Detection device, program, and detection system

Abstract

To provide a detection device, a program, and a detection system capable of improving accuracy of detection of movement of a moving body.SOLUTION: A detection device 20 detects a mobile object M from an image acquired by a LiDAR device 10 that acquires an image of a detection region DR including one region 50a and another region 50b that are in contact with each other across a boundary 55, and detects that the mobile object M moves from the one region 50a to the other region 50b when the mobile object M passes through a first detection line 57a located in the other region 50a from the one region 50b.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a detection device, a program, and a detection system. [Background technology]

[0002] BACKGROUND ART Detection systems that detect moving objects such as people and vehicles are known, and Patent Document 1 listed below discloses such a detection system.

[0003] In the detection system described in Patent Document 1 below, a control device detects moving objects within a specified area based on moving object information obtained by a LiDAR (Light Detection And Ranging) device, and generates a moving object distribution map showing the positions of the moving objects at specified time intervals. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-149836 Summary of the Invention [Problem to be solved by the invention]

[0005] There is a demand for detecting whether a moving object has crossed a set boundary line. For example, the detection system described in Patent Document 1 can obtain a moving object distribution map including the boundary line and obtain the trajectory of the moving object from the map, thereby achieving the detection. However, when a moving object is located near the boundary line in one of two areas separated by a boundary line, the moving object may be erroneously detected as being located within the other area.

[0006] Therefore, an object of the present invention is to provide a detection device, a program, and a detection system that can improve the accuracy of detecting the movement of a moving object. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, the detection device of the present invention is a detection device that detects a moving object from image data acquired by an image acquisition device that acquires an image of a detection area including one area and another area that are adjacent to each other across a boundary line, and is characterized in that when the moving object passes from one area to the other area, it detects that the moving object is moving from one area to the other area.

[0008] The present invention also provides a program executed by a detection device that detects a moving body from image data acquired by an image acquisition device that acquires an image of a detection area including one area and another area that are adjacent to each other across a boundary line, characterized in that the program causes the detection device to execute a step of detecting that the moving body is moving from one area to the other area when the moving body passes from the one area through a first detection line located within the other area.

[0009] The detection system of the present invention comprises an image acquisition device that acquires an image of a detection area including one area and another area that are adjacent to each other across a boundary line, and a detection device that detects a moving object from the image data acquired by the image acquisition device, wherein the detection device detects that the moving object is moving from one area to the other area when the moving object passes through a first detection line located within the other area.

[0010] The above detection device, program, and detection system can reduce the likelihood of erroneously detecting a moving object located near a boundary line in one area as being located in another area, thereby improving the accuracy of detecting the movement of the moving object.

[0011] The first sensing line may extend along the boundary line.

[0012] The detection device may detect that the moving object is moving from one area to the other area when the moving object passes through a second detection line located within the one area and then passes through the first detection line.

[0013] This configuration makes it more difficult to erroneously detect a moving object located near a boundary line in one area as being located in the other area, thereby improving the accuracy of detecting the movement of the moving object.

[0014] The first and second sensing lines may be arranged along the boundary line, and a distance between the first sensing line and the boundary line may be equal to a distance between the second sensing line and the boundary line.

[0015] The detection device may detect that the moving object is moving from the other area to the one area when the moving object passes through a second detection line located within the one area from the other area.

[0016] With this configuration, it is possible to detect the movement of a moving object in both directions, from one area to the other area and from the other area to the one area.

[0017] At least one of the one area and the other area may be a closed area.

[0018] The detection device may detect that the moving body is moving from one area to another area when the moving body passes through another first detection line located in another area adjacent to the one area across another boundary line.

[0019] With this configuration, it is possible to detect the movement of a moving object between three or more areas, for example, between areas arranged in a matrix, or between areas aligned in a predetermined direction.

[0020] The detection device may detect that the moving body is moving from the one region to the other region when the moving body is located in the one region in the image data of at least two consecutive frames out of the image data of the multiple frames, and when the moving body is located on the opposite side of the boundary line from the first detection line in the other region in the image data of at least one frame after the at least two consecutive frames.

