Determination device, program, and management system

Abstract

A determination device (20) determines the presence or absence of a vehicle (CA) from point cloud data which is output from a LiDAR device (10) constituting an image acquisition device for acquiring an image of a detection region (DR). The detection region includes a parking region (51) that is partitioned such that one vehicle (CA) is located therein. The determination device (20) determines whether the vehicle (CA) is in a first state of being located in the parking region (51) or in a second state of not being located in the parking region (51). In a case where the ratio of a blind spot region (BS) to the entire parking region (51) is equal to or greater than a first threshold, the determination device (20) maintains the determination immediately before the ratio becomes equal to or greater than the first threshold.

Description

Determination device, program, and management system

[0001] The present invention relates to a determination device, a program, and a management system.

[0002] A determination device that determines whether a vehicle is parked in a parking area from an image of a parking lot is known, and Patent Document 1 below discloses such a determination device.

[0003] The determination device described in Patent Document 1 below calculates the ratio of the blind spot area of ​​the camera to the entire parking area, and determines that the parking area is an area where parking is possible if the ratio is less than a threshold, and determines that the parking area is an area where parking is possible if the ratio is equal to or greater than the threshold.

[0004] International Publication No. 2023 / 007785

[0005] In the determination device of Patent Document 1, if the ratio is large, the parking area is determined to be an area that may be vacant. Here, there is a demand for determining whether a vehicle is parked in a parking area even if the parking area has a blind spot. Also, when a vehicle is defined as a moving object including a vehicle and a non-vehicle, and the parking area is defined as a placement area of ​​the moving object, there is a demand for determining whether the moving object is located in the placement area even if the placement area has a blind spot.

[0006] Therefore, an object of the present invention is to provide a determination device, a program, and a management system that can determine whether a moving object is located even if there is a blind spot in the placement area.

[0007] In order to achieve the above-mentioned object, the present invention provides a judgment device that judges the presence or absence of a moving body from image data output from an image acquisition device that acquires an image of a detection area including a placement area partitioned so that a single moving body is located, and that judges whether the state is a first state in which the moving body is located in the placement area, or a second state in which the moving body is not located in the placement area, and that, if the ratio of blind spots in the placement area to the entire placement area is greater than or equal to a first threshold, maintains the judgment at the time just before the ratio becomes greater than or equal to the first threshold.

[0008] The present invention also provides a program executed by a judgment device that judges the presence or absence of a moving body from image data output from an image acquisition device that acquires an image of a detection area including a placement area partitioned so that a single moving body is located, and causes the judgment device to execute a step of judging whether the state is a first state in which the moving body is located in the placement area, or a second state in which the moving body is not located in the placement area, and in this step, if the ratio of the blind spot area in the placement area to the entire placement area is greater than or equal to a first threshold, the judgment at the time just before the ratio becomes greater than or equal to the first threshold is maintained.

[0009] The management system of the present invention also comprises an image acquisition device that acquires an image of a detection area including a placement area partitioned so that one moving body can be located, and a judgment device that judges whether the moving body is present or absent from image data output from the image acquisition device, wherein the judgment device judges whether the state is a first state in which the moving body is located in the placement area, or a second state in which the moving body is not located in the placement area, and when the ratio of the blind spot area to the entire placement area is greater than or equal to a first threshold, maintains the judgment at the time just before the ratio becomes greater than or equal to the first threshold.

[0010] The smaller the ratio of the blind spot area in the placement area to the entire placement area, the higher the accuracy of the determination tends to be. In the above-mentioned determination device, program, and management system, if the ratio is equal to or greater than a first threshold, the determination made immediately before the ratio became equal to or greater than the first threshold is maintained. Therefore, with this determination device, program, and management system, it is possible to determine whether a moving object is located even if there is a blind spot area in the placement area.

[0011] The determination device may determine the state as the second state when, after maintaining the determination, the moving object is detected from the image data with the ratio being equal to or greater than the first threshold value, and may determine the state as the first ... detecting the moving object leaving the blind spot area with the ratio being equal to or greater than the first threshold value, the step of the program may determine the state as the second state when, after maintaining the determination, the moving object is detected from the image data with the ratio being equal to or greater than the first threshold value, and may determine the state as the first state when, after detecting the moving object entering the blind spot area with the ratio being equal to or greater than the first threshold value, the step of the program may determine the state as the second state when, after detecting the moving object leaving the blind spot area with the ratio being equal to or greater than the first threshold value,

[0012] This configuration can improve the accuracy of determination when there is a blind spot area in the placement area.

[0013] The determination device may determine that the state is a third state different from the first state and the second state when the ratio is equal to or greater than the first threshold after a predetermined period has elapsed since the determination was maintained immediately before the ratio became equal to or greater than the first threshold. Furthermore, in the step of the program, the state may determine that the state is a third state different from the first state and the second state when the ratio is equal to or greater than the first threshold after a predetermined period has elapsed since the determination was maintained immediately before the ratio became equal to or greater than the first threshold.

[0014] If the ratio is equal to or greater than the first threshold value even after a predetermined period of time has elapsed after maintaining the determination, this indicates that a blind spot continues to exist in the placement area, and a moving object may enter or exit the blind spot. As a result, the accuracy of the determination of the presence or absence of a moving object in the placement area decreases over time. This configuration can indicate that the accuracy of the determination is decreasing.

