Information Processing Apparatus, Information Processing Method, and Program

Abstract

It is desired to provide a technology capable of improving the determination accuracy of the object position while reducing the labor required for the user. 【Solution means】An information processing apparatus is provided, which includes an object detection unit that detects an object region based on first sensor data obtained by a sensor, a graphic element passing through a plurality of positions included in the object region, and a position determination unit that determines the object position by determining whether or not the graphic element intersects a reference function serving as a reference for determining the object position.

Description

Technical Field

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

Background Art

[0002] In recent years, a technique for detecting an object based on data obtained by a sensor (hereinafter also referred to as "sensor data") is known (see, for example, Patent Document 1). The detection result of an object can be used in various scenes. For example, a technique for determining whether an object exists inside a preset area (hereinafter also referred to as a "detection area") based on the detection result of the object is known. For example, in such a technique, a person is mainly assumed as the object.

[0003] More specifically, in such a technique, a polygonal detection area is set on a two-dimensional plane. For example, the polygon may include a rectangle or the like. Then, it is determined whether the object exists in the detection area based on whether the contour (for example, vertices or sides) of the object area detected from the image obtained by the camera enters the detection area. For example, the object area is a rectangular area including the object shown in the image.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the setting of the detection area is generally performed based on a plurality of straight lines specified by the user so as to surround the range (hereinafter also referred to as the "detection required range") in which it is to be determined whether an object exists.

[0006] Therefore, when the detection request range is narrow or curved, etc., if the user tries to specify a position just outside the detection request range, it will take a lot of time and effort for the user.

[0007] On the other hand, if the detection area is made too wide compared to the detection request range, a situation may occur where an object existing outside the detection request range is determined to exist within the detection area. Therefore, there may also be a possibility that false detections of objects occur frequently.

[0008] Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to provide a technology capable of improving the determination accuracy of the object position while reducing the time and effort required for the user.

Means for Solving the Problems

[0009] In order to solve the above problems, according to an aspect of the present invention, an object detection unit that detects an object area based on first sensor data obtained by a sensor, a graphic element passing through a plurality of positions included in the object area, and a position determination unit that determines the object position by determining whether or not the graphic element intersects a reference function serving as a reference for determining the object position are provided. , the reference function is determined by an approximation based on the position input by the user, the approximation is a polynomial approximation, and the reference function is a function represented by using the polynomial determined by the polynomial approximation. An information processing apparatus is provided.

[0011] The reference function may be determined by converting the position information obtained by the GNSS sensor into the position information in the coordinate system of the sensor and approximating based on the position information in the coordinate system of the sensor.

[0013] The graphic element may be a line segment or a plane.

[0014] When the graphic element intersects the reference function, the position determination unit may determine that the object position is inside the area sandwiched between the train on the line and the platform, and when the graphic element does not intersect the reference function, the position determination unit may determine that the object position is outside the area.

[0015] When the shape element and the reference function intersect, the position determination unit may determine that the object position is inside a predetermined driving lane, and when the shape element and the reference function do not intersect, the position determination unit may determine that the object position is outside the predetermined driving lane.

[0016] When the shape element and the reference function intersect, the position determination unit may determine that the object position is on the boundary line between the outside and the inside of a predetermined driving lane, and when the shape element and the reference function do not intersect, the position determination unit may determine that the object position is not on the boundary line.

[0017] According to another aspect of the present invention for solving the above problems, detecting an object area based on first sensor data obtained by a sensor, a shape element passing through a plurality of positions included in the object area, and determining whether the shape element intersects a reference function serving as a reference for determining an object position, thereby determining the object position, are included , the reference function is determined by an approximation based on the position input by the user, the approximation is a polynomial approximation, and the reference function is a function represented by using the polynomial determined by the polynomial approximation. An information processing method executed by a computer is provided.

[0018] According to another aspect of the present invention for solving the above problems, a computer is caused to function as an object detection unit that detects an object area based on first sensor data obtained by a sensor, and a position determination unit that determines the object position by determining whether a shape element passing through a plurality of positions included in the object area intersects a reference function serving as a reference for determining the object position , the reference function is determined by an approximation based on the position input by the user, the approximation is a polynomial approximation, and the reference function is a function represented by using the polynomial determined by the polynomial approximation. A program is provided.

Advantages of the Invention

[0019] As described above, according to the present invention, a technique capable of improving the determination accuracy of an object position while reducing the labor required for a user is provided.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0021] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0022] <1. Details of the Embodiment> Subsequently, details of the embodiments of the present invention will be described. The information processing system according to the embodiments of the present invention includes a laser sensor 10 (FIGS. 1 and 2), a reference function determination device 1 (FIG. 1), and an object position determination device 2 (FIG. 2).

[0023] In the embodiments of the present invention, it is mainly assumed that the object whose position is determined by the object position determination device 2 (hereinafter also referred to as "target object") is a person. However, the target object is not limited to a person. For example, the target object may be a moving body other than a person (e.g., an automobile, a ship, an animal other than a person, a robot, etc.).