[0021] With this configuration, the accuracy of detecting the movement of a moving object from one area to another area can be further improved.

[0022] In the detection system, the image acquisition device may be a LiDAR device that measures the detection area.

[0023] In the detection system, the LiDAR device may not measure the side of the one region opposite the boundary line.

[0024] With this configuration, the range measured by the LiDAR device can be narrowed, and the load on the LiDAR device can be reduced. [Effects of the Invention]

[0025] As described above, according to the present invention, it is possible to provide a detection device, a program, and a detection system that can improve the accuracy of detecting the movement of a moving object. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is a schematic diagram illustrating a detection system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram mainly showing a LiDAR device and a detection device according to an embodiment. [Figure 3] FIG. 10 is a diagram for explaining a reference region. [Figure 4] 4 is a flowchart illustrating an operation of the detection device according to the embodiment. [Figure 5]10 is a diagram for explaining detection of movement of a moving object in Modification 2. FIG. [Figure 6] 13 is a diagram for explaining detection of movement of a moving object in Modification 3. FIG. [Figure 7] 13 is a diagram for explaining an area in which a detection unit in Modification 4 detects a moving object. FIG. [Figure 8] FIG. 13 is a diagram for explaining detection of movement of a moving object in Modification 5. DETAILED DESCRIPTION OF THE INVENTION

[0027] Preferred embodiments of a detection device, a program, and a detection 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 present invention. The present invention can be modified and improved within the scope of the claims without departing from the spirit thereof. The present invention may also be realized by appropriately combining the components in the embodiments exemplified below. 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 denoted with reference symbols only in part, and some reference symbols may be omitted.

[0028] 1 is a schematic diagram showing a detection system according to an embodiment. The detection system 1 of this embodiment mainly includes a LiDAR device 10 as an image acquisition device, a detection device 20, a memory 30, and a monitor 40.

[0029] As shown in FIG. 1, the LiDAR device 10 is installed at a slightly elevated position so as to be able to detect objects within a detection region DR. For example, if the detection region DR includes a road, the LiDAR device 10 is installed on a support pillar near the road, and if the detection region DR is indoors, the LiDAR device 10 is installed on a pillar or the like. The detection system 1 of this embodiment detects objects within the detection region DR measured by the LiDAR device 10. Through this detection, the LiDAR device 10 can detect background objects such as walls and benches, as well as moving objects M such as people and vehicles. In FIG. 1, the detection region DR includes the road, and multiple vehicles are depicted as the moving objects M.

[0030] FIG. 2 is a block diagram mainly showing the LiDAR device 10 and the detection device 20. As the LiDAR device 10 of this embodiment, for example, a raster scan type LiDAR device is used. 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 generation unit 16. Note that in the example of FIG. 1, the LiDAR device 10 is a mechanical type LiDAR device, but it may also be a phased array type LiDAR device that does not include a drive unit.

[0031] The cover 19 has a storage space for 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 DR.

[0032] 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.

[0033] 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.

[0034] The H-direction scanning drive mirror 13 has 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. The change in the reflection angle of the H-direction scanning drive mirror 13 allows the LiDAR device 10 to perform horizontal scanning.

[0035] The V-direction scanning drive mirror 14 has a mirror that reflects the laser light Lb reflected by the H-direction scanning drive mirror 13, and a drive unit (not shown) that is 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.

[0036] 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 an MEMS mirror. The H-direction scanning drive mirror 13 and the V-direction scanning drive mirror 14 may be combined into one biaxial scan type 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.

[0037] The light receiving element 15 is an element that receives reflected light Lr, which is laser light Lb reflected by an object in the detection region DR. The reflected light Lr received by the light receiving element 15 contains information related to the object located within the detection region DR. 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.

[0038] 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 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 detection device 20, and the point cloud data is input to the detection device 20.

