Control devices and control systems
Patent Information
- Application Number
- JP2025025800
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-20
- Publication Date
- 2026-09-01
AI Technical Summary
【0012】 以上のように、本発明によれば、センサに対して斜めとなる検出対象についても精度よく検出対象を検出することができる。
Smart Images

Figure 2026139262000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to a control device and a control system that detect objects using clustering processing. [Background Art]
[0002] In recent years, various technologies for supporting automatic driving of vehicles have been developed. For example, Patent Document 1 discloses an approach notification system that is placed at a location adjacent to a cut-down portion of a sidewalk and includes a road attachment installed on the sidewalk near the boundary between the pedestrian road and the roadway, the road attachment includes a first road attachment and a second road attachment installed across the cut-down portion, the first road attachment includes a first columnar portion and a first sensor provided on an upper portion of the first columnar portion for detecting moving objects around the first road attachment, the first sensor is arranged such that the center of the detection range faces inward from the cut-down portion, the second road attachment includes a second columnar portion and a second sensor provided on an upper portion of the second columnar portion for detecting moving objects around the first road attachment, and the second sensor is arranged such that the center of the detection range faces inward from the cut-down portion. [Prior Art Documents] [Patent Documents]
[0003] [Patent Document 1] Japanese Patent No. 7556621 [Summary of the Invention] [Problem to be Solved by the Invention]
[0004] However, it is necessary to install the sensor so as to directly face the detection target, which causes a problem that the installation position of the sensor is extremely limited.
[0005] In view of the above circumstances, an object of the present invention is to provide a control device and a control system that can accurately detect a detection target even when the detection target is oblique with respect to a sensor. [Means for solving the problem]
[0006] To achieve the above objective, a control device according to one embodiment of the present invention comprises an acquisition unit, a projection unit, a size calculation unit, an orientation calculation unit, a position determination unit, and a generation unit. The acquisition unit acquires three-dimensional point cloud data generated by a sensor that measures the distance to each point on the surface of a detection target moving along a first road. The projection unit projects the three-dimensional point cloud data onto a two-dimensional region. The size calculation unit calculates the outline box of the detection target in the two-dimensional region based on the projection result of the projection unit. The orientation calculation unit calculates the orientation of the object to be detected from the outer shape box. The position determination unit determines a reference position for identifying the position or velocity of the object to be detected based on the calculation result of the orientation calculation unit.
[0007] The size calculation unit may divide the outer box into rectangular sections based on the point cloud data of the two-dimensional region projected by the projection unit.
[0008] The position determination unit may determine any point on the shorter side of the rectangle as the reference position.
[0009] The system further comprises a memory unit that stores the direction of travel of the first road described above, The orientation calculation unit may calculate the front and rear of the detected object based on the direction of travel of the first road.
[0010] The system may further include a generation unit that generates state information relating to the detection target based on the above-mentioned reference position, and an output unit that outputs the generated state information to a transmitter that transmits it to a second road different from the first road.
[0011] A control system according to one embodiment of the present invention comprises a sensor and a control device. The above sensor measures the distance to each point on the surface of the object being detected as it moves along the first road. The control device includes an acquisition unit for acquiring the three-dimensional point cloud data, a projection unit for projecting the three-dimensional point cloud data onto a two-dimensional region, a size calculation unit for calculating the outline box of the detection target in the two-dimensional region based on the projection result of the projection unit, a direction calculation unit for calculating the orientation of the detection target based on the calculation result of the size calculation unit, and a position determination unit for determining a reference position for identifying the position or velocity of the detection target based on the calculation result of the direction calculation unit. [Effects of the Invention]
[0012] As described above, according to the present invention, even detection targets that are at an angle to the sensor can be detected with high accuracy. [Brief explanation of the drawing]
[0013] [Figure 1] This figure shows a control system according to an embodiment of the present invention. [Figure 2] This figure shows the positional relationship between the sensor and the object to be detected according to an embodiment of the present invention. [Figure 3] This is a block diagram of a control system according to an embodiment of the present invention. [Figure 4] This figure shows three-dimensional point cloud data according to an embodiment of the present invention. [Figure 5] This is a diagram showing an embodiment of the present invention projected onto a two-dimensional region. [Figure 6] This figure shows the calculation of the orientation of the object to be detected according to an embodiment of the present invention, where (A) is a diagram showing the outer box, and (B) is a diagram showing the calculation of the orientation of the object to be detected from the outer box. [Figure 7] This figure shows a detection target traveling diagonally with respect to a sensor according to an embodiment of the present invention. [Figure 8] This figure shows a flowchart of a control system according to an embodiment of the present invention. [Figure 9] This is a block diagram of a modified control system. [Figure 10] FIG. 4 is a diagram illustrating a detection object traveling obliquely with respect to a sensor according to a modified example. [Figure 11] FIG. 5 is a diagram illustrating a conventional method for calculating a reference position of a detection object. DESCRIPTION OF EMBODIMENTS
[0014] Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[0015] <First Embodiment> FIG. 1 is a diagram illustrating a control system 100 according to an embodiment of the present invention, and FIG. 2 is a diagram illustrating a positional relationship between a sensor 10 and a detection object K1 according to an embodiment of the present invention. FIG. 3 is a block diagram of the control system 100 according to an embodiment of the present invention, and FIG. 4 is a diagram illustrating three-dimensional point cloud data G according to an embodiment of the present invention. In the drawings, the X axis, Y axis, and Z axis indicate three mutually orthogonal axial directions.