[0024] In the embodiments of the present invention, the reference function determination device 1 determines a reference function that serves as a reference for determining the position of the target object, and the object position determination device 2 determines the position of the target object based on the reference function. A reference position is used for determining the reference function.

[0025] In the embodiments of the present invention, it is mainly assumed that the reference position is the position of the end of the platform of a railway station (hereinafter also simply referred to as "platform") (hereinafter also simply referred to as "platform end position"). When the reference position is the platform end position, it can be determined as the object position whether the target object exists inside the area that is the area sandwiched between the platform and the train on the track. However, as will be described later, the reference position is not limited to the platform end position.

[0026] In the embodiments of the present invention, it is mainly assumed that the reference function determination device 1 and the object position determination device 2 are realized by different devices. However, the reference function determination device 1 and the object position determination device 2 may be realized by the same device.

[0027] [1-1. Configuration example of reference function determination device 1] FIG. 1 is a block diagram showing a functional configuration example of the reference function determination device 1 according to an embodiment of the present invention. As shown in FIG. 1, the reference function determination device 1 according to an embodiment of the present invention includes a point cloud acquisition unit 20, an input point cloud storage unit 30, a platform end position acquisition unit 40, a reference function determination unit 50, and a reference function storage unit 60. Further, the reference function determination device 1 is connected to each of the laser sensor 10 and the object position determination device 2. First, after briefly explaining the laser sensor 10, the functional configuration example of the reference function determination device 1 will be described with reference to FIG. 1.

[0028] (Laser Sensor 10) The laser sensor 10 is a sensor that irradiates 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 at a position where the target object and the home end can be measured (e.g., at home or around the home, etc.). The laser sensor can also be paraphrased as a LiDAR (Laser Imaging Detection and Ranging) sensor.

[0029] The laser sensor 10 corresponds to an example of a sensor that obtains the three-dimensional position of an object as sensor data. Therefore, instead of the laser sensor 10, various sensors other than the laser sensor (e.g., a distance measurement sensor, etc.) may be used. For example, the sensor may be a radar (e.g., a millimeter-wave radar, etc.) 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 is also referred to as "point cloud data" or "point cloud".

[0030] (Reference Function Determination Device 1) The reference function determination device 1 is an information processing device realized by a computer. For example, the point cloud acquisition unit 20, the home end position acquisition unit 40, and the reference function determination unit 50 may be realized by a control unit (not shown). On the other hand, the input point cloud storage unit 30 and the reference function storage unit 60 may be realized by a storage unit (not shown).

[0031] The control unit (not shown) includes a CPU (Central Processing Unit), etc., and its function can be realized by a program stored in a non-volatile storage device being expanded and executed by the CPU in a RAM (Random Access Memory). At this time, a computer-readable recording medium recording the program may also be provided. Alternatively, the control unit (not shown) may be composed of dedicated hardware or may be composed of a combination of multiple hardware.

[0032] The memory unit (not shown) is a memory device capable of storing programs and data for operating a control unit (not shown). Also, the memory unit (not shown) can temporarily store various data required in the process of operating the control unit (not shown). For example, the memory device may be a non-volatile memory device.

[0033] (Point cloud acquisition unit 20) The point cloud acquisition unit 20 acquires, from the laser sensor 10, point cloud data (second sensor data) obtained by the laser sensor 10 as input point cloud. 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.

[0034] (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. Also, the input point cloud storage unit 30 outputs the input point cloud to the home position acquisition unit 40.

[0035] (Home position acquisition unit 40) The home position acquisition unit 40 acquires the home position. The home position acquisition unit 40 may acquire the home position in any manner. As an example, the home position acquisition unit 40 may cause the input point cloud to be displayed on a predetermined display by a point cloud display application or the like, and acquire, as the home position, the 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 home position acquisition unit 40 may automatically acquire the home position without relying on manual operation by the user. The home position acquisition unit 40 outputs the home position to the reference function determination unit 50.

[0036] (Reference function determination unit 50) The reference function determination unit 50 determines a reference function based on the home end position. For example, the reference function determination unit 50 may determine the reference function by approximation based on the home end position. Hereinafter, the case where the approximation performed by the reference function determination unit 50 is polynomial approximation will be described. At this time, the reference function may be a function represented by using a polynomial determined by polynomial approximation. That is, the reference function can be expressed by polynomial coefficients that are coefficients of each dimension forming the polynomial.

[0037] Note that in this specification, the polynomial includes not only the case where the number of terms is plural but also the case where the number of terms is one. Also, in this specification, the polynomial can be an expression whose highest degree is 0 dimension or 1 dimension or more. The reference function determination unit 50 outputs the determined reference function to the reference function storage unit 60.

[0038] (Reference function storage unit 60) The reference function storage unit 60 stores the reference function output from the reference function determination unit 50. The reference function stored by the reference function storage unit 60 is output to the reference function setting unit 120 provided in the object position determination device 2.