[0039] The LiDAR device 10 configured as described above measures the detection region DR at predetermined time intervals, and inputs point cloud data indicating the state of the detection region DR, which is the measurement result, to the detection device 20. As described above, each point in this point cloud data includes the coordinates of the point. Therefore, if the points are considered to be dots in an image, the point cloud data indicating the state of the detection region DR is data of an image indicating the detection region DR, and the LiDAR device 10 is an image acquisition device that acquires the image of the detection region DR. 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 region DR.

[0040] The detection 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 detection device 20 may or may not use a machine learning device. The detection device 20 is electrically connected to the driver circuit 11, memory 30, and monitor 40 of the LiDAR device 10. The detection device 20 does not have to be electrically connected to the driver circuit 11.

[0041] The memory 30 is configured to store information and 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 detection device 20 may be provided in an integrated package. The memory 30 stores various programs for controlling several components of the detection device 20 and generating information, as well as data required for generating information. The detection 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 detection device 20.

[0042] The detection device 20 has a reference region setting unit 21, a detection unit 22, a movement detection unit 23, and a counting unit 24, which are electrically connected to each other via a bus line.

[0043] The reference region setting unit 21 sets a reference region within the detection region DR in image data indicating the detection region DR of a plurality of frames. The reference region setting unit 21 also sets a detection line, which will be described later, within the reference region.

[0044] FIG. 3 is a diagram illustrating the reference area. As shown in FIG. 3, the reference area 50 of this embodiment is a rectangle that is elongated in a predetermined direction. The reference area setting unit 21 of this embodiment sets the reference area as one area 50a, which is a first closed area, and the other area 50b, which is a second closed area, so that they are adjacent to each other with a boundary line 55 in between. The short sides of the areas 50a and 50b are connected to each other, and no gap is formed between the areas. The sizes of the areas 50a and 50b are larger than the size that allows at least one moving object M to be positioned inside.

[0045] The reference region setting unit 21 also sets a first detection line 57a within the region 50b. In this embodiment, the first detection line 57a is aligned with the boundary line 55. A distance W1 between the boundary line 55 and the first detection line 57a is generally constant along the longitudinal direction of the first detection line 57a. In this embodiment, the first detection line 57a is set to follow the entire boundary line 55, but this is not limited to this. The first detection line 57a may follow only a portion of the boundary line 55, or may not follow the boundary line 55. Furthermore, the distance W1 between the boundary line 55 and the first detection line 57a may vary along the longitudinal direction of the first detection line 57a. Information about the positions and shapes of the regions 50a and 50b, and information about the positions of the boundary line 55 and the first detection line 57a are sent to the memory 30 and stored therein.

[0046] The detection unit 22 generates position information of the moving object M in the detection area DR from image data input from the LiDAR device 10. In this embodiment, the detection unit 22 detects the moving object M by calculating the difference between the image data and data of a reference image prepared in advance and stored in the memory 30, and generates position information of the moving object M. The reference image is an image showing the detection area DR in a state where the moving object M is not located, for example, an image obtained by measuring the detection area DR using the LiDAR device 10 in a state where the moving object M is not located. Note that the reference image is not limited to an image obtained in advance by the LiDAR device 10. For example, the reference image may be updated to an image in which the moving object M is not detected by the detection unit 22, or may be updated at predetermined intervals. Furthermore, even if the moving object M is detected in an image, if the moving object M does not move for a predetermined period of time, an image including the moving object M may be used as the reference image. Alternatively, the reference image may be an image obtained by measuring the detection area DR using the LiDAR device 10 at a time when there is a high probability that the moving object M is not located, for example, at a specific time during the night. The position information of the moving object M is sent to the memory 30 and stored in the memory 30, but does not have to be stored in the memory 30. The method of detecting the moving object M by the detection unit 22 is not limited.

