (Third Modification) 15 is a diagram for explaining a third modified example. In the second embodiment of the present invention, it is assumed that the movement determination unit 250 determines that the representative position c(j-1) and the representative position c(j), which are associated as representative positions of the object region of the same object, are located in different areas. More specifically, it is assumed that the movement determination unit 250 determines that the representative position c(j-1) is located in the platform side area and the representative position c(j) is located in the track side area.

[0162] In such a case, the movement determination unit 250 may determine whether the same object has fallen from the platform side area to the track side area based on whether the difference between the statistical processing result (first statistical processing result) for the representative position of the object area of ​​the same object detected before representative position c(j-1) and the statistical processing result (second statistical processing result) for the representative position of the object area of ​​the same object detected after representative position c(j) is greater than a predetermined value. This allows for more accurate determination results to be obtained.

[0163] The statistical processing may be processing for calculating an average value. Referring to FIG. 15, representative positions c(j-4) to c(j-1) of the object region of the same object that were detected before representative position c(j-1) are shown. Also shown are representative positions c(j) to c(j+4) of the object region of the same object that were detected after representative position c(j). The movement determination unit 250 may calculate an average value Ave1 of c(j-4) to c(j-1) and an average value Ave2 of c(j) to c(j+4), and determine whether the same object has fallen from the platform side area to the track side area based on whether the difference between the average values ​​Ave1 and Ave2 is greater than a predetermined value.

[0164] (Fourth Modification) In the above, it is mainly assumed that the platform edge position acquisition unit 40 acquires as the platform edge position a position input by the user to a specified input device based on the input point cloud displayed on the display. However, the platform edge position acquisition unit 40 may acquire the platform edge position automatically without relying on manual input by the user.

[0165] For example, the platform edge position acquisition unit 40 may detect the position of an edge detected from the input point cloud as the platform edge position.

[0166] Alternatively, the platform edge position acquisition unit 40 may acquire position information obtained by a GNSS (Global Navigation Satellite System) sensor installed at the platform edge. The platform edge position acquisition unit 40 may then convert the position information into position information in the coordinate system of the laser sensor 10 based on the correspondence between the coordinate system of the laser sensor 10 and the coordinate system of the GNSS sensor. The platform edge position acquisition unit 40 may then determine the basis function by polynomial approximation based on the position information in the coordinate system of the laser sensor 10. The correspondence between the coordinate system of the laser sensor 10 and the coordinate system of the GNSS sensor may be measured in advance.

[0167] Alternatively, the platform edge position acquisition unit 40 may acquire position information obtained by a laser scanner installed at the platform edge. The platform edge position acquisition unit 40 may then convert this into position information in the coordinate system of the laser sensor 10 based on the correspondence between the coordinate system of the laser sensor 10 and the coordinate system of the laser scanner. The platform edge position acquisition unit 40 may then determine the reference function by polynomial approximation based on the position information in the coordinate system of the laser sensor 10. The correspondence between the coordinate system of the laser sensor 10 and the coordinate system of the laser scanner may be measured in advance.

[0168] Various modifications have been described above.

[0169] <4. Hardware configuration example> Next, an example of the hardware configuration of the area determination device 2 according to an 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 area determination device 2 according to an 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 area determination device 2. Therefore, the hardware configuration of the area determination device 2 may be such that unnecessary components are deleted from the hardware configuration of the information processing device 900 described below, or new components may be added. Note that the hardware of each of the basis function determination device 1 and the area determination device 3 can be realized in a similar manner.

[0170] 16 is a diagram showing a hardware configuration of an information processing device 900 as an example of the area determination device 2 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] An example of the hardware configuration of the area determination device 2 according to the embodiment of the present invention has been described above.

[0178] <5. 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]

[0179] 1. Basis function determination device 10 Laser Sensor 100 Background point cloud storage 110 Object detection unit 120 Reference function setting section 130 Area determination unit 140 Display section 2, 3 Area determination device 20 point cloud acquisition section 200 Processing area cutout 210 Detection memory unit 230 Object Tracking Unit 240 Area Memory Unit 250 Movement determination section 30 Input point cloud storage unit 40 Platform edge position acquisition unit 50 Criterion function determination unit 60 Criterion function memory section 71, 72 Judgment section 80 point cloud acquisition section 90 Input point cloud storage unit

Claims

1. a sensor data acquisition unit that acquires sensor data obtained by a sensor; a determination unit that determines whether the representative position is present in a first area or a second area based on a reference function that serves as a reference for determining an area in which a representative position of an object region exists and the sensor data; An information processing device comprising:

2. The information processing device includes: a processing area cutout unit that cuts out the sensor data within a predetermined processing area; the determination unit determines whether the representative position is located in the first area or the second area based on the criterion function and the sensor data. The information processing device according to claim 1 .