[0039] The functional configuration example of the reference function determination device 1 according to the embodiment of the present invention has been described above.

[0040] [1-2. Configuration example of object position determination device 2] FIG. 2 is a block diagram showing a functional configuration example of the object position determination device 2 according to the embodiment of the present invention. As shown in FIG. 2, the object position determination device 2 according to the embodiment of the present invention includes a point cloud acquisition unit 80, an input point cloud storage unit 90, a background point cloud storage unit 100, an object detection unit 110, a reference function setting unit 120, and a position determination unit 130. Also, the object position determination device 2 is connected to the laser sensor 10, the display unit 140, and the reference function determination device 1 respectively. First, the functional configuration example of the object position determination device 2 will be described with reference to FIG. 2, and then the display unit 140 will be briefly described.

[0041] (Object position determination device 2) The object position determination device 2 is an information processing device realized by a computer. For example, the point cloud acquisition unit 80, the object detection unit 110, the reference function setting unit 120, and the position determination unit 130 can 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 can be realized by a storage unit (not shown).

[0042] The control unit (not shown) includes a CPU (Central Processing Unit) etc., and its function can be realized by a program stored in a non-volatile storage device being expanded to the RAM (Random Access Memory) by the CPU and executed. At this time, a computer-readable recording medium recording the program may also be provided. Alternatively, the control unit (not shown) may be composed of dedicated hardware, or may be composed of a combination of multiple hardware components.

[0043] The storage unit (not shown) is a storage device capable of storing programs and data for operating the control unit (not shown). Also, the storage unit (not shown) can temporarily store various data required in the process of operating the control unit (not shown). For example, the storage device may be a non-volatile storage device.

[0044] (Point cloud acquisition unit 80) When there is no target object in the measurement range by the laser sensor 10, the point cloud acquisition unit 80 acquires, as the background point cloud, the point cloud data (third sensor data) obtained by the laser sensor 10 from 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.

[0045] After the point cloud acquisition unit 80 outputs the background point cloud to the background point cloud storage unit 100, it acquires, as the input point cloud, the point cloud data (first sensor data) obtained by the laser sensor 10 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.

[0046] (Input point cloud memory unit 90) The input point cloud memory unit 90 stores the input point cloud output from the point cloud acquisition unit 80. Also, the input point cloud memory unit 90 outputs the input point cloud to the object detection unit 110.

[0047] (Background point cloud memory unit 100) The background point cloud memory unit 100 stores the background point cloud output from the point cloud acquisition unit 80. Also, the background point cloud memory unit 100 outputs the background point cloud to the object detection unit 110.

[0048] (Object detection unit 110) The object detection unit 110 detects a region containing the target object as the object region based on the input point cloud output from the input point cloud memory unit 90. More specifically, the object detection unit 110 detects the object region based on the background point cloud output from the background point cloud memory unit 100 and the input point cloud output from the input point cloud memory unit 90. The object detection unit 110 outputs information indicating the object region to the reference function setting unit 120.

[0049] (Reference function setting unit 120) The reference function setting unit 120 sets a reference function. More specifically, the reference function setting unit 120 may set the reference function by acquiring the reference function output from the reference function memory unit 60. Also, the reference function setting unit 120 acquires information indicating the object region output from the object detection unit 110. The reference function setting unit 120 outputs the reference function and the information indicating the object region to the position determination unit 130.

[0050] (Position determination unit 130) The position determination unit 130 identifies a graphic element passing through a plurality of positions included in the object area based on the information indicating the object area. The graphic element may be a line segment or a plane (for example, a flat surface). Further, the position determination unit 130 determines the position of the target object by determining whether the graphic element intersects with the reference function. More specifically, the position determination unit 130 determines whether the position of the target object is inside the area corresponding to the reference function by determining whether the graphic element intersects with the reference function. For example, the area corresponding to the reference function y = g(x) may be the area sandwiched between the train on the track and the platform.

[0051] The position determination unit 130 outputs the determination result to the display unit 140. As a result, the display by the display unit 140 of the determination result is controlled. For example, a person who has visually recognized the determination result that the position of the target object is inside the area sandwiched between the train on the track and the platform can take some measures with respect to the target object.

[0052] (Display unit 140) The display unit 140 displays the determination result when the determination result is output from the position determination unit 130. For example, the display unit 140 may include a lamp, and may display the determination result that the position of the target object is inside the area sandwiched between the train on the track and the platform by lighting the lamp. Alternatively, the display unit 140 may be constituted by a display, and may display the determination result that the position is inside the area sandwiched between the train on the track and the platform by displaying a predetermined color (for example, red) on the display.

[0053] Note that the position where the display unit 140 is provided is not particularly limited. For example, the display unit 140 may be provided on the platform. Alternatively, the display unit 140 may be provided in the station office where the station staff is present. Alternatively, the display unit 140 may be provided in the monitoring center where the monitor who monitors the operation status of the train is present.

[0054] The functional configuration example of the object position determination device 2 according to the embodiment of the present invention has been described above.