[0047] The movement detection unit 23 detects whether the moving object M moves from the region 50a to the region 50b based on the position information of the moving object M generated by the detection unit 22 and the position information of the first detection line 57a. The movement detection unit 23 detects that the moving object M moves from the region 50a to the region 50b when the moving object M passes through the first detection line 57a located within the region 50b from the region 50a.

[0048] The counting unit 24 generates movement amount information, which is the amount of moving object M moving from area 50a to area 50b. In this embodiment, the counting unit 24 generates the movement amount information based on the detection result of the movement of the moving object M from area 50a to area 50b by the movement detection unit 23. The counting unit 24 outputs a signal indicating data of the movement amount information to the monitor 40, and stores the movement amount information in the memory 30.

[0049] The monitor 40 displays, for example, movement amount information. Note that the monitor 40 is not an essential component of the detection system 1.

[0050] Next, the operation of the detection device 20 will be described.

[0051] Fig. 4 is a flowchart showing the operation of the detection device 20 in this embodiment. A program for executing the operation of this flowchart is stored in the memory 30. Therefore, the detection device 20 executes the flowchart of Fig. 4 by reading the program from the memory 30. As shown in Fig. 4, the operation of the detection device 20 of this embodiment includes steps S1 to S5.

[0052] <Step S1> This step is a step of acquiring image data from the LiDAR device 10. In this step, the reference area setting unit 21 of the detection device 20 acquires image data of a plurality of frames output from the LiDAR device 10. After this step, the detection device 20 advances the flow to step S2.

[0053] <Step S2> This step is a step of setting regions 50a and 50b that are adjacent to each other across the boundary line 55 in the detection region DR. In this step, the reference region setting unit 21 of the detection device 20 sets the regions 50a and 50b. The reference region setting unit 21 also sets a first detection line 57a within the region 50b. After this step, the detection device 20 advances the flow to step S3.

[0054] <Step S3> This step is a step of detecting a moving object M located in the detection region DR from the image data of multiple frames in which multiple reference regions are set, over a predetermined period including multiple frames. In this step, the detection unit 22 of the detection device 20 detects the moving object M located in the detection region DR from the image data of multiple frames in which regions 50a and 50b are set, over a predetermined period including multiple frames, and generates position information of the moving object M. After this step, the detection device 20 advances the flow to step S4.

[0055] <Step S4> This step is a step of detecting movement of moving object M from area 50a to area 50b. In this step, when moving object M passes through first detection line 57a set in area 50b from area 50a, movement detection unit 23 of detection device 20 detects that moving object M moves from area 50a to area 50b. After this step, detection device 20 advances the flow to step S5.

[0056] <Step S5> This step is a step of counting the moving objects M detected as moving from the area 50a to the area 50b and generating movement amount information, which is the amount of the moving objects M moving from the area 50a to the area 50b. In this step, the counting unit 24 of the detection device 20 generates movement amount information of the moving objects M moving from the area 50a to the area 50b based on the detection result of the movement of the moving objects M from the area 50a to the area 50b by the movement detection unit 23. The counting unit 24 outputs a signal indicating data of the movement amount information to the monitor 40, and the movement amount information is displayed on the monitor 40. The counting unit 24 also stores the movement amount information in the memory 30.

[0057] In this way, in the detection system 1 of this embodiment, the movement of the moving body M from area 50a to area 50b is detected by the movement detection unit 23 of the detection device 20, and movement amount information of the moving body M moving from area 50a to area 50b is generated by the counting unit 24 of the detection device 20.

[0058] As described above, one aspect of the present invention according to this embodiment is the detection device 20 that detects a moving object M from image data acquired by the LiDAR device 10, which is an image acquisition device that acquires an image of a detection region DR including the regions 50a and 50b that are adjacent to each other across the boundary line 55. The detection device 20 detects that the moving object M moves from the region 50a to the region 50b when the moving object M passes through the first detection line 57a located within the region 50b from the region 50a.

