Systems and methods

Abstract

To generate a 3D map used for detecting a detection target or monitoring a monitoring target area.SOLUTION: A system comprises: a placement unit where a LiDAR is placed; a motor to rotate the placement unit; and an acquisition unit for acquiring a measurement result measured by the LiDAR while the placement unit is rotated using the motor so as to generate a 3D map. A computer-implemented method includes an acquisition step of acquiring a measurement result measured by a LiDAR while a motor to rotate a placement unit where the LiDAR is placed is used to rotate the placement unit so as to generate a 3D map.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system and method. [Background technology]

[0002] Patent Document 1 describes a LiDAR (Light Detection and Ranging) device mounted on a vehicle. [Prior art document] [Patent documents] [Patent Document 1] JP 2019-156261 A Summary of the Invention

[0003] According to one embodiment of the present invention, there is provided a system. The system may include a mount that carries a LiDAR. The system may include a motor that rotates the mount. The system may include an acquisition unit that acquires measurements measured by the LiDAR while rotating the mount using the motor to generate a 3D map.

[0004] The system may further include a generator that generates the 3D map based on the measurement results.

[0005] Any of the systems may further include a detection unit that detects a predetermined detection target based on the 3D map generated by the generation unit.

[0006] In any of the systems, the detection unit may detect the detection target by aligning the 3D map generated by the generation unit with a 3D map in a state in which the detection target is not included, thereby associating each of a plurality of first points in the 3D map generated by the generation unit with each of a plurality of second points in the 3D map in a state in which the detection target is not included, and detecting a target point where the distance in map space from a first point of the plurality of first points to a second point associated with the first point is longer than a predetermined first distance threshold.

[0007] In any of the systems, the detection unit may classify, for each of the multiple detected target points, the one target point as a core point if the number of other target points whose distance to the one target point in the map space is shorter than a predetermined second distance threshold is greater than a predetermined first target point number threshold, classify the one target point as a boundary point if the number of the other target points is less than the first target point number threshold and the core point is included among the other target points, classify the one target point as a noise point if the number of the other target points is less than the first target point number threshold and the core point is not included among the other target points, cluster the detected multiple target points, and determine that the detection target is present in an area corresponding to the one cluster if the number of target points clustered to belong to the one cluster as a result of the clustering is greater than a predetermined second target point number threshold.

[0008] In any of the systems described above, the detection section may determine whether the detection target is present in the area corresponding to the one cluster, further based on the shape and size of the one cluster.

[0009] Any of the systems may further include a division unit that divides a horizontal plane in the map space of the 3D map generated by the generation unit into a plurality of grid cells, the grid cell size of which is determined based on the size of the detection target, and the detection unit may determine that the detection target is present in an area of ​​the plurality of grid cells corresponding to a grid cell in which the number of target points existing in the vertical direction in the map space is greater than a predetermined third target point number threshold.

[0010] Any of the systems may further include a zone setting unit that sets zones specified by a user of the system for the 3D map generated by the generation unit.

[0011] Any of the systems may further include a detection unit that detects, based on the 3D map generated by the generation unit, that a predetermined detection target is present in an area corresponding to the zone set by the zone setting unit, and a monitoring unit that monitors the area corresponding to the zone set by the zone setting unit based on the detection result by the detection unit.

[0012] Any of the systems may further comprise the LiDAR.

[0013] According to one embodiment of the present invention, there is provided a computer-implemented method, which may include acquiring measurements taken by a LiDAR while rotating a mount carrying the LiDAR using a motor that rotates the mount to generate a 3D map.

[0014] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions. [Brief explanation of the drawings]

[0015] [Figure 1] An example of a system 10 is shown schematically. [Figure 2] 1 illustrates an example of a hardware configuration of the rotating LiDAR 100. [Figure 3] 1 illustrates an example of a functional configuration of the rotary LiDAR 100. [Figure 4] 2 shows an example of a functional configuration of an information processing device 200. [Figure 5] FIG. 10 is an explanatory diagram for explaining an example in which the information processing device 200 aligns the detection 3D map and the background 3D map. [Figure 6] FIG. 10 is an explanatory diagram for explaining an example in which the information processing device 200 detects a detection target in normal mode. [Figure 7] FIG. 10 is an explanatory diagram illustrating an example in which the information processing device 200 detects a detection target in a dense mode. [Figure 8] FIG. 2 is an explanatory diagram for explaining an example of a processing flow of the system 10. [Figure 9] FIG. 10 is an explanatory diagram for explaining another example of the processing flow of the system 10. [Figure 10] FIG. 10 is an explanatory diagram for explaining another example of the processing flow of the system 10. [Figure 11] An example of the hardware configuration of a computer 1200 that functions as the rotating LiDAR 100 or the information processing device 200 is shown schematically. DETAILED DESCRIPTION OF THE INVENTION

[0016] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] FIG. 1 schematically illustrates an example of a system 10. The system 10 may include a rotating LiDAR 100. Although FIG. 1 illustrates an example in which the system 10 includes one rotating LiDAR 100, the system 10 may include a plurality of rotating LiDARs 100. The system 10 may include an information processing device 200. The system 10 may include a sensor 300.