[0055] [Operation Example Related to the Reference Function Determination Stage] Next, an operation example of the information processing system according to the embodiment of the present invention will be described. The operation example of the information processing system is divided into a first stage and a second stage performed after the first stage. The first stage is the reference function determination stage. The second stage is the object position determination stage. First, an operation example of the reference function determination device 1 related to the reference function determination stage will be described with reference to FIGS. 3 to 5 (appropriately referring to FIG. 1 as well).

[0056] FIG. 3 is a flowchart showing an operation example of the reference function determination device 1 related to the reference function determination stage. As shown in FIG. 3, in the reference function determination stage, the point group acquisition unit 20 acquires, as an input point group, the point group data obtained by the laser sensor 10 from the laser sensor 10 (step A1). The point group acquisition unit 20 outputs the input point group acquired from the laser sensor 10 to the input point group storage unit 30. The input point group storage unit 30 stores the input point group output from the point group acquisition unit 20. Then, the input point group storage unit 30 outputs the input point group to the home end position acquisition unit 40.

[0057] FIG. 4 is a diagram showing an example of the input point group acquired in the reference function determination stage. As shown in FIG. 4, the coordinate system of the laser sensor 10 (hereinafter also referred to as the "sensor coordinate system") is represented by the x-axis, y-axis, and z-axis. And the input point group measured by the laser sensor 10 is represented by the x coordinate, y coordinate, and z coordinate.

[0058] In the example shown in FIG. 4, within the measurement range of the laser sensor 10, the first car T1, second car T2, third car T3, and fourth car T4 of the train and the home H1 exist, and the positions of their respective surfaces are obtained as the input point group. However, the number of cars of the train existing within the measurement range of the laser sensor 10 does not have to be four. Alternatively, there may be no train within the measurement range of the laser sensor 10.

[0059] The home position acquisition unit 40 sets 1 to the counter j (step A2). Then, when the counter j is equal to or less than a predetermined threshold value n ( "YES" in step A3), the home position acquisition unit 40 acquires the home position aj(xj, yj) (step A4). The threshold value n is an integer of 1 or more.

[0060] Note that the z coordinate may be included in the home position. However, hereinafter, for simplicity of calculation, the home position is assumed to be a position on the xy plane, and the description will proceed without including the z coordinate in the home position. Also, as the position of the input point group, 3D coordinates (x, y, z) and 2D coordinates (x, y) may be appropriately used depending on the situation.

[0061] The home position acquisition unit 40 may acquire the home position aj(xj, yj) in any manner. As an example, the home position acquisition unit 40 may cause a point group display application or the like to display the input point group on a predetermined display, and acquire the home position aj(xj, yj) input by the user to a predetermined input device based on the input point group displayed on the display. Alternatively, as will be described later, the home position acquisition unit 40 may automatically acquire the home position aj(xj, yj) without relying on manual operation by the user.

[0062] The home position acquisition unit 40 increments the counter j by 1 (step A5) and shifts the operation to step A3. When the counter j is greater than the predetermined threshold value n ( "NO" in step A3), the home position acquisition unit 40 shifts the operation to step A6.

[0063] Referring to FIG. 4, the home end position acquisition unit 40 has acquired the home end positions a1(x1, y1), a2(x2, y2), a3(x3, y3), ···, aj-1(xj-1, yj-1), aj(xj, yj), ···, an-1(xn-1, yn-1), an(xn, yn), which are shown. The home end position acquisition unit 40 outputs a1(x1, y1) to an(xn, yn) to the reference function determination unit 50.

[0064] The reference function determination unit 50 determines a reference function y = g(x) based on the home end positions a1(x1, y1) to an(xn, yn). For example, the reference function determination unit 50 may determine the reference function y = g(x) by polynomial approximation based on the home end positions a1(x1, y1) to an(xn, yn) (step A6). The reference function can be expressed by polynomial coefficients, which are the coefficients of each dimension forming the polynomial.

[0065] More specifically, the reference function determination unit 50 may determine an approximation function y = f(x) along the home end based on the home end positions a1(x1, y1) to an(xn, yn). For example, when the polynomial to be approximated is a quadratic equation, the approximation function y = f(x) is determined as shown in Equation (1).

[0066] y = f(x) = ax 2 + bx + c ···(1)

[0067] FIG. 5 is a diagram showing an example of an approximation curve corresponding to the approximation function. Referring to FIG. 5, the home end positions a1(x1, y1) to an(xn, yn) are shown. Also shown is the approximation curve f(x) = ax 2 + bx + c corresponding to the approximation function approximated to a quadratic equation based on the home end positions a1(x1, y1) to an(xn, yn).

[0068] Then, the reference function determination unit 50 may obtain Δy, which is the deviation amount between the approximate curve f(x) and the reference function g(x) (step A7), and determine the reference function y = g(x) by calculating f(x) + Δy. At this time, the reference function y = g(x) is determined as shown in Equation (2).