[0016] The control system 100 according to the present embodiment notifies, for example, at an intersection or a merging point of an expressway, state information (travel position, travel speed, travel lane, etc.) of a vehicle traveling from one lane to a vehicle traveling from the other lane (e.g., an autonomous driving vehicle), to support safe driving.
[0017] As illustrated in FIGS. 1 and 2, the control system 100 includes the sensor 10, a control device 20, and a transmitter 30. As illustrated in FIG. 1, in the present embodiment, there is a road including a first road D1 and a second road D2 different from the first road D1, and the sensor 10 is provided to face the first road D1. In the present embodiment, a T-junction is described as an example, but the present invention is not limited to this of course.
[0018] Furthermore, the transmitter 30 is positioned facing the second road D2. In this embodiment, a wall W is provided between the first road D1 and the second road D2, making it impossible to see the second road D2 from the first road D1, and the first road D1 from the second road D2. However, this is by no means limited, and the wall W does not necessarily have to be provided between the first road D1 and the second road D2.
[0019] (sensor) In this embodiment, the sensor 10 is mounted at a predetermined height on a support column S that supports the control device 20 (described later), and detects objects present in a predetermined area A on the road D1. In this embodiment, the sensor 10 is mounted on a support column S, but of course, it is not limited to this.
[0020] In this embodiment, the sensor 10 is, for example, a LiDAR (Light Detection and Ranging) sensor, which measures the distance to each point on the surface of the object to be detected that is present on the first road D1.
[0021] The sensor 10 also measures the time from irradiation to reflection, calculates the distance to the target object, calculates the coordinates of each point (reflection point) G1 on the target object's surface based on that distance, and generates three-dimensional point cloud data G. The sensor 10 transmits the generated three-dimensional point cloud data G to the control device 20, which will be described later.
[0022] As shown in Figure 4, in this embodiment, the sensor 10 outputs the three-dimensional point cloud data G described above using coordinates where the direction of travel of the first road D1 is the Y axis, the direction perpendicular to the first road D1 (direction of gravity) is the Z axis, and the direction perpendicular to the Y and Z axes is the X axis. However, the method of determining the coordinates is, of course, not limited to this.
[0023] Furthermore, the sensor 10 is provided so as to be able to communicate with the control device 20 by wire or wireless connection.
[0024] In this embodiment, the detection target is described as a vehicle K1, but it is not limited to this, and could be a person K2.
[0025] (Control device) The control device 20 includes an acquisition unit 21, a projection unit 22, a calculation unit 23, a position determination unit 24, a generation unit 25, a storage unit 26, and an output unit 27. It generates state information of the vehicle K1 to be detected and outputs it to the transmitter 30, which will be described later. The calculation unit 23 includes a size calculation unit 231 and an orientation calculation unit 232.
[0026] Figure 5 is a diagram projected onto a two-dimensional region R according to an embodiment of the present invention, and Figure 6 is a diagram showing the calculation of the orientation of the detection target K1 according to an embodiment of the present invention, where (A) is a diagram showing the outer box B, and (B) is a diagram showing the calculation of the orientation of the detection target K1 from the outer box B. Figure 7 is a diagram showing the detection target K1 traveling diagonally with respect to the sensor 10 according to an embodiment of the present invention. In this embodiment, as shown in Figure 7, the detection target K1 traveling in the first lane D11 of a two-lane road (first lane D11 and second lane D12) is traveling on a curved road. The detection target K1 located in area A, which includes the curved road, is detected by the sensor 10.