[0015] The image acquisition device may be a LiDAR (Light Detection and Ranging) device that outputs point cloud data of the detection area as the image data.

[0016] In this case, the determination device may calculate, as the ratio, a ratio of the number of cells in which points of the point cloud data input from the LiDAR device are not located to a total number of cells in which the placement area is divided. Also, the program may cause the control device to execute a step of calculating, as the ratio, a ratio of the number of cells in which points of the point cloud data input from the LiDAR device are not located to a total number of cells in which the placement area is divided.

[0017] The determination device may determine that the moving object is located in the placement area when a ratio of the number of cells in which points indicating a height equal to or greater than a predetermined height in the point cloud data are located to the total number of cells dividing the placement area is equal to or greater than a second threshold, and determine that the moving object is not located in the placement area when the ratio is less than the second threshold. Furthermore, in the step of the program, the determination device may determine that the moving object is located in the placement area when a ratio of the number of cells in which points indicating a height equal to or greater than a predetermined height in the point cloud data are located to the total number of cells dividing the placement area is equal to or greater than a second threshold, and determine that the moving object is not located in the placement area when the ratio is less than the second threshold.

[0018] With this configuration, it is possible to make it less likely that an erroneous determination that a moving body is located is made when an object that is lower in height than the target moving body enters the placement area.

[0019] As described above, according to the present invention, it is possible to provide a determination device, a program, and a management system that can determine whether a moving object is located even if there is a blind spot in the placement area.

[0020] Fig. 1 is a schematic diagram showing a management system according to an embodiment of the present invention. Fig. 2 is a conceptual diagram showing a detection area measured by a LiDAR device according to an embodiment. Fig. 3 is a diagram showing how a parking area is divided into cells. Fig. 4 is a diagram showing the state of the cells in the parking area in the situation shown in Fig. 2. Fig. 5 is a flowchart showing the operation of a determination device according to an embodiment. Fig. 6 is a flowchart showing a specific operation of the determination device according to Modification 1. Fig. 7 is a flowchart showing another specific operation of the determination device according to Modification 2.

[0021] Preferred embodiments of a determination device, a program, and a management system according to the present invention will be described in detail below with reference to the drawings. The embodiments exemplified below are intended to facilitate understanding of the present invention and are not intended to limit the scope of the present invention. Therefore, the present invention can be modified and improved from the following embodiments within the scope of the claims. Note that in the drawings referred to below, the dimensions of each component may be changed to facilitate understanding. Also, in the drawings, for ease of viewing, similar components may be assigned reference symbols only in some cases, and some reference symbols may be omitted.

[0022] 1 is a schematic diagram illustrating a management system according to an embodiment of the present invention. The management system 1 of this embodiment mainly includes a LiDAR device 10, a determination device 20, a memory 30, and a monitor 40.

[0023] The management system 1 of this embodiment can determine whether a moving object such as a vehicle or luggage is located in the placement area of ​​the detection area measured by the LiDAR device 10 as an image acquisition device.

[0024] The LiDAR device 10 of this embodiment is, for example, a raster scan LiDAR device. The LiDAR device 10 of this embodiment includes a cover 19, a driver circuit 11, a laser light source 12, an H-direction scanning drive mirror 13, a V-direction scanning drive mirror 14, a light receiving element 15, and a point cloud data generator 16. Note that, although the LiDAR device 10 in the example of FIG. 1 is a mechanical LiDAR device, it may also be a phased array LiDAR device that does not include a drive unit.

[0025] The cover 19 has a storage space for housing the driver circuit 11, the laser light source 12, the driving mirror 13 for H-direction scanning, the driving mirror 14 for V-direction scanning, the light receiving element 15, and the point cloud data generation unit 16, and transmits the laser light Lb emitted from the laser light source 12 and the reflected light Lr that is reflected by an object within the detection area.

[0026] The driver circuit 11 is composed of, for example, a plurality of logic circuits, and is electrically connected to the laser light source 12, the H-direction scanning drive mirror 13, and the V-direction scanning drive mirror 14 to control them.

[0027] The laser light source 12 emits laser light Lb of a predetermined wavelength. This laser light Lb is near-infrared light with a wavelength of, for example, 905 nm or 1550 nm. The timing at which the laser light source 12 emits the laser light Lb is controlled by a driver circuit 11, and the laser light source 12 emits the laser light Lb in response to a signal from the driver circuit 11. The driver circuit 11 is electrically connected to a point cloud data generator 16, and outputs data including the timing at which the laser light Lb is emitted from the laser light source 12 to the point cloud data generator 16.

[0028] The H-direction scanning drive mirror 13 includes a mirror that reflects the laser light Lb emitted from the laser light source 12 and a drive unit (not shown) that is controlled by the driver circuit 11. When reflecting the laser light Lb, the H-direction scanning drive mirror 13 reflects the laser light Lb while changing the reflection angle in the horizontal direction using the drive unit. By changing the reflection angle of the H-direction scanning drive mirror 13, the LiDAR device 10 performs horizontal scanning.