[0069] y = g(x) = f(x) + Δy = ax 2 + bx + c + Δy ···(2)

[0070] Note that Δy may be a predetermined value. For example, it is desirable that the reference function y = g(x) be determined at a position corresponding to the center of the area sandwiched between the home end and the train on the track. Therefore, Δy may be set to the width in the xy plane corresponding to half of the distance between the home end and the train on the track. At this time, the distance between the home end and the train on the track may be determined assuming that the home end is outside the construction limit, which is the range where the installation of obstacles is prohibited.

[0071] The reference function determination unit 50 outputs the determined reference function y = g(x) = ax 2 + bx + c + Δy to the reference function storage unit 60. Specifically, the reference function determination unit 50 may output the polynomial coefficients (a, b, c + Δy) to the reference function storage unit 60 (step A8). Note that the reference function determination unit 50 may divide the polynomial coefficients (a, b, c + Δy) into the polynomial coefficients (a, b, c) and the deviation amount Δy and output them to the reference function storage unit 60.

[0072] The reference function storage unit 60 stores the reference function output from the reference function determination unit 50. Specifically, when the polynomial coefficients (a, b, c + Δy) are output from the reference function determination unit 50, the reference function storage unit 60 may store the polynomial coefficients (a, b, c + Δy). The reference function stored by the reference function storage unit 60 is output to the reference function setting unit 120 provided in the object position determination device 2.

[0073] The operation example of the reference function determination device 1 according to the reference function determination stage has been described above with reference to FIGS. 3 to 5 (and appropriately with reference to FIG. 1).

[0074] [Operation Example Related to Object Position Determination Stage] Subsequently, with reference to FIGS. 6 to 8 (and appropriately referring to FIG. 2 as well), an operation example of the object position determination device 2 related to the object position determination stage will be described. As described above, the object position determination stage is performed after the reference function determination stage.

[0075] FIG. 6 is a flowchart showing an operation example of the object position determination device 2 related to the object position determination stage. As shown in FIG. 6, in the object position determination stage, the reference function setting unit 120 sets the reference function by acquiring the reference function output from the reference function storage unit 60. More specifically, the reference function determination unit 50 sets the reference function by acquiring the polynomial coefficients (a, b, c + Δy) from the reference function storage unit 60 (step B1).

[0076] Subsequently, when there is no target object in the measurement range by the laser sensor 10, the point cloud acquisition unit 80 acquires the point cloud data obtained by the laser sensor 10 from the laser sensor 10 as the background point cloud (step B2). Here, it is assumed that a train exists in the measurement range by the laser sensor 10. That is, it is assumed that the background point cloud includes the point cloud data corresponding to the train and the platform respectively.

[0077] 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.

[0078] 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 differential point cloud, a point cloud that is not in the background point cloud among the input point clouds by 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 the Octree module of PCL (Point Cloud Library) can be applied to the extraction of the differential point cloud.

[0079] Note that in order to improve the extraction accuracy of the differential point cloud, it is desirable to extract a differential point cloud represented by three-dimensional coordinates based on the background point cloud represented by three-dimensional coordinates and the input point cloud represented by three-dimensional coordinates. However, a differential point cloud represented by two-dimensional coordinates may be extracted based on the background point cloud represented by two-dimensional coordinates and the input point cloud represented by two-dimensional coordinates.

[0080] The object detection unit 110 performs clustering on the extracted differential point cloud to extract a cluster of point clouds as a cluster (step B5). For example, a method using the Kdtree module of PCL (Point Cloud Library) can be applied to the clustering. Here, it is mainly assumed that the point cloud included in the cluster is represented by two-dimensional coordinates. However, the point cloud included in the cluster may be represented by three-dimensional coordinates.

[0081] The object detection unit 110 uses the extracted cluster as a detected object point cloud and detects a region having a predetermined shape including the detected object point cloud as an object region. Here, it is assumed that both the detected object point cloud and the object region are represented by two-dimensional coordinates. At this time, the predetermined shape may be a rectangular shape in a two-dimensional plane orthogonal to the z-axis. That is, the 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 (step B6).

[0082] Alternatively, each of the detected object point group and the object region may be represented by three-dimensional coordinates. At this time, the predetermined shape may be a quadrangular prism shape having a rectangular shape in a two-dimensional plane orthogonal to the z-axis as a bottom surface and the z-axis direction as a height direction.

[0083] FIG. 7 is a diagram showing an example of a target object and an object region. Referring to FIG. 7, similar to the example shown in FIG. 4, within the measurement range by the laser sensor 10, there are the first car T1, the second car T2, the third car T3, and the fourth car T4 of the train, and the platform H1, and the positions of their respective surfaces are obtained as input point groups. Whether or not the point group corresponding to the train is included in the input point group may be adjusted according to whether or not the point group corresponding to the train is included in the background point group.

[0084] Furthermore, referring to FIG. 7, a target object F is shown, and a rectangular region circumscribing the target object F is shown as an object region R. The object detection unit 110 outputs information indicating the object region R to the reference function setting unit 120.