[0018] The system 10 provides, for example, a service for generating a 3D map using the rotating LiDAR 100. The system 10 provides, for example, a service for detecting a detection target using the rotating LiDAR 100. The system 10 provides, for example, a service for monitoring a predetermined monitoring target area using the rotating LiDAR 100. The system 10 provides, for example, a service for supporting the movement of a vehicle or a robot.

[0019] The rotary LiDAR 100 outputs laser light from the LiDAR while rotating the LiDAR, and measures the distance between the output position of the laser light and the point at which the laser light is reflected based on the reflected light of the laser light. For example, if the time from the output time of the laser light to the reception time of the reflected light of the laser light reflected at the point is t [s] and the propagation speed of the laser light is c [m / s], the rotary LiDAR 100 measures the distance x [m] between the output position of the laser light and the point at which the laser light is reflected as x [m] = 1 / 2 × t [s] × c [m / s].

[0020] The rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100, for example, by rotating the LiDAR by a predetermined angle. The rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100, for example, by rotating the LiDAR 360 degrees.

[0021] The rotating LiDAR 100 may scan the surroundings of the rotating LiDAR 100 by rotating the LiDAR more than 360 degrees. For example, the rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100 by rotating the LiDAR 720 degrees. For example, the rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100 by rotating the LiDAR 100 1080 degrees.

[0022] The rotating LiDAR 100 may scan the surroundings of the rotating LiDAR 100 by rotating the LiDAR less than 360 degrees. For example, the rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100 by rotating the LiDAR 180 degrees. For example, the rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100 by rotating the LiDAR 180 degrees.

[0023] The rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100, for example, by continuously outputting laser light from the LiDAR while the LiDAR is rotating. The rotating LiDAR 100 scans the surroundings of the rotating LiDAR 100, for example, by outputting laser light from the LiDAR at predetermined angular intervals while the LiDAR is rotating. The rotating LiDAR 100 may scan the surroundings of the rotating LiDAR 100 by outputting laser light from the LiDAR at predetermined time intervals while the LiDAR is rotating.

[0024] The rotating LiDAR 100 acquires measurement results to generate a 3D map, for example. The 3D map includes, for example, a 3D map in a state where the detection target is not included (sometimes referred to as a "background 3D map"), and a 3D map in a state where the detection target may be included (sometimes referred to as a "detection 3D map").

[0025] The 3D map may be used, for example, to detect a target, to monitor a target area, or to guide a vehicle or robot.

[0026] The rotating LiDAR 100 communicates with, for example, an information processing device 200. The rotating LiDAR 100 communicates with the information processing device 200 via, for example, a network 20.

[0027] The network 20 includes, for example, a LAN (Local Area Network). The LAN includes, for example, a wireless LAN conforming to standards such as Wi-Fi (registered trademark). The LAN may also include a wired LAN conforming to standards such as Ethernet (registered trademark). The network 20 may also include a mobile communication network. The network 20 may also include the Internet.

[0028] For example, the rotating LiDAR 100 transmits the measurement results to the information processing device 200. For example, the rotating LiDAR 100 transmits the measurement results to the information processing device 200 while scanning the surroundings. The rotating LiDAR 100 may transmit the measurement results together to the information processing device 200 in response to completion of scanning the surroundings.

[0029] The information processing device 200 executes various processes, for example, the information processing device 200 executes a process of generating a 3D map.

[0030] The information processing device 200 generates a 3D map based on, for example, measurement results received from the rotating LiDAR 100 via the network 20. The information processing device 200 may generate the 3D map further based on sensor data detected by the sensor 300 received from the sensor 300 via the network 20.

[0031] The sensor 300 includes, for example, a camera. The sensor 300 includes, for example, a distance measurement sensor. The sensor 300 may also include any other sensor.

[0032] The information processing device 200 generates, for example, a background 3D map. For example, the information processing device 200 receives, from the rotary LiDAR 100, measurement results obtained when the rotary LiDAR 100 rotates the LiDAR 110 by 360 degrees, and creates a background 3D map based on the measurement results.

[0033] The information processing device 200 generates, for example, a detection 3D map. For example, the information processing device 200 receives, from the rotary LiDAR 100, measurement results obtained every time the rotary LiDAR 100 rotates the LiDAR 110 by 180 degrees, combines the measurement results obtained every time the rotary LiDAR 100 rotates the LiDAR 110 by 180 degrees, and creates a detection 3D map based on the combined measurement results.