3. the processing area includes a first processing area in a sensor coordinate system corresponding to an area located above a predetermined horizontal plane orthogonal to a vertical direction in real space, and a second processing area in the sensor coordinate system corresponding to an area located below the predetermined horizontal plane; The information processing device according to claim 2 .

4. a sensor coordinate space or a sensor coordinate plane is divided into two areas by a figure corresponding to the basis function, and the first processing area exists in one of the two areas, and the second processing area exists in the other area; The information processing device according to claim 3 .

5. the determination unit detects the object region based on the sensor data, and an object detection unit detects the representative position of the object region; an area determination unit that determines whether the representative position is located in the first area or the second area based on the representative position and the reference function; The information processing device according to any one of claims 1 to 4, comprising:

6. the area determination unit acquires an output value output from the criterion function in response to inputting the representative position as an input value into the criterion function, and determines whether the representative position exists in the first area or the second area based on the output value. The information processing device according to claim 5 .

7. the object detection unit detects a first representative position of a first object region at a first time and a second representative position of a second object region at a second time after the first time; The determination unit an object tracking unit that calculates a distance between the first representative position and the second representative position, and associates the first representative position with the second representative position when the distance is smaller than a threshold; The determination unit a movement determination unit that determines whether the same object has moved between the first area and the second area based on whether the associated first representative position and the associated second representative position are located in the same area or in different areas; The information processing device according to claim 5 .

8. When it is determined that the associated first representative position and the second representative position exist in different areas, the movement determination unit determines whether the same object has moved between the first area and the second area based on whether a difference between a first statistical processing result for the representative position of the object region of the same object before the first time point and a second statistical processing result for the representative position of the object region of the same object after the second time point is greater than a predetermined value. The information processing device according to claim 7 .

9. The coordinate axes are set along the vertical direction in real space, the first statistical processing result is an average value of coordinates on the coordinate axes of representative positions of object regions of the same object before the first time point, the second statistical processing result is an average value of coordinates on the coordinate axes of representative positions of object regions of the same object after the second time point; The information processing device according to claim 8 .

10. the object detection unit detects a first representative position of a first object region at a first time and a second representative position of a second object region at a second time after the first time; The determination unit an object tracking unit that calculates a distance between the first representative position and the second representative position, and associates the first representative position with the second representative position when the distance is smaller than a threshold; The coordinate axes are set along the vertical direction in real space, The determination unit a movement determination unit that determines whether the same object has moved between the first area and the second area based on a coordinate of the first representative position on the coordinate axis and a coordinate of the second representative position on the coordinate axis, which are associated as representative positions of the object area of ​​the same object in a sensor coordinate system based on the sensor; The information processing device according to claim 5 .

11. the movement determination unit determines whether the same object has moved between the first area and the second area based on whether a difference between a coordinate of the first representative position on the coordinate axis and a coordinate of the second representative position on the coordinate axis is greater than a predetermined value. The information processing device according to claim 10.

12. The basis function is determined by approximation based on position information input by a user, position information obtained by a GNSS sensor or a laser scanner. The information processing device according to claim 1 .

13. the second area includes a third area and a fourth area, the determination unit determines whether the representative position is located in the third area or the fourth area based on another criterion function obtained by adding a constant to the criterion function and the sensor data. The information processing device according to claim 12.

14. the approximation is a polynomial approximation, the reference function is a function expressed using a polynomial determined by the polynomial approximation. The information processing device according to claim 12.

15. the criterion function is determined by approximation based on position information input by the user; The information processing device according to claim 12.

16. The reference function is determined by converting position information obtained by a GNSS sensor or a laser scanner into position information in a sensor coordinate system based on the sensor, and approximating the position information in the sensor coordinate system. The information processing device according to claim 12.

17. acquiring sensor data obtained by a sensor; determining whether the representative position of the object region is located in a first area or a second area based on a reference function serving as a reference for determining an area in which the representative position of the object region is located and the sensor data; 2. A computer-implemented information processing method, comprising:

18. Computer, a sensor data acquisition unit that acquires sensor data obtained by a sensor; a determination unit that determines whether the representative position is present in a first area or a second area based on a reference function that serves as a reference for determining an area in which a representative position of an object region exists and the sensor data; A program that functions as a

Images