[0085] The reference function setting unit 120 sets a reference function by acquiring the reference function output from the reference function storage unit 60. More specifically, the reference function setting unit 120 acquires the polynomial coefficients (a, b, c + Δy) output from the reference function storage unit 60, whereby the reference function y = g(x) = ax 2 + bx + c + Δy is set.

[0086] Also, the reference function setting unit 120 acquires the information indicating the object region R output from the object detection unit 110. The reference function setting unit 120 outputs the reference function y = g(x) = ax 2 + bx + c + Δy and the information indicating the object region R to the position determination unit 130.

[0087] The position determination unit 130 determines a plurality of positions included in the object region R. Here, it is mainly assumed that the plurality of positions included in the object region R are two positions, i.e., position A1(x1, y1) and position A2(x2, y2) included in the object region R. However, the plurality of positions included in the object region R may be three or more positions included in the object region R.

[0088] Position A1(x1, y1) and position A2(x2, y2) may be determined in any way. For example, position A1(x1, y1) and position A2(x2, y2) may be positions on the contour line (or contour surface) of the object region R.

[0089] Furthermore, the greater the distance between position A1(x1, y1) and position A2(x2, y2), the higher the accuracy of the position determination of the target object F by the position determination unit 130 can be. Therefore, position A1(x1, y1) and position A2(x2, y2) may be positions on different sides in the object region R. In the case where the object region R has a quadrangular prism shape, the two positions included in the object region R may be positions on different surfaces in the object region R.

[0090] The position determination unit 130 specifies a graphic element passing through position A1(x1, y1) and position A2(x2, y2). Here, it is mainly assumed that the graphic element is a line segment passing through position A1(x1, y1) and position A2(x2, y2). However, as the graphic element, instead of the line segment passing through position A1(x1, y1) and position A2(x2, y2), a surface (for example, a plane) passing through position A1(x1, y1) and position A2(x2, y2) may be used.

[0091] The position determination unit 130 determines the position of the target object F by determining whether a line segment passing through the positions A1(x1, y1) and A2(x2, y2) intersects with the reference function y = g(x). More specifically, the position determination unit 130 determines whether a line segment passing through the positions A1(x1, y1) and A2(x2, y2) intersects with the reference function y = g(x), thereby determining whether the position of the target object F is inside the area corresponding to the reference function y = g(x). For example, the area corresponding to the reference function y = g(x) may be the area sandwiched between the train on the track and the platform.

[0092] For example, the position determination unit 130 calculates Y1 = y1 - g(x1) (step B7), calculates Y2 = y2 - g(x2) (step B8), and calculates Z = Y1·Y2 (step B9).

[0093] Assume that the position determination unit 130 determines that Z is 0 or less (``YES'' in step B10). In such a case, it means that the line segment passing through the positions A1(x1, y1) and A2(x2, y2) intersects with the reference function y = g(x). Therefore, the position determination unit 130 may determine that the position of the target object F is inside the area sandwiched between the train (the first car T1, the second car T2, the third car T3, and the fourth car T4) on the track and the platform H1 (step B11).

[0094] On the other hand, assume that the position determination unit 130 determines that Z is greater than 0 (``NO'' in step B10). In such a case, it means that the line segment passing through the positions A1(x1, y1) and A2(x2, y2) does not intersect with the reference function y = g(x). Therefore, the position determination unit 130 may determine that the position of the target object F is outside the area sandwiched between the train (the first car T1, the second car T2, the third car T3, and the fourth car T4) on the track and the platform H1 (step B12).

[0095] FIG. 8 is a diagram for explaining the details of the process of determining whether the position of the target object is inside the area sandwiched between the train on the track and the platform.

[0096] As shown in FIG. 8, the position determination unit 130 calculates Y1 = y1 - g(x1), calculates Y2 = y2 - g(x2), and calculates Z = Y1·Y2. At this time, since Y1 < 0 and Y2 > 0, Z = Y1·Y2 ≤ 0. Therefore, the position determination unit 130 may determine that the position of the target object corresponding to the object area including the positions A1(x1, y1) and A2(x2, y2) is inside the area sandwiched between the train on the track and the platform.

[0097] Also, assume that an object area including the positions A3(x3, y3) and A4(x4, y4) is detected. At this time, the position determination unit 130 calculates Y1 = y3 - g(x3), calculates Y2 = y4 - g(x4), and calculates Z = Y1·Y2. At this time, since Y1 < 0 and Y2 < 0, Z = Y1·Y2 > 0. Therefore, the position determination unit 130 may determine that the position of the target object corresponding to the object area including the positions A3(x3, y3) and A4(x4, y4) is outside the area sandwiched between the train on the track and the platform.