[0034] The information processing device 200 executes, for example, a detection process for a detection target. For example, the information processing device 200 aligns the detection 3D map with the background 3D map to locate a plurality of points P d and multiple points P in the background 3D map. b Next, the information processing device 200 associates the plurality of points P d For each of the points P d From the point P d The point P associated with b The information processing device 200 determines whether the distance d in the map space to the point P is longer than a predetermined distance threshold δ. d On the other hand, the information processing device 200 maintains the point P where d is shorter than δ in the detected 3D map. d from the detected 3D map. That is, the information processing device 200 deletes the point P d are filtered from the detected 3D map.

[0035] The information processing device 200 detects the detection target based on the filtered detection 3D map. The information processing device 200 detects the detection target by, for example, executing an algorithm for detecting the detection target. The algorithm for detecting the detection target will be described in detail later.

[0036] The information processing device 200, for example, executes a monitoring process for a monitoring target area. The information processing device 200 monitors the monitoring target area by, for example, monitoring whether the position of a detection target detected by the detection process is included in the monitoring target area.

[0037] Conventional fixed LiDARs are limited in the irradiation angle of the laser light they can output to a range of approximately 30 to 50 degrees. Therefore, when using fixed LiDARs to simultaneously generate a 3D map of a wide-angle area, such as an omnidirectional area, and detect targets within the wide-angle area or monitor the wide-angle area, multiple fixed LiDARs are essential. Furthermore, when generating a high-density 3D map using a single fixed LiDAR that can cover a wide-angle area, a laser light source with a propagation distance of approximately 20 to 30 meters must be used.

[0038] In contrast, the system 10 according to the present embodiment uses a rotating LiDAR 100 to acquire measurement results necessary for generating a 3D map while rotating the LiDAR with a motor. As a result, the system 10 according to the present embodiment can simultaneously generate a 3D map of a wide-angle area, detect a target within the wide-angle area, or monitor the wide-angle area using only one LiDAR. Furthermore, the rotating LiDAR 100 can change the output position of the laser light output from the LiDAR by rotating the LiDAR with a motor. Therefore, a laser light source with a propagation distance of approximately 200 m can be used to generate a 3D map with the same level of density as a high-density 3D map generated using a fixed LiDAR. As a result, the system 10 according to the present embodiment can detect targets located farther away with high accuracy and monitor a target area located farther away with high accuracy.

[0039] 2 schematically illustrates an example of a hardware configuration of the rotating LiDAR 100. The rotating LiDAR 100 may include a LiDAR 110, a mounting unit 120, and a housing 150.

[0040] The LiDAR 110 has an output unit 115 that outputs laser light. The output unit 115 includes, for example, a laser light source that outputs laser light with a wavelength in the infrared region. The output unit 115 includes, for example, a laser light source that outputs laser light with a wavelength in the visible light region. The output unit 115 may also include a laser light source that outputs laser light with a wavelength in the ultraviolet region.

[0041] The output unit 115 includes, for example, 16 laser light sources. The output unit 115 includes, for example, 32 laser light sources. The output unit 115 includes, for example, 64 laser light sources. The output unit 115 includes, for example, 128 laser light sources.

[0042] The mounting unit 120 mounts the LiDAR 110. The mounting unit 120 rotates with the LiDAR 110 mounted thereon, for example, by power energy from a motor. The mounting unit 120 is connected to the motor via, for example, a slip ring.

[0043] For example, the mounting unit 120 rotates around the z-axis of the xyz coordinate system shown in Fig. 2. For example, the mounting unit 120 rotates clockwise around the z-axis. For example, the mounting unit 120 rotates counterclockwise around the z-axis.

[0044] The mounting unit 120 rotates, for example, at a constant angular velocity around the z-axis. By using a motor to rotate the mounting unit 120 at a constant angular velocity, the rotary LiDAR 100 can identify the rotation angle of the mounting unit 120 when the output unit 115 outputs laser light without using an inertial motion unit (IMU).

[0045] The housing 150 houses various devices. The housing 150 houses, for example, a motor. The housing 150 houses, for example, a circuit board that functions as a communication unit of the rotary LiDAR 100. The housing 150 houses, for example, a minicomputer board that functions as a control unit that controls the LiDAR 110 and motor of the rotary LiDAR 100.

[0046] 3 shows an example of a functional configuration of the rotating LiDAR 100. The rotating LiDAR 100 includes a control unit 102, an acquisition unit 104, a generation unit 106, a communication unit 108, a LiDAR 110, a mounting unit 120, and a motor 130. Note that it is not essential that the rotating LiDAR 100 include all of these components.