[0029] The V-direction scanning drive mirror 14 includes a mirror that reflects the laser light Lb reflected by the H-direction scanning drive mirror 13 and a drive unit (not shown) controlled by the driver circuit 11. When reflecting the laser light Lb, the V-direction scanning drive mirror 14 reflects the laser light Lb while changing the reflection angle in the vertical direction using the drive unit. This change in the reflection angle of the V-direction scanning drive mirror 14 changes the horizontal scanning position performed by the LiDAR device 10 in the vertical direction. The laser light reflected by the V-direction scanning drive mirror 14 passes through the cover 19 and is irradiated forward of the LiDAR device 10.

[0030] The H-direction scanning drive mirror 13 and the V-direction scanning drive mirror 14 are configured to include, for example, a polygon mirror or a galvanometer mirror. The H-direction scanning drive mirror 13 and the V-direction scanning drive mirror 14 may each be configured with a MEMS mirror. The H-direction scanning drive mirror 13 and the V-direction scanning drive mirror 14 may be combined into one biaxial scan mirror, and the order in which the laser light Lb is reflected by the H-direction scanning drive mirror 13 and the V-direction scanning drive mirror 14 may be reversed.

[0031] The light receiving element 15 receives reflected light Lr, which is laser light Lb reflected by an object in the detection area. The reflected light Lr received by the light receiving element 15 contains information about the object located in the detection area. The light receiving element 15 is electrically connected to the point cloud data generation unit 16, and the information is input to the point cloud data generation unit 16 as an electrical signal.

[0032] The point cloud data generator 16 generates point data for each reflection position based on the direction of the reflection position where the laser beam Lb is reflected and the distance to the reflection position, based on data related to the emission timing of the laser beam Lb input from the driver circuit 11, information input from the light receiving element 15, and timing data of the information input from the light receiving element 15. The point data includes the coordinates of the point. Therefore, the point cloud data generator 16 generates point cloud data, which is a collection of point data. The point cloud data generator 16 is electrically connected to the determination device 20, and the point cloud data is input to the determination device 20.

[0033] The LiDAR device 10 configured as described above measures the detection area at predetermined time intervals, and the measurement results, which are point cloud data indicating the state of the detection area, are input to the determination device 20. As described above, each point in this point cloud data includes the coordinates of that point. Therefore, if the points are considered to be dots in an image, the point cloud data indicating the state of the detection area is image data indicating the detection area, and the LiDAR device 10 is an image acquisition device that acquires an image of the detection area. For this reason, hereinafter, the point cloud data may be referred to as image data. In this embodiment, the LiDAR device 10 measures the entire detection area.

[0034] FIG. 2 is a conceptual diagram showing a detection area DR measured by the LiDAR device 10 in this embodiment. In this embodiment, the LiDAR device 10 is disposed on top of a pole 50 installed in an outdoor parking lot and faces diagonally downward. The detection area DR measured by the LiDAR device 10 includes a parking area 51 as a placement area and an area surrounding the parking area 51. The height at which the LiDAR device 10 is placed is higher than the vehicle height of a vehicle CA, such as a passenger car or truck, and is, for example, 5 m. The parking area 51 is a partitioned area in which the vehicle CA, as a single moving object, is located. In the example shown in FIG. 2, three parking areas 51 are included in the detection area DR. In this embodiment, each parking area 51 has a rectangular shape that is elongated in a direction generally parallel to the first direction D1 and is generally the same shape and size as the others. The parking lot is further divided into the parking area 51 and an area other than the parking area 51 by a frame line FB along the outer edge of the parking area 51. The three parking areas 51 are numbered 1 to 3. In the situation shown in Figure 2, no moving object is located in parking area 51 No. 1, vehicle CA1 is located in parking area 51 No. 2, and vehicle CA2 is located in parking area 51 No. 3. Vehicle CA1 located in parking area 51 No. 2 is a truck that is taller than a passenger car, and vehicle CA2 located in parking area 51 No. 3 is a passenger car. Note that the parking area 51 may be any area partitioned so that one vehicle can be located therein, and there is no limit to the number of parking areas 51 included in the detection area DR.

[0035] 1 , the determination device 20 is composed of, for example, an integrated circuit such as a microcontroller, an integrated circuit (IC), a large-scale integrated circuit (LSI), or an application specific integrated circuit (ASIC), or an NC (numerical control) device. The determination device 20 may or may not use a machine learning device. The determination device 20 is electrically connected to a memory 30 and a monitor 40.

[0036] The determination device 20 includes a partition section 21 and a determination section 22. The partition section 21 and the determination section 22 are electrically connected via a bus line.

[0037] FIG. 3 is a diagram showing how the parking area 51 is divided into cells. A mobile object located in the parking area 51 is shown in FIG. 3 . The partition unit 21 divides the parking area 51 into a plurality of cells in the data representing the parking area 51. In FIG. 3 , the cells C are indicated by dotted lines. To avoid complicating the diagram, the cells C are shown simply in FIG. 3 , but the size of the cells C is smaller than that shown in FIG. 3 , and the parking area 51 is divided into more cells C than the cells C shown in FIG. 3 . In this embodiment, the parking area 51 is indicated by the coordinates of the four corners of the parking area 51. The coordinate data is stored in a memory 30, which will be described later, and the partition unit 21 reads the data from the memory 30. The partition unit 21 divides the parking area 51 into a plurality of cells C so that a plurality of rows CR are formed in which the cells C are lined up in a first direction D1 that is generally parallel to the longitudinal direction of the parking area 51 and along the parking area 51, and a plurality of columns CC are formed in which the cells C are lined up in a second direction D2 that is generally perpendicular to the first direction D1 along the parking area 51. The coordinates of each of the divided cells C are calculated as data, and the calculated data is sent to the determination unit 22 via the bus line.