[0098] Also, assume that an object area including the positions A5(x5, y5) and A6(x6, y6) is detected. At this time, the position determination unit 130 calculates Y1 = y5 - g(x5), calculates Y2 = y6 - g(x6), and calculates Z = Y1·Y2. At this time, since Y1 > 0 and Y2 > 0, Z = Y1·Y2 > 0. Therefore, the position determination unit 130 may determine that the position of the target object corresponding to the object area including the positions A5(x5, y5) and A6(x6, y6) is outside the area sandwiched between the train on the track and the platform.

[0099] The position determination unit 130 outputs the determination result to the display unit 140 (step B13). When the determination result is output from the position determination unit 130, the display unit 140 displays the determination result. For example, a person who visually recognizes the determination result that the position of the target object F is inside the area sandwiched between the train on the track and the platform can take some measures with respect to the target object F.

[0100] The operation example of the object position determination device 2 according to the object position determination stage has been described above with reference to FIGS. 6 to 8 (and also with reference to FIG. 2 as appropriate).

[0101] [1-5. Effects of Embodiment] As described above, according to the embodiment of the present invention, an object detection unit 110 that detects an object region based on the point cloud data obtained by the laser sensor 10, a graphic element passing through a plurality of positions included in the object region, and a reference function serving as a reference for determining the object position are provided. An object position determination device 2 including a position determination unit 130 that determines whether they intersect is provided.

[0102] According to such a configuration, it is possible to improve the determination accuracy of the object position while reducing the labor required for the user.

[0103] The effects of the embodiment of the present invention have been described above.

[0104] <2. Various Modification Examples> Subsequently, various modification examples will be described.

[0105] (First Modification Example) In the above, the position determination unit 130 mainly assumes a case where when a graphic element passing through a plurality of positions included in the object region intersects the reference function, it is determined that the object position is inside the area sandwiched between the train on the track and the platform. Further, the position determination unit 130 mainly assumes a case where when the graphic element and the reference function do not intersect, it is determined that the object position is outside the area sandwiched between the train on the track and the platform. However, the area where the object position is determined does not necessarily have to be limited to the area sandwiched between the train on the track and the platform.

[0106] For example, when a graphic element passing through a plurality of positions included in the object area intersects with the reference function, the position determination unit 130 may determine that the object position is inside a predetermined driving lane. On the other hand, when the graphic element and the reference function do not intersect, the position determination unit 130 may determine that the object position is outside the predetermined driving lane. At this time, the target object may be a vehicle traveling on a road or the like. Further, the reference function may be set at a position corresponding to the central position in the width direction of the driving lane.

[0107] Alternatively, when a graphic element passing through a plurality of positions included in the object area intersects with the reference function, the position determination unit 130 may determine that the object position is on the boundary line between the outside and the inside of a predetermined driving lane. On the other hand, when the graphic element and the reference function do not intersect, the position determination unit 130 may determine that the object position is not on the boundary line between the outside and the inside of the predetermined driving lane. At this time, the target object may be a vehicle traveling on a road or the like. Further, the reference function may be set at a position corresponding to the boundary line.

[0108] (Second modification example) In the above, it is mainly assumed that the home position acquisition unit 40 acquires, as the home position, the position input to a predetermined input device by the user based on the input point group displayed on the display. However, the home position acquisition unit 40 may automatically acquire the home position without depending on the user's manual operation.

[0109] For example, the home position acquisition unit 40 may detect, as the home position, the position of an edge detected from the input point group.

[0110] Alternatively, the home end position acquisition unit 40 may acquire the position information obtained by a GNSS (Global Navigation Satellite System) sensor provided at the home end. Then, the home end position acquisition unit 40 may convert it into the position information in the coordinate system of the laser sensor 10 based on the correspondence relationship between the coordinate system of the laser sensor 10 and the coordinate system of the GNSS sensor. Then, the home end position acquisition unit 40 may determine the reference function by polynomial approximation based on the position information in the coordinate system of the laser sensor 10. The correspondence relationship between the coordinate system of the laser sensor 10 and the coordinate system of the GNSS sensor may be measured in advance.

[0111] (Third modification example) In the above, the case where the range in which it is necessary to determine whether or not the target object exists is a non-straight road (i.e., a curved road) is mainly assumed. However, the range in which it is necessary to determine whether or not the target object exists may be a straight road (i.e., a straight line road). Alternatively, the range in which it is necessary to determine whether or not the target object exists may be constituted by a combination of a curved road and a straight road.

[0112] The above has described various modification examples.

[0113] <3. Hardware configuration example> Subsequently, a hardware configuration example of the object position determination device 2 according to the embodiment of the present invention will be described. Hereinafter, as a hardware configuration example of the object position determination device 2 according to the embodiment of the present invention, a hardware configuration example of the information processing device 900 will be described. Note that the hardware configuration example of the information processing device 900 described below is merely an example of the hardware configuration of the object position determination device 2. Therefore, the hardware configuration of the object position determination device 2 may be obtained by deleting unnecessary configurations from the hardware configuration of the information processing device 900 described below, or new configurations may be added. Note that the hardware of the reference function determination device 1 can be realized in the same manner.