[0047] The control unit 102 controls the control target. The control unit 102 controls, for example, the motor 130 that rotates the mounting unit 120. The control unit 102 controls the motor 130, for example, to control the rotation angle of the mounting unit 120. The control unit 102 controls the motor 130, for example, to control the rotation speed of the mounting unit 120. The motor 130 may control the motor 130 to control the rotation direction of the mounting unit 120.

[0048] The control unit 102 controls the LiDAR 110. For example, the control unit 102 controls the output power of the laser light output by the LiDAR 110. The control unit 102 may also control the output timing of the laser light output by the LiDAR 110.

[0049] The acquisition unit 104 acquires the measurement results measured by the LiDAR 110. For example, the acquisition unit 104 acquires the measurement results measured by the LiDAR 110 while rotating the mounting unit 120 using the motor 130 in order to generate a 3D map.

[0050] The measurement result includes, for example, the measured distance between the output position where the output unit 115 outputs the laser light and the point where the laser light is reflected. The measurement result includes, for example, the received light intensity of the reflected light when the laser light is reflected at the point. The measurement result includes, for example, the amount of rotation of the motor 130 when the laser outputs the laser light at the output position.

[0051] The generation unit 106 generates a 3D map. The generation unit 106 generates, for example, a background 3D map. The generation unit 106 generates, for example, a detection 3D map.

[0052] The generating unit 106 generates a 3D map based on, for example, the measurement results acquired by the acquiring unit 104. The generating unit 106 generates the 3D map by, for example, associating an output position where the output unit 115 outputs laser light with a measured distance between the output position and a point where the laser light is reflected.

[0053] The communication unit 108 communicates with the information processing device 200. The communication unit 108 communicates with the information processing device 200 via the network 20, for example.

[0054] The communication unit 108, for example, transmits the measurement results acquired by the acquisition unit 104 to the information processing device 200. For example, the communication unit 108 transmits the measurement results acquired by the acquisition unit 104 to the information processing device 200 while the LiDAR 110 is scanning the surroundings. The communication unit 108 may collectively transmit the measurement results acquired by the acquisition unit 104 to the information processing device 200 in response to completion of scanning the surroundings by the LiDAR 110. The communication unit 108 may transmit the 3D map generated by the generation unit 106 to the information processing device 200.

[0055] 4 schematically illustrates an example of the functional configuration of the information processing device 200. The information processing device 200 includes a storage unit 250, an acquisition unit 252, a generation unit 254, a zone setting unit 256, a detection mode setting unit 257, a division unit 258, a detection unit 260, a monitoring unit 262, a display control unit 264, and a display unit 270. Note that it is not essential for the information processing device 200 to include all of these components.

[0056] The memory unit 250 stores various types of information. The memory unit 250 stores, for example, detection target information indicating a detection target to be detected using a 3D map. The detection target is, for example, a person. The detection target is, for example, an animal. The detection target is, for example, a car. The detection target is, for example, a bicycle. The detection target is a natural object such as a tree or a stone. The detection target may be any other object. The memory unit 250 stores, for example, monitored area information indicating a monitored area to be monitored using a 3D map. The monitored area is, for example, an event venue. The monitored area is, for example, a residential area. The monitored area may be any other area. The memory unit 250 may also store installation location information indicating the installation location of the sensor 300.

[0057] The acquisition unit 252 acquires various types of information. The acquisition unit 252 acquires the various types of information by communicating with an external device via the network 20, for example. The acquisition unit 252 may acquire the various types of information by receiving input from a user of the information processing device 200 via an input unit included in the information processing device 200. The user of the information processing device 200 is, for example, an administrator who manages the area for which a 3D map is generated. The user of the information processing device 200 may be any other user. The user of the information processing device 200 may be an example of a user of the system 10. The acquisition unit 252 stores the acquired various types of information in the storage unit 250.

[0058] The acquisition unit 252 acquires, for example, various pieces of information from the rotary LiDAR 100. The acquisition unit 252 acquires various pieces of information from one rotary LiDAR 100. The acquisition unit 252 may acquire various pieces of information from a plurality of rotary LiDARs 100.

[0059] For example, to generate a 3D map, the acquisition unit 252 acquires measurement results measured by the LiDAR 110 while rotating the mounting unit 120 using the motor 130. The acquisition unit 252 may acquire the 3D map.

[0060] The acquisition unit 252 acquires sensor data from the sensor 300, for example. The acquisition unit 252 acquires image data from a camera, for example. The acquisition unit 252 may acquire measured distance data from a distance measurement sensor. The measured distance indicated by the measured distance data is the distance between the output position of a beam output from the distance measurement sensor and the point at which the beam is reflected.

[0061] The generating unit 254 generates a 3D map. The generating unit 254 generates, for example, a background 3D map. The generating unit 254 generates, for example, a detection 3D map. The generating unit 254 may store the generated 3D map in the storage unit 250.