[0027] The acquisition unit 21 acquires three-dimensional point cloud data G, which includes multiple reflection points G1 generated by the sensor 10 (see Figure 4).
[0028] The projection unit 22 projects the three-dimensional point cloud data G onto a two-dimensional region R to generate point cloud data G' (two-dimensional point cloud data) of the two-dimensional region R (see Figures 5 and 6). The point cloud data G' of the two-dimensional region R is a collection of projected points G2, which are points obtained by projecting the reflection points G1 of the three-dimensional point cloud data G onto the XY plane to create a two-dimensional object. In other words, the point cloud data G' (two-dimensional point cloud data) of the two-dimensional region R is data obtained by viewing the three-dimensional point cloud data G in two dimensions from the Z-axis direction.
[0029] The size calculation unit 231 calculates the outline box B of the detection target K1 in the two-dimensional region R based on the projection result of the projection unit 22. As shown in Figure 6(A), the outline box (boundary box) is a rectangle that encloses each projection point G2. Since the detection target is a vehicle K1, the size calculation unit 231 partitions the area so that the outline box B is rectangular (because a vehicle is roughly rectangular in shape with its long axis in the direction of travel when viewed from the Z-axis direction).
[0030] As shown in Figure 6(A), the size calculation unit 231 generates a rectangular outer box B using point P1, which is the minimum value in the X-axis direction, point P2, which is the minimum value in the Y-axis direction, point P3, which is the maximum value in the X-axis direction, and correction point P4', which is the maximum value in the Y-axis direction generated by the correction, with respect to the origin O.
[0031] Points P1 to P3 are the actual projected points, and point P4' is a virtual projected point set up to form a rectangle. Here, the coordinate position of point P4' is determined such that the line segment SH2 connecting points P1 and P4' is parallel to the line segment SH1 connecting points P2 and P3, and the line segment LH1 connecting points P3 and P4' is parallel to the line segment LH2 connecting points P1 and P2.
[0032] On the other hand, when a quadrilateral is formed by points P1 to P3 and point P4, which is the actual projected point and the point with the maximum value in the Y-axis direction, the shape will be roughly trapezoidal and not rectangular. In that case, the size calculation unit 231 corrects the outer box B so that it becomes rectangular.
[0033] In this embodiment, when the projection point G2 is enclosed and a rectangular shape is formed, point P4 is corrected. That is, for example, if point P3 is corrected and a point is taken such that the line segment between point P4 and the corrected point P3 is parallel to the line segment LH2 between points P1 and P2, then a projection point P2 that is not enclosed will appear (the same applies to points P1 and P2 below). Furthermore, the size calculation unit 231 forms a rectangular outer box B so as to minimize the number of points to be corrected.
[0034] As shown in Figures 6(A) and (B), the outer box B is a rectangle having a first short side SH1, a second short side SH2, a first long side LH1, and a second long side LH2.
[0035] The orientation calculation unit 232 calculates the orientation of the detection target K1 from the outer box B based on the shape of the detection target stored in the storage unit 26, which will be described later. As shown in Figure 6(B), the orientation calculation unit 232 calculates a straight line SL connecting the midpoint ST1 of the first short side SH1 and the midpoint ST2 of the second short side SH2 of the outer box B generated by the size calculation unit 231, and the slope of the calculated straight line SL is calculated as the orientation of the detection target K1 (in this embodiment, the detection target is a vehicle K1, so the shape is rectangular).
[0036] In other words, for the vehicle K1 being detected, the shorter side of the rectangle will be either the front (windshield side) or the rear (rear window side). Therefore, the slope of the line connecting the midpoints of the two shorter sides will determine the orientation of the vehicle K1 being detected.
[0037] The position determination unit 24 determines a reference position for identifying the position or velocity of the detection target K1 based on the calculation result of the orientation calculation unit 232.