[0059] Another aspect of the present invention according to the above embodiment is a program executed by the detection device 20 that detects a moving object from image data acquired by the LiDAR device 10 that acquires an image of a detection region DR including regions 50a and 50b that are adjacent to each other across a boundary line 55. The program causes the detection device 20 to execute a step of detecting that the moving object M has moved from the region 50a to the region 50b when the moving object M passes through a first detection line 57a located within the region 50b.

[0060] Furthermore, yet another aspect of the present invention according to the above embodiment is a detection system 1 including a LiDAR device 10 that acquires an image of a detection region DR including regions 50a and 50b that are adjacent to each other across a boundary line 55, and a detection device 20 that detects a moving object M from image data acquired by the LiDAR device 10. When the moving object M passes through a first detection line 57a located within the region 50b from the region 50a, the detection device 20 detects that the moving object M has moved from the region 50a to the region 50b.

[0061] According to the detection device 20, the program, and the detection system 1 of the present embodiment, it is possible to reduce the likelihood of erroneously detecting a moving object M located near the boundary line 55 in the area 50a as being located in the other area 50b. Therefore, it is possible to improve the accuracy of detecting the movement of the moving object M.

[0062] 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 given the same reference numerals and will not be described again unless otherwise specified.

[0063] (Variation 1) In the above embodiment, the image acquisition device that acquires an image of the detection area DR is the LiDAR device 10. However, the image acquisition device is not limited to this. The image acquisition device in this modified example is a camera. Note that the image data acquired by the LiDAR device 10 includes data on the distance from the LiDAR device 10. Therefore, as in the above embodiment, by using the LiDAR device 10 as the image acquisition device, even if the image acquisition device is positioned to acquire an image of the detection area DR from diagonally above the detection area DR, the movement of the moving object M can be detected more accurately than when the image acquisition device is a camera.

[0064] (Variation 2) In the above embodiment, the movement detection unit 23 detects that the moving object M moves from the region 50a to the region 50b when the moving object M passes through the first detection line 57a located in the region 50b from the region 50a. However, the movement detection unit 23 may further use the second detection line located within the region 50a to detect the movement of the moving object M from the region 50a to the region 50b.

[0065] 5 is a diagram illustrating detection of movement of a moving object M from region 50a to region 50b in this modified example. This modified example differs from the above embodiment in that the reference region setting unit 21 sets a second detection line 57b within region 50a. In this modified example, the second detection line 57b extends along the boundary line 55. The distance W2 between the boundary line 55 and the second detection line 57b is generally constant along the longitudinal direction of the second detection line 57b and is equal to the distance W1 between the boundary line 55 and the first detection line 57a.

[0066] The movement detection unit 23 of this modified example detects that the moving object M has moved from the area 50a to the area 50b when the moving object M passes through the second detection line 57b located within the area 50a and then the first detection line 57a. This configuration makes it less likely that the moving object M located near the boundary line 55 within the area 50a will be erroneously detected as being located within the area 50b. Therefore, the accuracy of detection of the movement of the moving object M can be further improved.

[0067] In this modification, distance W1 and distance W2 are equal, but they do not have to be equal. Furthermore, distance W1 may vary along the longitudinal direction of first detection line 57a, and distance W2 may vary along the longitudinal direction of second detection line 57b. Second detection line 57b may extend along a portion of boundary line 55, or may not extend along boundary line 55.

[0068] (Variation 3) In the above embodiment, the movement detection unit 23 detects the movement of the moving object M from the area 50a to the area 50b. However, the movement detection unit 23 may also detect the movement of the moving object M from the area 50b to the area 50a. In other words, the movement detection unit 23 may detect the movement of the moving object M in both directions, from the area 50a to the area 50b and from the area 50b to the area 50a.

[0069] 6 is a diagram illustrating detection of movement of a moving object M in this modified example. Similar to modified example 2, this modified example differs from the above embodiment in that the reference area setting unit 21 sets a second detection line 57b within the area 50a. In this modified example, the second detection line 57b is aligned with the boundary line 55. The distance W2 between the boundary line 55 and the second detection line 57b is approximately constant along the longitudinal direction of the second detection line 57b and is equal to the distance W1 between the boundary line 55 and the first detection line 57a.