[0062] The generating unit 254 generates a 3D map based on, for example, the measurement results stored in the storage unit 250. The generating unit 254 generates the 3D map by associating an output position where the output unit 115 outputs laser light with a measured distance between the output position and a point where the laser light is reflected.

[0063] If the measurement result includes the intensity of the light received when the laser light output from the output position is reflected at the point, the generation unit 254 may color-code the pixel corresponding to the point according to the intensity of the light received, thereby enabling the information processing device 200 to generate a 3D map that allows the user to easily grasp the reception intensity at each point.

[0064] The generation unit 254 generates a 3D map based on, for example, measurement results measured by a plurality of rotary LiDARs 100. In this case, one 3D map is generated by combining the measurement results measured by each rotary LiDAR 100. This enables the information processing device 200 to generate a wider and higher-density 3D map.

[0065] The generation unit 254 may generate the 3D map further based on the sensor data stored in the storage unit 250. The generation unit 254 generates the 3D map further based on, for example, image data. The generation unit 254 combines, for example, the image data and the 3D map. This allows the information processing device 200 to generate a 3D map that is more in line with the real world.

[0066] The generation unit 254 may generate a 3D map further based on the measured distance data. For example, the generation unit 254 uses the measured distance data to compensate for the measured distances of points for which the measured distances have not been measured by the rotary LiDAR 100. This allows the information processing device 200 to generate a 3D map with even higher density.

[0067] The zone setting unit 256 sets zones for the 3D map stored in the storage unit 250. The zone setting unit 256 sets, for example, a plurality of zones for the 3D map. The zone setting unit 256 may store, in the storage unit 250, zone information indicating the zones set for the 3D map.

[0068] The zone setting unit 256 sets, for example, three-dimensional zones for the 3D map. The zone setting unit 256 may also set two-dimensional zones for the 3D map.

[0069] The zone setting unit 256 sets zones for the 3D map generated by the generation unit 254, for example. The zone setting unit 256 sets zones for the 3D map generated by the generation unit 106, for example.

[0070] The zone setting unit 256 sets zones for, for example, the background 3D map. The zone setting unit 256 sets zones for, for example, the detection 3D map.

[0071] The zone setting unit 256 sets a zone on the 3D map, for example, by being specified by the user of the information processing device 200. The user of the information processing device 200 sets a zone on the 3D map, for example, by performing a click operation using an input unit provided in the information processing device 200. This allows the information processing device 200 to set a zone on the 3D map with a simple click operation, thereby reducing the burden on the user of the information processing device 200 when setting a zone on the 3D map.

[0072] The zone setting unit 256 sets zones of any shape for the 3D map, for example. When setting three-dimensional zones for the 3D map, for example, the zone setting unit 256 sets zones of shapes such as triangular pyramids, quadrangular pyramids, other polygonal pyramids, triangular prisms, quadrangular prisms, other polygonal prisms, cones, cylinders, ellipsoids, spheres, etc. When setting two-dimensional zones for the 3D map, for example, the zone setting unit 256 sets zones of shapes such as triangles, quadrilaterals, other polygons, ellipses, circles, etc.

[0073] The zone setting unit 256 sets, for example, a zone in a shape desired by the user of the information processing device 200 on a 3D map. The zone setting unit 256 sets, for example, a zone in the shape of an area in which the user of the information processing device 200 wants to detect a detection target. The zone setting unit 256 sets, for example, a zone in the shape of an area in which the user of the information processing device 200 wants to monitor.

[0074] Conventional systems could only set zones with simple shapes such as circles and squares on a 3D map. In contrast, the information processing device 200 can set zones with more complex shapes. This allows the information processing device 200 to set zones on a 3D map in shapes that better suit the preferences of the user of the information processing device 200. Furthermore, because the information processing device 200 sets zones on a high-density 3D map, it can set zones with an accuracy of approximately 3 cm, which is not possible with a surveillance camera.

[0075] When multiple zones are set for the 3D map, the zone setting unit 256 may set a color for each zone so that the zones are color-coded. This allows the information processing device 200 to set multiple zones so that the user of the information processing device 200 can more easily understand each zone.

[0076] The detection mode setting unit 257 sets a detection mode for detecting a detection target that may be included in the 3D map. The detection mode setting unit 257 may set a detection mode for each zone set in the 3D map, for example. The detection mode setting unit 257 sets the detection mode, for example, in response to a designation by the user of the information processing device 200.

[0077] The detection mode includes, for example, a normal mode. The detection mode includes, for example, a dense mode. Specific processes when the information processing device 200 detects a detection target in the normal mode and specific processes when the information processing device 200 detects a detection target in the dense mode will be described in detail later.