[0038] Here, the reference position is a point used to calculate the position and velocity of the detection target K1, and in this embodiment, it is the midpoint ST1 of the first short side SH1. The velocity and other values are calculated based on this reference position. In this embodiment, the midpoint ST1 of the first short side SH1 is used as the reference position, but of course, it is not limited to this, and for example, it may be any point on the first short side SH1.
[0039] The position determination unit 24 calculates the orientation (front / back) of the detection target K1 based on the information regarding the direction of travel of the first road D1 stored in the storage unit 26, which will be described later. In other words, as shown in Figure 1, if the traffic lane of the first road D1 is moving in the direction approaching the sensor 10, the detection target K1 present on the first road D1 will have its short side (in this embodiment, the first short side SH1) facing forward (towards the windshield) on the sensor 10 side. Based on this, the position determination unit 24 determines the reference position.
[0040] The generation unit 25 generates state information, including the driving position (coordinate position), driving speed, and driving lane information of the detected target K1, based on the reference position ST1 determined by the position determination unit 24.
[0041] The generation unit 25 calculates the driving speed based on the time interval at which the three-dimensional point cloud data G is transmitted by the sensor 10 and the amount of change in the coordinate position of the reference position ST1 determined by the position determination unit 24. It also generates information about the driving lane of the detected target K1 traveling on the road D1 based on the reference position ST1 determined by the position determination unit 24.
[0042] The memory unit 26 stores road condition information relating to the first road D1. Road condition information includes the shape of the first road D1, including area A detected by the sensor 10, the number of lanes, and the direction of travel. The shape of the first road D1 refers to whether it is a straight road or a curved road. The memory unit 26 also stores the shape of the outer box of the object to be detected. For example, if the object to be detected is a vehicle, the outer box is rectangular. Furthermore, the memory unit 26 stores information related to programs and parameters that execute various functions of the control device 20.
[0043] The output unit 27 transmits the status information generated by the generation unit 25 to the transmitter 30, which will be described later, by wire or wireless connection.
[0044] (Transmitter) As described above, the transmitter 30 is installed facing the second road D2. In this embodiment, as shown in Figure 1, the transmitter 30 is installed at a predetermined height on the support column S and wirelessly transmits the status information output by the output unit 27. The transmitter 30 may transmit the status information at predetermined intervals, or it may transmit it when the target vehicle T is detected by a vehicle detector (a sensor different from sensor 10) or the like.
[0045] (Flowchart of the control system) Next, the details of the control device 20 will be described along with the operation of the control system 100 of this embodiment. Figure 8 is a flowchart of the control system 100 according to an embodiment of the present invention. The object to be detected is vehicle K1.
[0046] First, the acquisition unit 21 acquires the three-dimensional point cloud data G generated by the sensor 10 (step 101).
[0047] Next, the projection unit 22 projects the three-dimensional point cloud data G onto a two-dimensional region R to generate point cloud data G' (two-dimensional point cloud data) of the two-dimensional region R (step 102).
[0048] Next, the size calculation unit 231 generates the outer box B (step 103). The size calculation unit 231 calculates the outer box B of the detection target K1 in the two-dimensional region R based on the projection result of the projection unit 22. The size calculation unit 231 also divides the outer box B so that it is rectangular.
[0049] Next, the orientation calculation unit 232 calculates the orientation of the detection target K1 (step 104). The orientation calculation unit 232 calculates the orientation from the outline box B generated by the size calculation unit 231. In this embodiment, the slope of the line connecting the midpoints of the two short sides of the outline box B becomes the orientation of the detection target K1.
[0050] Next, the position determination unit 24 determines the reference position of the detection target K1 (step 105). Based on the information regarding the direction of travel of the first road D1 stored in the memory unit 26 as described above, the position determination unit 24 calculates the orientation (front and back) of the detection target K1. The position determination unit 24 then determines the midpoint ST1 in front of the detection target K1 as the reference position.
[0051] Next, the generation unit 25 generates state information (step 106). Based on the reference position ST1 determined by the position determination unit 24, the generation unit 25 generates information regarding the position of the detection target K1, information regarding the driving speed, information regarding the driving lane, and so on.
[0052] Next, the transmitter 30 transmits status information (step 107). The transmitter 30 wirelessly transmits the status information output by the output unit 27 to the target vehicle T traveling on the second road D2.
[0053] As described above, the control system 100 generates an outer box B based on the detection result of the sensor 10, and determines the orientation of the detection target K1 and the reference position ST1 based on the outer box B. This makes it possible to accurately detect the detection target K1 even if it is at an angle to the sensor 10.