[0038] The determination unit 22 determines whether each of the parking areas 51 serving as a placement area is in a first state in which a vehicle CA, which is a moving object, is located, or in a second state in which the vehicle CA is not located. The determination unit 22 generates determination information based on the determination result. The determination unit 22 outputs a signal indicating data of the determination information to the monitor 40 and stores the determination information in the memory 30. The determination unit 22 outputs such a signal for each parking area 51. In this specification, the term "determination" is used to include the output of such a signal. Note that the signal indicating the first state may be any signal that can distinguish between the first state and a state other than the first state, and the signal indicating the second state may be any signal that can distinguish between the second state and a state other than the second state. For example, the signal indicating the first state may be a signal indicating "11," and the signal indicating the second state may be a signal indicating "10."

[0039] In this embodiment, the determination unit 22 calculates the number of cells C above which points indicating a height equal to or greater than a predetermined height in the point cloud data are located, among the plurality of cells C in each parking area 51. In this embodiment, the predetermined height is set to, for example, a height that is higher than the height of a car stopper (not shown) provided in the parking area 51 and lower than the vehicle height of the passenger vehicle, e.g., 0.3 m, but is not limited thereto.

[0040] FIG. 4 is a diagram showing the state of cells in a parking area in the situation shown in FIG. 2. In FIG. 4, cell C, where points indicating a height above a predetermined height in the point cloud data for the parking area 51 are located above, is shown with hatching slanting to the left in the figure. When a moving object is located in the parking area 51, the point cloud data measured by the LiDAR device 10 includes points indicating the outer surfaces of the moving object, such as the top surface and periphery, and these points are located above the parking area 51. In FIG. 4, vehicle CA1 is located in the second parking area 51 from the bottom in FIG. 3, so points indicating the outer surface of vehicle CA1 are located above the parking area 51. In this specification, a point cloud indicating a height above a predetermined height in the point cloud data is referred to as a vehicle point cloud.

[0041] 3, since no vehicle CA is located in the bottom parking area 51, a vehicle point cloud does not exist, and a ground point cloud, which is a point indicating the height of the ground, is obtained. Furthermore, there is no cell C above which a point indicating a height above a predetermined height is located.

[0042] Here, because a tall truck is parked in the second parking area 51 from the bottom in Figure 3, a portion of the top parking area 51 in Figure 3 overlaps with the blind spot area BS, which is the blind spot of the LiDAR device 10. As a result, neither the vehicle point cloud nor the ground point cloud can be obtained. In the situation shown in Figure 3, vehicle CA2 is located within the blind spot area BS of the LiDAR device 10, so vehicle point cloud data representing vehicle CA2 cannot be obtained. In Figure 4, cell C, from which neither the vehicle point cloud nor the ground point cloud can be obtained, is shown with hatching slanting to the right.

[0043] The determination unit 22 calculates an overall occupancy rate, which is the ratio of the number of cells C in which points showing a predetermined height or higher in the point cloud data are located to the total number of multiple cells C that divide the target parking area 51, and when the overall occupancy rate is equal to or greater than a second threshold, determines that the target parking area 51 is in a first state in which a vehicle CA is located in the target parking area 51. Furthermore, when the overall occupancy rate is less than the second threshold, the determination unit 22 determines that the target parking area is in a second state in which a vehicle CA is not located in the target parking area.

[0044] The determination unit 22 calculates the ratio of blind spot areas BS in each parking area 51, which are hidden by the presence of a vehicle CA or the like and therefore do not provide information on the presence or absence of the vehicle CA, to the parking area 51. Hereinafter, the ratio of the blind spot areas BS in the parking area 51 to the entire parking area 51 will be referred to as the occlusion ratio. In this embodiment, the determination unit 22 calculates the ratio of the number of cells C in the parking area 51 that do not include a vehicle point cloud or a ground point cloud to the total number of cells C in the parking area 51 as the occlusion ratio. For example, in the bottom parking area 51 in FIG. 3 , there is nothing obstructing the view from the LiDAR device 10, so there is no blind spot area BS and the occlusion ratio is zero. Next, since a vehicle CA1 is parked in the second parking area 51 from the bottom in FIG. 3 , the portion of the top parking area 51 that is obstructed by the vehicle CA1 is the blind spot area BS. The occlusion ratio in the parking area 51 is calculated to be a value greater than zero. In addition, vehicle CA1 is parked in the second parking area 51 from the bottom, but since there are no vehicles or other obstacles blocking the view of the LiDAR device 10, the blind spot area BS is the shadow cast by vehicle CA1 itself as seen from the LiDAR device 10.