[0078] The dividing unit 258 divides the detection 3D map stored in the storage unit 250. For example, the dividing unit 258 divides a horizontal plane in the map space of the detection 3D map into a plurality of grid cells whose grid cell size is determined based on the size of the detection target indicated by the detection target information stored in the storage unit 250. For example, the dividing unit 258 divides the horizontal plane in the map space of the detection 3D map into a plurality of grid cells whose grid cell size is n×n.

[0079] The detection section 260 detects a predetermined detection target. For example, the detection section 260 detects the detection target indicated by detection target information stored in the storage section 250. The detection section 260 may store the detection result in the storage section 250.

[0080] The detection unit 260 detects, for example, a detection target that exists in an area corresponding to the detection 3D map stored in the storage unit 250. The detection unit 260 detects a detection target that exists in an area of ​​the detection 3D map that corresponds to a zone indicated by the zone information stored in the storage unit 250.

[0081] The detection unit 260 detects the detection target based on, for example, the 3D map generated by the generation unit 254. The detection unit 260 detects the detection target based on, for example, the 3D map generated by the generation unit 106.

[0082] Here, commonalities between the process when the detection unit 260 detects a detection target in the normal mode and the process when the detection unit 260 detects a detection target in the dense mode will be described.

[0083] The detection unit 260 detects the detection target based on, for example, the background 3D map and the detection 3D map. For example, in order to detect the detection target, the detection unit 260 aligns the detection 3D map with the background 3D map to locate a plurality of points P d and multiple points P in the background 3D map. b and each of the above.

[0084] The detection unit 260 aligns the detection 3D map and the background 3D map by, for example, executing an Iterative Closest Point (ICP) algorithm. For example, before executing the ICP algorithm, the detection unit 260 roughly aligns the detection 3D map and the background 3D map by executing a Random Sample Consensus (RANSAC) algorithm. Thereafter, the detection unit 260 precisely aligns the detection 3D map and the background 3D map by executing the ICP algorithm. The detection unit 260 may align the detection 3D map and the background 3D map by executing the ICP algorithm without executing the RANSAC algorithm.

[0085] The detection unit 260 executes the ICP algorithm, for example, at predetermined time intervals. The detection unit 260 executes the ICP algorithm, for example, at time intervals of 5 to 10 minutes. This allows the information processing device 200 to correct misalignment between the detection 3D map and the background 3D map caused by fluctuations in the rotation speed of the motor 130 mounted on the rotary LiDAR 100.

[0086] Detect multiple points P of the 3D map d and multiple points P in the background 3D map. b After the points P d Point P of d From the point P d The point P associated with b If the detection unit 260 determines that d is longer than the distance threshold δ, the detection unit 260 determines whether the distance d to the point P d target point P t On the other hand, when the detection unit 260 determines that d is shorter than δ, it detects the point P d Delete.

[0087] The information processing device 200 detects a point P dBy filtering out the detected 3D map as being indistinguishable from the background 3D map, the point P t After that, the information processing device 200 extracts only the extracted point P t This allows the information processing device 200 to detect the detection target at high speed without using a GPU, thereby enabling the information processing device 200 to detect the detection target at high speed and at low cost.

[0088] Next, a process specific to when the detection unit 260 detects the detection target in normal mode will be described. t The detection unit 260 performs clustering on the points P that are clustered as belonging to one cluster as a result of the clustering, for example. t The number of points is a predetermined target score threshold N t On the other hand, the detection unit 260 determines that the detection target exists in the area corresponding to the one cluster when the number of points P that are clustered as belonging to the one cluster as a result of the clustering is greater than or equal to the number of points P that are clustered as belonging to the one cluster. t The number of t If the number of clusters is less than N, it is determined that the detection target does not exist in the area corresponding to the cluster. In this case, the detection unit 260 may regard the cluster as noise and delete the cluster. t may be set depending on the detection target.

[0089] The detection unit 260 may determine whether or not the detection target exists in the area corresponding to the cluster, further based on the shape and size of the cluster. t The number of t In a cluster having a larger number of clusters, if the similarity between the shape and size of the cluster and the shape and size of the detection target is higher than a predetermined similarity threshold, the detection unit 260 determines that the detection target exists in the area corresponding to the cluster. t The number of tIf the similarity between the shape and size of a cluster and the shape and size of the detection target is lower than a similarity threshold for a larger number of clusters, it is determined that the detection target does not exist in the area corresponding to the cluster.

[0090] The detection unit 260 executes, for example, a clustering algorithm to detect a plurality of points P t The detection unit 260 executes, for example, a density-based spatial clustering of applications with noise (DBSCAN) algorithm to cluster the multiple points P t Clustering is performed.