[0054] Figure 11 shows a conventional method for calculating the reference position ST1' of the detection target.
[0055] Conventionally, a rectangular outline box B' was generated from the actually projected two-dimensional point cloud data G2'. In other words, as shown in Figure 11, the outline box B' was generated from the four points P5 to P8 that were actually projected, and the reference position ST1' was determined on the premise that the sensor was directly facing the object being detected.
[0056] However, in that case, it was difficult to accurately detect the position and speed of the object traveling on a curved road. Furthermore, because the sensor had to be directly facing the object, installation was sometimes difficult, such as limiting the possible installation locations.
[0057] In contrast, in this embodiment, the orientation (direction of travel and front / rear) of the detection target K1 is calculated from the shape of the outer box B. This makes it possible to accurately detect the detection target K1 even if it is at an angle to the sensor 10. Furthermore, by transmitting the state information of the detection target K1 to the target vehicle T traveling on the second road D2, the possibility of a collision at the merging point of the second road D2 and the first road D1 can be reduced.
[0058] Furthermore, the size calculation unit 231 divides the outer box B into rectangular sections. This allows for accurate detection of the orientation of the object to be detected K1. In other words, as shown in Figure 6(A), if the outer box is formed using only the points that are actually projected, it becomes trapezoidal, and calculating the orientation of the object to be detected K1 using this trapezoidal shape will result in an orientation different from the actual orientation. This is because it does not reflect the area not detected by the sensor 10. In contrast, in this embodiment, by calculating a rectangular outer box B that reflects the area not detected by the sensor 10, the orientation of the object to be detected K1 can be accurately detected.
[0059] Furthermore, the position determination unit 24 determined one point on the front short side of the rectangular outer box B as the reference position. As a result, since the position information among the state information transmitted by the transmitter 30 is based on the front portion of the detection target K1, the possibility of collision with the detection target K1 for the target vehicle T traveling on the second road D2 can be reduced.
[0060] Furthermore, in this embodiment, vehicle status information can be accurately detected not only when driving on a curved road, but also when a vehicle changes lanes.
[0061] <Variation> The embodiments described above are not limited to those described, and various other embodiments can be realized. For example, if the angular difference between the direction of travel of the road and the direction of travel of the detected object is greater than a predetermined value, the direction of travel of the detected object may be corrected to match the direction of travel of the road. Figure 9 is a block diagram of the control system 100' according to a modified example, and Figure 10 is a diagram showing the detected object K1' traveling diagonally with respect to the sensor 10 according to the modified example. The explanation of configurations similar to those in the first embodiment will be simplified or omitted.
[0062] The control device 20' includes an acquisition unit 21, a projection unit 22, a calculation unit 23', a position determination unit 24, a generation unit 25, a storage unit 26, and an output unit 27. The calculation unit 23' includes a size calculation unit 231, an orientation calculation unit 232, an angle determination unit 233, and an orientation correction unit 234.
[0063] The acquisition unit 21 acquires three-dimensional point cloud data G, which includes multiple reflection points G1 generated by the sensor 10, using the sensor 10. The projection unit 22 projects the three-dimensional point cloud data G onto a two-dimensional region R to generate point cloud data G' (two-dimensional point cloud data) of the two-dimensional region R. The size calculation unit 231 calculates the outline box of the detection target K1' in the two-dimensional region R based on the projection result of the projection unit 22.
[0064] The orientation calculation unit 232 calculates the orientation of the detection target K1' from the outline box based on the shape of the detection target stored in the storage unit 26. The orientation calculation unit 232 calculates a straight line SL' connecting the midpoint ST1' of the first short side and the midpoint ST2' of the second short side of the outline box generated by the size calculation unit 231, and the slope of the calculated straight line SL' is calculated as the orientation of the detection target K1'.
[0065] The angle determination unit 233 determines whether the angle between the direction of travel of the first road D1 at the reference position ST1' determined by the position determination unit 24 and the direction of travel of the detected object K1' is greater than or equal to a predetermined angle.