[0070] In this modification, the movement detection unit 23 detects that the moving object M is moving from the region 50a to the region 50b when the moving object M passes through the first detection line 57a from the region 50a. Furthermore, the movement detection unit 23 detects that the moving object M is moving from the region 50b to the region 50a when the moving object M passes through the second detection line 57b from the region 50b. According to this modification, the movement of the moving object M can be detected in both directions, from the region 50a to the region 50b and from the region 50b to the region 50a.

[0071] In this modification, distance W1 and distance W2 are equal, but they do not have to be equal. Furthermore, distance W1 may vary along the longitudinal direction of first detection line 57a, and distance W2 may vary along the longitudinal direction of second detection line 57b. Second detection line 57b may extend along a portion of boundary line 55, or may not extend along boundary line 55.

[0072] Similarly to Modification 2, the movement detection unit 23 of this modification may detect that the moving object M is moving from the region 50a to the region 50b when the moving object M passes from the region 50a through the second detection line 57b located within the region 50a and then through the first detection line 57a. The movement detection unit 23 of this modification may detect that the moving object M is moving from the region 50b to the region 50a when the moving object M passes from the region 50b through the first detection line 57a located within the region 50b and then through the second detection line 57b. In this case, the second detection line 57b used when detecting the movement of the moving object M from the region 50a to the region 50b is the same as the second detection line 57b used when detecting the movement of the moving object M from the region 50b to the region 50a, but may be different. Furthermore, the first detection line 57a used when detecting the movement of the moving object M from the region 50b to the region 50a is the same as the first detection line 57a used when detecting the movement of the moving object M from the region 50a to the region 50b, but may be different. That is, two first detection lines 57a may be provided in the region 50b, and two second detection lines 57b may be provided in the region 50a.

[0073] (Variation 4) In the above embodiment, the LiDAR device 10 measures the entire detection region DR. That is, the LiDAR device 10 acquires image data showing the entire detection region DR. However, it is sufficient if the detection unit 22 can detect a moving object M moving from the region 50a to the region 50b adjacent to the region 50a across the boundary line 55.

[0074] In this modification, the LiDAR device 10 does not measure the area of ​​the detection region DR that corresponds to the non-measurement portion 58a shown in FIG. 7 , but measures the area other than the non-measurement portion 58a. Specifically, in this modification, the LiDAR device 10 measures the entire detection region DR as a preparatory measurement and acquires image data showing the entire detection region DR. Next, the reference region setting unit 21 of the detection device 20 sets regions 50a and 50b in the image data, and the detection device 20 sends position information of the regions 50a and 50b to the driver circuit 11 of the LiDAR device 10. Next, as a main measurement, the driver circuit 11 controls several components of the LiDAR device 10, such as the laser light source 12, based on the position information of the region 50a input from the detection device 20, to cause the LiDAR device 10 to not measure the area that corresponds to the non-measurement portion 58a, but to measure the area other than the non-measurement portion 58a, including the first detection line 57a. That is, the LiDAR device 10 of this modified example acquires image data showing an area other than the non-measurement portion 58a in the detection area DR that includes the first detection line 57a. The detection unit 22 of this modified example does not detect a moving object M located in the non-measurement portion 58a in the area 50b of the detection area DR, but detects a moving object M located in an area of ​​the detection area DR other than the non-measurement portion 58a that includes the first detection line 57a.

[0075] In Fig. 7, non-measurement portion 58a is hatched with multiple diagonal lines. In this modification, non-measurement portion 58a is on the opposite side of boundary line 55 in region 50a. However, non-measurement portion 58a is not limited to this and may be any region that is separated from boundary line 55 in region 50a. In Fig. 7, non-measurement portion 58a has a rectangular shape, but this is not limited thereto and may be, for example, a circular shape.