[0091] The detection unit 260 detects, for example, a plurality of points P t By classifying multiple points P t The detection unit 260 clusters the detected points P t For each of these, one target point P' t Other target points P'' whose distance in the map space is shorter than a predetermined distance threshold ε t The number of the first target points is a predetermined first target point threshold N c If more than P' t the core point P c Classify into point P'' t The number of c fewer and core points P c is point P'' t If point P' is included in t Let P be the boundary point e Classify into point P'' t The number of c fewer and core points P c is point P'' t If point P' is not included in t At the noise point P n The detection unit 260 classifies the points P t Without classifying multiple P t may be clustered.

[0092] By detecting the detection target in normal mode, the information processing device 200 can detect the detection target in a distant area where the pixel density is too low to detect the detection target using a deep learning-based method. Furthermore, by detecting the detection target in normal mode, the information processing device 200 can increase robustness against noise and detect the detection target more accurately.

[0093] Next, a description will be given of processing specific to when the detection unit 260 detects a detection target in the dense mode. The detection unit 260 detects a detection target based on, for example, the multiple grid cells divided by the division unit 258. The detection unit 260 detects a detection target by, for example, executing a grid occupancy algorithm.

[0094] The detection unit 260 detects, for example, a point P that exists in the vertical direction in the map space among a plurality of grid cells. t The number of points is a predetermined target score threshold N g On the other hand, the detection unit 260 determines that the detection target exists in an area corresponding to a larger number of grid cells. t The number of g In this case, the detection unit 260 determines that the detection target does not exist in the area corresponding to the fewer grid cells. t is regarded as noise, and the point P t You can delete N. g may be set depending on the detection target.

[0095] A point P in the vertical direction in the map space of a grid cell t is, for example, a point P that lies above a grid cell in map space. t The vertical point P in the map space of the grid cell t For example, the point P that exists on a grid cell in the map space t The vertical point P in the map space of the grid cell tis, for example, a point P that lies below a grid cell in map space. t Includes.

[0096] By detecting the detection target in the dense mode, the information processing device 200 can efficiently and accurately detect the detection target that exists in a distant area where the number of pixels per detection target is small and the detection targets are densely packed together.

[0097] When detecting that multiple detection targets exist in an area corresponding to the detection 3D map in normal mode or dense mode, the detection unit 260 may count the number of detection targets present in the area corresponding to the detection 3D map.When detecting that multiple detection targets exist in an area corresponding to a zone in normal mode or dense mode, the detection unit 260 may count the number of detection targets present in the area corresponding to the zone.

[0098] The monitoring unit 262 monitors the monitoring target area. For example, the monitoring unit 262 monitors the monitoring target area indicated by the monitoring target area information stored in the storage unit 250. The monitoring unit 262 may store the monitoring results in the storage unit 250.

[0099] The area to be monitored is, for example, an area corresponding to the detected 3D map stored in the storage unit 250. The area to be monitored is an area of ​​the detected 3D map corresponding to a zone indicated by the zone information stored in the storage unit 250.

[0100] The monitoring unit 262 monitors the area to be monitored, for example, based on the detection result by the detection unit 260. The monitoring unit 262 monitors, for example, whether the position of the detection target detected by the detection unit 260 is included in the area to be monitored. This allows the information processing device 200 to monitor whether the detection target has entered the area to be monitored using a 3D map when the area to be monitored is a restricted area, a dangerous area, or the like.

[0101] The monitoring unit 262 monitors, for example, the number of detection targets present in the monitoring target area. For example, if the number of detection targets present in the monitoring target area is greater than a predetermined number, the monitoring unit 262 determines that the monitoring target area is in a congested state. This allows the information processing device 200 to monitor the congestion state of the monitoring target area using a 3D map.

[0102] The display control unit 264 controls the display of the display unit 270. The display control unit 264 controls the display of the display unit 270 based on, for example, various types of information stored in the storage unit 250. The display unit 270 may display various types of information in accordance with the control of the display control unit 264.

[0103] The display control unit 264 controls the display of the display unit 270, for example, to display a background 3D map. The display control unit 264 controls the display of the display unit 270, for example, to display the background 3D map with zones indicated by the zone information superimposed thereon. For example, when multiple zones are superimposed on the background 3D map, the display control unit 264 controls the display of the display unit 270 to display the background 3D map with each zone color-coded. For example, the display control unit 264 controls the display of the display unit 270 to display the background 3D map with each pixel color-coded according to the received light intensity included in the measurement results.

[0104] The display control unit 264 controls the display of the display unit 270 to display, for example, a detection 3D map. The display control unit 264 controls the display of the display unit 270 to display, for example, the detection 3D map with zones indicated by the zone information superimposed thereon. For example, when multiple zones are superimposed on the detection 3D map, the display control unit 264 controls the display of the display unit 270 to display the detection 3D map with each zone color-coded. For example, the display control unit 264 controls the display of the display unit 270 to display the detection 3D map with each pixel color-coded according to the received light intensity included in the measurement result. For example, the display unit 270 controls the display of the display unit 270 to display the detection 3D map with the detection 3D map divided into multiple grid cells.