[0114] FIG. 9 is a diagram showing the hardware configuration of an information processing apparatus 900 as an example of the object position determination apparatus 2 according to an embodiment of the present invention. The information processing apparatus 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.

[0115] The CPU 901 functions as an arithmetic processing unit and a control unit, and controls the overall operation within the information processing apparatus 900 according to various programs. Further, the CPU 901 may be a microprocessor. The ROM 902 stores programs, arithmetic parameters, etc. used by the CPU 901. The RAM 903 temporarily stores programs used in the execution of the CPU 901 and parameters that appropriately change during the execution. These are interconnected by a host bus 904 composed of a CPU bus or the like.

[0116] The host bus 904 is connected to an external bus 906 such as a PCI (Peripheral Component Interconnect / Interface) bus via the bridge 905. Note that it is not necessarily required to separately configure the host bus 904, the bridge 905, and the external bus 906, and these functions may be implemented on one bus.

[0117] The input device 908 includes input means such as a mouse, a keyboard, a touch panel, buttons, a microphone, switches, and levers for the user to input information, and an input control circuit that generates an input signal based on the input by the user and outputs it to the CPU 901. The user who operates the information processing apparatus 900 can input various data to the information processing apparatus 900 or instruct a processing operation by operating this input device 908.

[0118] 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, a lamp, etc., and an audio output device such as a speaker.

[0119] 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, a deleting device for deleting data recorded on the storage medium, etc. The storage device 910 is composed of, for example, an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs and various data executed by the CPU 901.

[0120] The communication device 911 is a communication interface composed of, for example, a communication device for connecting to a network. Also, the communication device 911 may support either wireless communication or wired communication.

[0121] The hardware configuration example of the object position determination device 2 according to the embodiment of the present invention has been described above.

[0122] <4. Supplementary> The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that those having ordinary knowledge in the technical field to which the present invention pertains can conceive of various modification examples or correction examples within the scope of the technical idea described in the claims, and these are naturally understood to belong to the technical scope of the present invention.

Explanation of Reference Numerals

[0123] 1 Reference function determination device 10 Laser sensor 100 Background point cloud storage unit 110 Object detection unit 120 Reference function setting unit 130 Position determination unit 140 Display unit 2 Object position determination device 20 Point cloud acquisition unit 30 Input point cloud memory unit 40 Home end position acquisition unit 50 Reference function determination unit 60 Reference function memory unit 80 Point cloud acquisition unit 90 Input point cloud memory unit

Claims

1. An object detection unit that detects an object region based on first sensor data obtained by a sensor; A position determination unit that determines the object position by determining whether a graphic element passing through a plurality of positions included in the object region intersects a reference function that is a reference for determining the object position; Comprising: The reference function is determined by approximation based on a position input by a user; The approximation is a polynomial approximation; The reference function is a function represented by using a polynomial determined by the polynomial approximation; An information processing apparatus.

2. The reference function is determined by approximation based on position information obtained by a GNSS sensor being converted into position information in the coordinate system of the sensor and based on the position information in the coordinate system of the sensor. The information processing apparatus according to Claim 1. The information processing apparatus according to Claim 1.

3. The graphic element is a line segment or a plane. The information processing apparatus according to Claim 1. The information processing apparatus according to Claim 1.

4. When the graphic element and the reference function intersect, the position determination unit determines that the object position is inside an area sandwiched between a train on a track and a platform, and when the graphic element and the reference function do not intersect, the position determination unit determines that the object position is outside the area. The information processing apparatus according to Claim 1. The information processing apparatus according to Claim 1.

5. When the graphic element and the reference function intersect, the position determination unit determines that the object position is inside a predetermined travel lane, and when the graphic element and the reference function do not intersect, the position determination unit determines that the object position is outside the predetermined travel lane. The information processing apparatus according to Claim 1. The information processing apparatus according to Claim 1.

6. When the graphic element and the reference function intersect, the position determination unit determines that the object position is on a boundary line between the outside and the inside of a predetermined travel lane, and when the graphic element and the reference function do not intersect, the position determination unit determines that the object position is not on the boundary line. The information processing apparatus according to Claim 1. The information processing apparatus according to Claim 1.

7. Detecting an object region based on first sensor data obtained by a sensor; Determining the object position by determining whether a graphic element passing through a plurality of positions included in the object region intersects a reference function that is a reference for determining the object position; Including: The reference function is determined by approximation based on a position input by a user; The approximation is a polynomial approximation; The reference function is a function represented by using a polynomial determined by the polynomial approximation. An information processing method executed by a computer. **Claim 8** A computer, An object detection unit that detects an object region based on first sensor data obtained by a sensor, A position determination unit that determines the object position by determining whether a graphic element passing through a plurality of positions included in the object region intersects with a reference function serving as a reference for determining the object position, Functioning as, The reference function is determined by an approximation based on a position input by a user, The approximation is a polynomial approximation, The reference function is a function represented by using a polynomial determined by the polynomial approximation. A program.

Images