[0045] Returning to FIG. 1 , the memory 30 is configured to store information and to be able to read the stored information. The memory 30 is, for example, a non-transitory recording medium, and is preferably a semiconductor recording medium such as a random access memory (RAM) or a read-only memory (ROM), but may also include any type of recording medium, such as an optical recording medium or a magnetic recording medium. Note that "non-transitory" recording medium includes all computer-readable recording media except for transient, propagating signals, and does not exclude volatile recording media. Note that the memory 30 and the determination device 20 may be provided in an integrated package. The memory 30 stores various programs for controlling some components of the determination device 20 and generating information, as well as data necessary for generating information. The determination device 20 reads the programs and information stored in the memory 30. The memory 30 also stores information, etc., in response to instructions from the determination device 20.

[0046] The monitor 40 displays information corresponding to, for example, a signal input from the determination unit 22. For example, when a signal indicating a first state in which a mobile object is located in parking area No. 1 51 is input, the monitor 40 displays this state in a recognizable manner using graphics, text, etc. Note that the monitor 40 is not an essential component of the management system 1.

[0047] Next, the operation of the determination device 20 will be described.

[0048] Fig. 5 is a flowchart showing the operation of the determination device 20 in this embodiment. A program for executing the operation of this flowchart is stored in the memory 30. Therefore, the determination device 20 executes the flowchart of Fig. 5 by reading the program from the memory 30. As shown in Fig. 5, the operation of the determination device 20 in this embodiment includes steps S1 to S11.

[0049] At the start of this embodiment, the memory 30 of the management system 1 stores the determination result that the above-mentioned occlusion ratio for all parking areas 51 is below the first threshold value, and that the parking areas are in the first state.

[0050] <Step S1> This step is a step of dividing the parking area 51 into a plurality of cells C in the data representing the parking area 51 as a placement area. In this step, the partitioning unit 21 of the determination device 20 divides the parking area 51 into a plurality of cells C in the data representing the parking area 51, as shown in FIG. 3 . As described above, the partitioning unit 21 reads data on the coordinates of the four corners of the parking area 51 from the memory 30. The partitioning unit 21 divides the parking area 51 into a plurality of cells C so that a plurality of rows CR in which a plurality of cells C are arranged in a first direction D1 along the parking area 51 and a plurality of columns CC in which a plurality of cells C are arranged in a second direction D1 along the parking area 51 that is generally perpendicular to the first direction are formed. The partitioning unit 21 then calculates the coordinates of each cell C as data, and sends the calculated data to the determination unit 22 via the bus line. After this step, the determination device 20 advances the flow to step S2.

[0051] <Step S2> This step is a step of acquiring point cloud data from the LiDAR device 10. In this step, the judgment unit 22 of the determination device 20 acquires the point cloud data output from the LiDAR device 10. Note that in step S2 from the second time onwards, the judgment unit 22 acquires point cloud data measured after the measurement time of the previously acquired point cloud data. After this step, the determination device 20 advances the flow to step S3.

[0052] <Step S3> This step is a step in which n, which is the number of the parking area 51, is set to the initial value 1. Therefore, after this step, n = 1. After this step, the determination device 20 advances the flow to step S4.

[0053] <Step S4> This step is a step of calculating the occlusion ratio and the overall occupancy rate in the nth parking area 51. In this step, the determination unit 22 calculates the occlusion ratio and the overall occupancy rate. As described above for the determination unit 22, the overall occupancy rate is the ratio of the number of cells C in which points showing a height equal to or greater than a predetermined height in the point cloud data are located to the total number of cells C in the parking area 51. Furthermore, the occlusion ratio is the ratio of the number of cells C in the parking area 51 that do not include a vehicle point cloud and a ground point cloud to the total number of cells C in the parking area 51. After this step, the determination device 20 advances the flow to step S5.

[0054] <Step S5> This step is a step in which the next step is changed depending on the occlusion ratio calculated in step S4. In this step, if the occlusion ratio is equal to or greater than a predetermined first threshold, the determination device 20 proceeds to step S6 after this step. On the other hand, if the occlusion ratio is less than the first threshold, the determination device 20 proceeds to step S7.

[0055] <Step S6> This step is a step of maintaining the determination made immediately before the occlusion ratio becomes equal to or greater than the first threshold. In this step, if the state of the nth parking area 51 is determined to be the first state immediately before the occlusion ratio becomes equal to or greater than the first threshold, the determination unit 22 outputs a signal indicating the first state. If the state is determined to be the second state immediately before the occlusion ratio becomes equal to or greater than the first threshold, the determination unit 22 outputs a signal indicating the second state. In this step, the determination unit 22 outputs the signal to the monitor 40 and rewrites the determination result stored in the memory 30. After this step, the determination device 20 advances the flow to step S10.

[0056] <Step S7> This step determines the next step depending on the overall occupancy rate calculated in step S4. In this step, if the overall occupancy rate is equal to or greater than a predetermined second threshold, the determination device 20 proceeds to step S8. In addition, in this step, if the overall occupancy rate is less than the second threshold, the determination device 20 proceeds to step S9.

[0057] <Step S8> This step is a step of determining that the first state is present, in which the vehicle CA, which is a moving object, is located in the parking area 51. In this step, the determination unit 22 outputs a signal indicating the first state, and rewrites the determination result stored in the memory 30. After this step, the determination device 20 advances the flow to step S10.