[0066] In other words, the angle determination unit 233 determines whether the angle Δφ formed by the straight line SL' calculated by the direction calculation unit 232 and the direction of travel SS of the first road D1 at the reference position ST1' is greater than or equal to a predetermined angle. The memory unit 26 stores in advance the shape of the first road D1 (first lane D11 and second lane D12) (such as the radius of curvature and the position of the road's centerline). Also, as shown in Figure 10, area A' is a road with a radius of curvature r (with the sensor 10 position as the origin and the predetermined coordinates (x, y) = (A, B) as the center of the circle of curvature).
[0067] As shown in Figure 10, when the detection target K1' is at coordinate position ST1', the direction of travel of the first road D1 at coordinate position ST1' is the tangential direction SS at coordinate position ST1'.
[0068] The direction correction unit 234 corrects the direction of travel of the detected object K1' to the direction of travel SS of the first road D1 at the reference position ST1' determined by the position determination unit 24, if the angle determined by the angle determination unit 233 is greater than a predetermined angle. Alternatively, it may correct the angle to be limited to a predetermined angle.
[0069] This allows for accurate detection of the direction of travel of the object being detected. In other words, in the case of an outer box whose shape is corrected and calculated by the size calculation unit 231, there may be a discrepancy in the direction of travel of the object being detected. Therefore, if the angle determined by the angle determination unit 233 is greater than a predetermined angle, the direction of travel of the object being detected K1' is corrected to the direction of travel SS of the first road D1 at the reference position ST1' determined by the position determination unit 24, thereby preventing the transmission of incorrect state information regarding the direction of travel of the object being detected K1' to the target vehicle T.
[0070] <Other variations> In the above embodiments, the reference position was determined to be in front of the object to be detected, but of course, it is not limited to this, and could be, for example, the center of gravity of the outer box. Also, in the above embodiments, the transmitter 30 transmitted status information to the target vehicle T traveling on the second road D2, but of course, it is not limited to this, and the status information (for example, there is a vehicle that will merge from the first road D1 in X seconds) could be displayed on the display panel.
[0071] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications can be made. Furthermore, the configurations of each embodiment and its modified form may be combined. [Explanation of Symbols]
[0072] 10...Sensor 20...Control device 21…Acquisition part 22...Projection section 23...Calculation section 231...Size calculation section 232... Direction calculation unit 233...Angle determination section 234... Direction correction unit 24...Positioning section 25…Generation part 26...Storage section 27…Output section 30…Transmitter K1... Vehicle D1... First road D2... Second road
Claims
1. An acquisition unit that acquires three-dimensional point cloud data generated by a sensor that measures the distance to each point on the surface of a detection target moving on a first road; a projection unit that projects the three-dimensional point cloud data onto a two-dimensional region; a size calculation unit that calculates the outline box of the detection target in the two-dimensional region based on the projection result of the projection unit; an orientation calculation unit that calculates the orientation of the detection target from the outline box; a position determination unit that determines a reference position for identifying the position or velocity of the detection target based on the calculation result of the orientation calculation unit; and a generation unit that generates state information related to the detection target based on the reference position. A control device equipped with the following.
2. A control device according to claim 1, The size calculation unit divides the outer box into rectangular sections based on the point cloud data of the two-dimensional region projected by the projection unit. Control device.
3. A control device according to claim 2, The position determination unit determines an arbitrary point on the shorter side of the rectangle as the reference position. Control device.
4. A control device according to claim 1, The system further comprises a memory unit for storing the direction of travel of the first road, The position determination unit calculates the front and rear of the detection target based on the direction of travel of the first road. Control device.
5. A control device according to claim 1, The system further comprises a generation unit that generates state information relating to the detection target based on the reference position, and an output unit that outputs the generated state information to a transmitter that transmits it to a second road different from the first road. Control device.
6. A sensor that measures the distance to each point on the surface of a detection target moving on the first road, A control device comprising: an acquisition unit for acquiring the three-dimensional point cloud data; a projection unit for projecting the three-dimensional point cloud data onto a two-dimensional region; a size calculation unit for calculating the outline box of the detection target in the two-dimensional region based on the projection result of the projection unit; a direction calculation unit for calculating the orientation of the detection target based on the calculation result of the size calculation unit; a position determination unit for determining a reference position for identifying the position or velocity of the detection target based on the determination result of the front / rear determination unit; and a generation unit for generating state information relating to the detection target based on the reference position. A control system equipped with the following features.
Citation Information
Patent Citations
Approach warning system
JP7556621B1