[0076] According to the detection device 20 of this modified example, the range in which the detection unit 22 detects the moving body M can be narrowed, and the calculation load on the detection device 20 required to detect the moving body M can be reduced. Furthermore, according to the detection device 20 of this modified example, the range in which the LiDAR device 10 measures can be narrowed, and the load on the LiDAR device 10 can be reduced.

[0077] (Variation 5) In the above embodiment, the reference area setting unit 21 sets, as the reference area 50, one area 50a and the other area 50b that are adjacent to each other across the boundary line 55, but this is not limited to this. The reference area setting unit 21 may set, in addition to the areas 50a and 50b, one or more other areas that are adjacent to the area 50a across another boundary line as the reference area 50. Specifically, the reference area setting unit 21 may set the reference areas in a matrix pattern that is arranged in a predetermined direction and in a direction approximately perpendicular to the predetermined direction.

[0078] 8 is a diagram illustrating detection of movement of a moving object M in this modified example. In this modified example, the reference area setting unit 21 sets a first detection line 57a located in area 50b, as well as other first detection lines 57c located in three other areas 50c that are adjacent to area 50a with other boundary lines 55c in between.

[0079] When the moving object M passes from the region 50a through a first detection line 57a located within the region 50b, the movement detection unit 23 detects that the moving object M has moved from the region 50a to the region 50b. Furthermore, when the moving object M passes from the region 50a through a specific first detection line 57c among other first detection lines 57c located within another region 50c, the movement detection unit 23 detects that the moving object M has moved to another region 50c where the specific first detection line 57c is located. In other words, when the moving object M passes from the region 50a through another first detection line 57c located within another region 50c that borders the region 50a across another boundary line 55c, the movement detection unit 23 detects that the moving object M has moved from the region 50a to the other region 50c. This configuration makes it possible to detect the movement of the moving object M between three or more regions 50a, 50b, and 50c.

[0080] The number of other regions 50c bordering region 50a across another boundary line 55c is not limited. Although region 50a is entirely surrounded by region 50b and three other regions 50c, a portion of region 50a may border a region other than regions 50b and 50c. The arrangement of regions 50a, 50b, and 50c is not limited. For example, regions 50a, 50b, and 50c may be arranged in a predetermined direction so that regions 50b and 50c sandwich region 50a. In this modification, reference region setting unit 21 may provide second detection lines 57b, as in modification 2. In this case, second detection lines 57b may be provided within region 50b and within other regions 50c.

[0081] (Variation 6) This modification differs from the first embodiment in that the movement detection unit 23 detects the movement of the moving object M from the area 50a to the area 50b.

[0082] In step S4 in this modification, the movement detection unit 23 detects whether the moving object M is located in the region 50a in the image data of at least two consecutive frames among the image data of the multiple frames. Then, if the movement detection unit 23 detects that the moving object M is located in the region 50a in the image data of the two consecutive frames, and if the moving object M is located on the opposite side of the boundary line 55 from the first detection line 57a in the region 50b in the image data of at least one frame after the at least two frames, the movement detection unit 23 detects that the moving object M is moving from the region 50a to the region 50b. This configuration can further improve the accuracy of detecting the movement of the moving object M from the region 50a to the region 50b.

[0083] Although the present invention has been described above using the above-mentioned modified examples and the modified examples as examples, the present invention is not limited to these.

[0084] For example, in the above-described modified example and modified example, the detection system 1 includes the LiDAR device 10 as one image acquisition device or a camera as one image acquisition device. However, there may be a plurality of image acquisition devices.

[0085] In the above embodiment, the regions 50a and 50b adjacent to each other across the boundary line 55 are both closed regions, but this is not limiting. For example, at least one of the regions 50a and 50b may be a closed region, or may be an open region that does not have a portion of its outer edge.