[0058] <Step S9> This step is a step of determining that the parking area 51 is in the second state, in which the vehicle CA, which is a moving object, is not located. In this step, the determination unit 22 outputs a signal indicating the second state and rewrites the determination result stored in the memory 30. After this step, the determination device 20 advances the flow to step S10. Therefore, if the occlusion ratio is less than the first threshold in step S5, the determination device 20 determines whether the parking area 51 is in the first state or the second state based on the overall occupancy rate. That is, in this case, the determination device 20 determines whether the parking area 51 is in the first state or the second state based on the point cloud data of the detection area DR as image data.

[0059] <Step S10> This step is a step for incrementing the number of the parking area 51. n = n + 1 means that 1 is added to the value of n before this step to create a new n. After the first step S3, n = 1, so after this step following the first step S5, n = 2. After this step, the determination device 20 advances the flow to step S11.

[0060] <Step S11> This step is a step in which the next step varies depending on the value of n. In this step, if the value of n is equal to or less than nmax, which is the maximum number of the parking areas 51, the determination device 20 returns the flow to step S4, and if the value of n is greater than nmax, the determination device 20 returns the flow to step S2. Therefore, this determination is repeated until it is determined whether a vehicle is located in all of the parking areas 51. Furthermore, if it is determined whether a vehicle is located in all of the parking areas 51, the determination unit 22 acquires point cloud data measured after the measurement time of the previously acquired point cloud data, and determines whether a vehicle is located in the parking area 51 based on this point cloud data. In this embodiment, nmax is 3.

[0061] In this way, the management system 1 determines whether the vehicle CA is located in the parking area 51.

[0062] As described above, in the determination device 20, program, and management system 1 of this embodiment, when the occlusion ratio, which is the ratio of the blind spot area BS in the parking area 51 to the entire parking area 51 as a placement area, is equal to or greater than the first threshold, the determination made immediately before the occlusion ratio became equal to or greater than the first threshold is maintained. The smaller the ratio of the blind spot area BS in the parking area 51 to the entire parking area 51, the higher the accuracy of the determination tends to be. Therefore, the determination device 20, program, and management system 1 of this embodiment can determine whether the vehicle CA, as a moving object, is located even if there is a blind spot area BS in the parking area 51.

[0063] Next, a modified example of the above embodiment will be described. Note that components that are the same as or equivalent to those in the above embodiment will be assigned the same reference numerals and redundant description will be omitted unless otherwise specified.

[0064] (Modification 1) This modification differs from the above embodiment in that the determination device 20 performs a specific operation after the determination unit 22 maintains the determination.

[0065] In this modification, the determination unit 22 acquires point cloud data for a predetermined period after maintaining the determination. Then, if the determination unit 22 detects a vehicle CA exiting the blind spot BS of the parking area 51 while the occlusion ratio is equal to or greater than the first threshold during the predetermined period from the point cloud data, the determination unit 22 determines the above-described second state. If the determination unit 22 detects a vehicle CA entering the blind spot BS of the parking area 51 while the occlusion ratio is equal to or greater than the first threshold, the determination unit 22 determines the above-described first state. In this modification, the specific operation is performed in parallel with the operation of the above-described embodiment shown in FIG. 5 . The predetermined period in this modification is, for example, 10 minutes, but is not limited thereto. In this modification, the LiDAR device 10 outputs point cloud data of the detection area DR including the parking area 51 and the vicinity of the parking area 51 as image data.

[0066] 6 is a flowchart showing a specific operation of the determination device 20 in this modified example. As shown in FIG. 6, the specific operation of the determination device 20 in this modified example includes steps S21 to S27, and is performed after step S6.

[0067] <Step S21> This step is a step in which the determination unit 22 changes the next step depending on the detection of a vehicle CA entering or exiting the blind spot BS of the parking area 51 for which the determination unit 22 has maintained its determination. In this example, the determination unit 22 detects the vehicle CA by calculating the difference between the point cloud data and reference point cloud data prepared in advance and stored in the memory 30. The reference point cloud data is, for example, point cloud data of the detection area DR obtained by the LiDAR device 10 in a state in which the vehicle CA is not located in the detection area DR. Note that the method for detecting the vehicle CA by the determination unit 22 is not limited. Then, in this step, the determination unit 22 detects the vehicle CA entering or exiting the blind spot BS of the parking area 51 from the point cloud data for a predetermined period. If the determination unit 22 detects the vehicle CA exiting the blind spot BS of the parking area 51, the determination device 20 advances the flow to step S22. Furthermore, if the determination unit 22 does not detect the vehicle CA leaving the blind spot area BS of the parking area 51, the determination device 20 advances the flow to step S24.

[0068] <Step S22> This step is a step in which the next step is changed depending on the occlusion ratio. In this step, if the occlusion ratio is equal to or greater than the first threshold, the determination device 20 proceeds to step S23. In addition, if the occlusion ratio is less than the first threshold, the determination device 20 ends the specific operation.

[0069] <Step S23> This step is a step of determining that the parking area 51 is in a second state, in which the vehicle CA, which is a moving object, is not located. In this step, the determination unit 22 outputs a signal indicating the second state and rewrites the determination result stored in the memory 30. That is, the determination unit 22 stores the determination result immediately before the occlusion ratio becomes equal to or greater than the first threshold value in the memory 30 as the second state. After this step, the determination device 20 ends the specific operation.

[0070] <Step S24> This step is a step in which the next step is differentiated depending on whether or not the vehicle CA has entered the blind spot BS of the parking area 51 for which the determination unit 22 has maintained its determination. In this step, the determination unit 22 detects the vehicle CA entering the blind spot BS of the parking area 51 from the point cloud data for a predetermined period, as in step S21. If the determination device 20 detects the vehicle CA entering the blind spot BS of the parking area 51, the flow proceeds to step S25. Furthermore, if the determination device 20 does not detect the vehicle CA entering the blind spot BS of the parking area 51 in this step, the flow proceeds to step S27.

[0071] <Step S25> This step is a step in which the next step is changed depending on the occlusion ratio. In this step, if the occlusion ratio is equal to or greater than the first threshold, the determination device 20 proceeds to step S26. On the other hand, in this step, if the occlusion ratio is less than the first threshold, the determination device 20 ends the specific operation.

[0072] <Step S26> This step is a step of determining that the first state is present, in which the vehicle CA, which is a moving object, is located in the parking area 51. In this step, the determination unit 22 outputs a signal indicating the first state and rewrites the determination result stored in the memory 30. That is, the determination unit 22 stores the determination result immediately before the occlusion ratio becomes equal to or greater than the first threshold value in the memory 30 as the first state. After this step, the determination device 20 ends the specific operation.

[0073] <Step S27> This step is a step in which the next step is changed depending on the occlusion ratio. In this step, if the occlusion ratio is equal to or greater than the first threshold, the determination device 20 returns the flow to step S21. Also, if the occlusion ratio is less than the first threshold in this step, the determination device 20 ends the specific operation. In other words, if the occlusion ratio is less than the first threshold during the specific operation, the determination device 20 does not determine whether the state is the first state or the second state.

[0074] As described above, in the determination device 20, program, and management system 1 of this modified example, after maintaining the determination, if a vehicle CA is detected leaving a blind spot BS with the occlusion ratio being equal to or greater than the first threshold from the point cloud data, the determination device 20 determines the state to be the second state, and if a vehicle CA is detected entering a blind spot BS with the occlusion ratio being equal to or greater than the first threshold, the determination device 20 determines the state to be the first state. This can improve the accuracy of determination when a blind spot BS exists in the parking area 51.

[0075] (Modification 2) This modification differs from the above embodiment in that the determination device 20 performs another specific operation after the determination unit 22 maintains the determination.

[0076] In this modification, when the occlusion ratio is equal to or greater than the first threshold value after a predetermined period of time has elapsed since the determination was maintained immediately before the occlusion ratio became equal to or greater than the first threshold value, the determination unit 22 determines that the parking area 51 for which the determination unit 22 maintained its determination is in a third state, which is different from the first state and the second state. Specifically, the determination unit 22 determines that the state of the parking area 51 is unknown. In this modification, another specific operation is performed in parallel with the operation of the embodiment shown in FIG. 5. The predetermined period of time in this modification is, for example, 10 minutes, but is not limited thereto.

[0077] 7 is a flowchart showing another specific operation of the determination device 20 in this modified example. As shown in FIG. 7, the other specific operation of the determination device 20 in this modified example includes steps S31 to S35, and is performed after step S6.

[0078] <Step S31> This step is a step in which the next step differs depending on whether a predetermined period has elapsed since the determination unit 22 maintained the determination. In this step, if the predetermined period has elapsed since the determination unit 22 maintained the determination, the determination device 20 advances the flow to step S32. If the predetermined period has not elapsed since the determination unit 22 maintained the determination, the determination device 20 returns the flow to step S31.

[0079] <Step S32> This step is a step of acquiring point cloud data of the parking area 51 for which the determination has been maintained from the LiDAR device 10. In this step, the determination unit 22 of the determination device 20 acquires the point cloud data output from the LiDAR device 10. After this step, the determination device 20 advances the flow to step S33.

[0080] <Step S33> This step is a step of calculating the occlusion ratio in the parking area 51 for which the determination unit 22 has maintained the determination. In this step, the determination unit 22 calculates the occlusion ratio. After this step, the determination device 20 advances the flow to step S34.

[0081] <Step S34> This step is a step in which the next step is changed depending on the occlusion ratio. If the occlusion ratio is equal to or greater than the first threshold in this step, the determination device 20 proceeds to step S35. If the occlusion ratio is less than the first threshold, the determination device 20 ends another specific operation.

[0082] <Step S35> This step is a step for determining that the parking area 51 is in the third state. In this step, the determination unit 22 outputs a signal indicating the third state and rewrites the determination result stored in the memory 30. After this step is completed, the determination device 20 ends another specific operation. In other words, if the occlusion ratio is less than the first threshold value during the other specific operation, the determination device 20 determines that the parking area 51 is not in the third state.