[0086] Furthermore, in the above-described modified example and modified example, the detection device 20 has been described as an example in which image data showing the detection region DR is input from the LiDAR device 10 or a camera as an image acquisition device. However, it is sufficient if image data of the detection region DR acquired by the image acquisition device is input to the detection device 20. For example, image data of the detection region DR may be stored in the memory 30, and the image data of the detection region DR stored in the memory 30 may be input to the detection device 20.

[0087] Furthermore, the above-described modified example and the operation flow of the detection device 20 in the modified example are not limited. For example, step S1 and step S2 may be performed simultaneously.

[0088] Furthermore, in the above-mentioned modified examples and modified examples, a rectangular region that is elongated in a predetermined direction has been described as an example, but the two regions only need to be adjacent to each other across a boundary line, and the shapes of the two regions may be triangular, circular, etc., or may be different shapes from each other.

[0089] In the above embodiment and modified example, the boundary line 55, the first detection lines 57a and 57c, and the second detection line 57b are straight lines, but they may also be curved lines.

[0090] Furthermore, in the above embodiment and the above modified example, the detection device 20 includes the counting unit 24, but the counting unit 24 may not be included.

[0091] In the above-described modified example and modified example, the moving object M is a vehicle. However, the moving object M is not limited to this and may be, for example, a person. [Industrial Applicability]

[0092] According to the present invention, a detection device, a program, and a detection system that can improve the accuracy of detecting the movement of a moving object are provided, and can be used in fields such as indoor and outdoor detection systems. [Explanation of symbols]

[0093] 1. Detection System 10...LiDAR device 20. Detection device 21...Reference area setting section 22. Detection unit 23. Movement detection unit 24. Counter 30...Memory 40···Monitor 50a,50b,50c...area 55,55c...Borderline 57a, 57c...First detection line 57b Second detection line 58a Non-measuring section DR···Detection area

Claims

1. A detection device that detects a moving object from image data acquired by an image acquisition device that acquires an image of a detection area including one area and another area adjacent to each other across a boundary line, When the moving object passes through a first detection line located in the other area from the one area, the moving object is detected as moving from the one area to the other area. A detection device characterized by:

2. The first detection line is along the boundary line.

2. The detection device according to claim 1.

3. When the moving object passes through the first detection line after passing through a second detection line located within the one area, it is detected that the moving object has moved from the one area to the other area.

2. The detection device according to claim 1.

4. the first detection line and the second detection line are along the boundary line, The distance between the first detection line and the boundary line is equal to the distance between the second detection line and the boundary line.

4. The detection device according to claim 3.

5. When the moving object passes through a second detection line located within the one area from the other area, it is detected that the moving object has moved from the other area to the one area.

2. The detection device according to claim 1.

6. At least one of the one area and the other area is a closed area.

2. The detection device according to claim 1.

7. When the moving object passes through another first detection line located in another area adjacent to the one area across another boundary line, the moving object is detected as moving from the one area to the other area.

2. The detection device according to claim 1.

8. When the moving object is located in the one area in the image data of at least two consecutive frames among the image data of a plurality of frames, and when the moving object is located on the opposite side of the boundary line from the first detection line in the other area in the image data of at least one frame after the at least two consecutive frames, it is detected that the moving object is moving from the one area to the other area.

2. The detection device according to claim 1.

9. A program executed by a detection device that detects a moving object from image data acquired by an image acquisition device that acquires an image of a detection area including one area and another area adjacent to each other across a boundary line, The detection device When the moving object passes from the one area through a first detection line located in the other area, a step of detecting that the moving object has moved from the one area to the other area is executed. A program characterized by:

10. an image acquisition device that acquires an image of a detection area including one area and another area that are adjacent to each other across a boundary line; a detection device that detects a moving object from the image data acquired by the image acquisition device; Equipped with The detection device detects that the moving object moves from the one area to the other area when the moving object passes through a first detection line located in the other area. A detection system comprising:

11. The image acquisition device is a LiDAR device that measures the detection area. The detection system of claim 10.

12. The detection system of claim 11 , wherein the LiDAR device does not measure the side of the one region opposite the boundary line.

Images