[0083] As described above, in the determination device 20, the program, and the management system 1 of this modified example, if the occlusion ratio is equal to or greater than the first threshold after a predetermined period has elapsed since the timing at which the determination was maintained immediately before the occlusion ratio became equal to or greater than the first threshold, the determination device 20, the program, and the management system 1 determine that the state is the third state, which is different from the first state and the second state. This may indicate that the accuracy of the determination is decreasing.

[0084] Although the present invention has been described above using the above-mentioned embodiment and modified examples as examples, the present invention is not limited to these.

[0085] For example, in the above embodiment, the partition unit 21 is described as dividing the parking area 51 so as to form a plurality of rows CR in which the cells C are arranged in a first direction D1 along the parking area 51, and a plurality of columns CC in which the cells C are arranged in a second direction D2 along the parking area 51 that is generally perpendicular to the first direction D1. However, the first direction D1 may be any direction as long as it is along the parking area 51, and the second direction D2 may be any direction as long as it is along the parking area 51 and non-parallel to the first direction D1. For example, the angle between the first direction D1 and the second direction D2 may be an acute angle, or the first direction D1 may be non-parallel to the longitudinal direction of the parking area 51. Furthermore, the partition unit 21 may divide the parking area 51 into a plurality of cells C. For example, the partition unit 21 may divide the parking area 51 so as to form one row CR in which the cells C are arranged in the first direction D1.

[0086] Furthermore, the operational flow of the determination device 20 in the above embodiment and the above modification is not limited. For example, in the above embodiment, step S2 may be performed after step S3. Furthermore, the above embodiment and the above modification can be combined as appropriate.

[0087] Furthermore, in the above embodiment and the above modified example, a management system 1 including one LiDAR device 10 has been described as an example, but there may be multiple LiDAR devices 10.

[0088] Furthermore, in the above embodiment and the above modified example, the image acquisition device is the LiDAR device 10, but it may also be a camera.

[0089] Furthermore, in the above embodiment and modified example, the placement area is the parking area 51. However, the placement area may be an area partitioned so that one mobile object can be located. Therefore, the placement area may be an area other than the parking area 51, and may be an indoor area. For example, the placement area may be an area where one transport container called an intermodal container is located. In this case, the management system 1 can determine whether a transport container is located in the placement area.

[0090] Furthermore, the method for calculating the occlusion ratio is not limited to the method described in the above embodiment. For example, the occlusion ratio may be the ratio between the width of the blind spot area BS in the parking area 51 in the first direction D1 and the width of the parking area 51 in the first direction D1.

[0091] According to the present invention, a determination device, program, and management system are provided that can determine whether a moving object is located even if there is a blind spot in the placement area, and can be used in fields such as indoor and outdoor management systems.

Claims

1. A determination device that determines the presence or absence of a moving object from image data output from an image acquisition device that acquires an image of a detection area including a placement area partitioned so that a single moving object is located, the determination device determines whether the state is a first state in which the moving object is located in the placement area, or a second state in which the moving object is not located in the placement area, and when the ratio of the blind spot area in the placement area to the entire placement area is equal to or greater than a first threshold, maintains the determination made just before the ratio became equal to or greater than the first threshold.

2. The determination device described in claim 1, characterized in that after maintaining the determination, if the moving object is detected from the image data leaving the blind spot area with the ratio being equal to or greater than the first threshold, it is determined to be in the second state, and if the moving object is detected entering the blind spot area with the ratio being equal to or greater than the first threshold, it is determined to be in the first state.

3. The determination device described in claim 1, characterized in that if the ratio is equal to or greater than the first threshold value after a predetermined period has elapsed from the time when the determination was maintained just before the ratio became equal to or greater than the first threshold value, it determines that the device is in a third state different from the first state and the second state.

4. A determination device according to any one of claims 1 to 3, characterized in that the image acquisition device is a LiDAR device that outputs point cloud data of the detection area as the image data.

5. The determination device described in claim 4, characterized in that the ratio is calculated as the ratio of the number of cells in which points of the point cloud data input from the LiDAR device are not located to the total number of multiple cells that divide the placement area.

6. The determination device described in claim 4, characterized in that it determines that the moving body is located in the placement area when the ratio of the number of cells in which points indicating a predetermined height or higher in the point cloud data are located to the total number of cells dividing the placement area is greater than or equal to a second threshold value, and determines that the moving body is not located in the placement area when the ratio is less than the second threshold value.

7. A program executed by a determination device that determines the presence or absence of a moving object from image data output from an image acquisition device that acquires an image of a detection area including a placement area partitioned so that a single moving object is located, the program causing the determination device to execute a step of determining whether the state is a first state in which the moving object is located in the placement area, or a second state in which the moving object is not located in the placement area, and in the step, if the ratio of the blind spot area in the placement area to the entire placement area is equal to or greater than a first threshold, the program maintains the determination at the time just before the ratio becomes equal to or greater than the first threshold.

8. A management system comprising: an image acquisition device that acquires an image of a detection area including a placement area partitioned so that one moving object can be located; and a determination device that determines whether the moving object is present or absent from image data output from the image acquisition device, wherein the determination device determines whether the state is a first state in which the moving object is located in the placement area, or a second state in which the moving object is not located in the placement area, and when the ratio of blind spot areas to the entire placement area is equal to or greater than a first threshold, maintains the determination made just before the ratio becomes equal to or greater than the first threshold.

Images