[0105] The display control unit 264 controls the display of the display unit 270, for example, to display the detection 3D map with a superimposed display of the detection result by the detection unit 260. The display control unit 264 controls the display of the display unit 270, for example, to display the detection 3D map with a superimposed display of a bounding box that encompasses the occupation area of ​​the detection target in the detection 3D map.

[0106] 5 is an explanatory diagram for explaining an example in which the information processing device 200 aligns the detection 3D map and the background 3D map. Here, an example in which the information processing device 200 aligns the detection 3D map and the background 3D map by executing the ICP algorithm will be mainly described. Note that the "◯" in FIG. 5 indicates a point P b and "▽" is the point P of the detected 3D map. d It is assumed that:

[0107] FIG. 5A shows the information processing device 200 detecting a plurality of points P d Each of these is taken as a set of multiple points P b1 is an explanatory diagram for explaining an example of a process (sometimes referred to as "process 1") for matching the detected 3D map with any of the above. Here, the explanation will be continued assuming that the detection unit 260 executes the RANSAC algorithm to align the detected 3D map with the background 3D map in advance.

[0108] The detection unit 260 detects, for example, the point P d The point P with the shortest distance in the map space from b By identifying the point P d Point P b The detection unit 260 may, for example, perform a nearest neighbor search to find the point P d The point P with the shortest distance in the map space from b For example, when performing the nearest neighbor search, the detection unit 260 identifies a plurality of points P b 5A, the detection unit 260 detects a point P d1 Point P b1 and match the point P d2 Point P b3 and match the point P d3 Point P b3 and match the point P d4 Point P b4 and match the point P d5 Point P b4 and point P d6 Point P b6 The explanation will continue assuming that it matches.

[0109] 5B is an explanatory diagram illustrating an example of a process (sometimes referred to as "process 2") in which the information processing device 200 determines an alignment matrix for aligning the detection 3D map with the background 3D map. Here, an example in which the detection unit 260 determines an alignment matrix from the matching result in process 1 shown in FIG. 5A will be mainly described.

[0110] The detection unit 260 detects a plurality of points P dFor each of the points P d The point P d The point P matched to b 5(A) , the detection unit 260 determines the position error in the map space for point P , and determines the alignment matrix so that the sum of the position errors is minimized. The alignment matrix includes, for example, a rotation matrix. The alignment matrix includes, for example, a translation matrix. In the example shown in FIG. 5(B) , the detection unit 260 determines the position error in the map space for point P , based on the matching result in process 1 shown in FIG. 5(A) . d1 Point P b1 The position error e1 in the map space for point P d2 Point P b3 The position error e2 in the map space for point P d3 Point P b3 The position error e3 in the map space for point P d4 Point P b4 The position error e4 in the map space for point P d5 Point P b4 The position error e5 in map space for point P d6 Point P b6 The sum of the position errors e6 in the map space for total The alignment matrix is ​​determined so that the following equation is minimized:

[0111] 5C is an explanatory diagram illustrating an example of a process (sometimes referred to as "process 3") in which the information processing device 200 determines whether the positional relationship between the detected 3D map and the background 3D map satisfies a predetermined termination condition. Here, the description will continue assuming that the detection unit 260 aligns the detected 3D map with the background 3D map using the alignment matrix determined by process 2 shown in FIG. 5B.

[0112] When the detection unit 260 determines that the positional relationship between the detection 3D map and the background 3D map satisfies the termination condition, the detection unit 260 may terminate the process of aligning the detection 3D map and the background 3D map. dand multiple points P in the background 3D map. b and completes the process of associating each of the detected 3D map and the background 3D map. On the other hand, if the detection unit 260 determines that the positional relationship between the detected 3D map and the background 3D map does not satisfy the termination condition, it may execute process 1 again. In this case, the detection unit 260 repeatedly executes processes 1 to 3 until it determines that the positional relationship between the detected 3D map and the background 3D map satisfies the termination condition.

[0113] The termination condition is, for example, the point P of the detected 3D map after the detected 3D map is aligned with the background 3D map. d and the point P in the background 3D map b The sum of the errors in the positions of the points P in the map space of the detected 3D map and the background 3D map is smaller than a predetermined error threshold. The detection unit 260 performs, for example, a nearest neighbor search to find the point P in the detected 3D map after the detected 3D map is aligned with the background 3D map. d The point P with the shortest distance in the map space from b By identifying the point P d Point P b In the example shown in FIG. 5C, the detection unit 260 matches the point P d1 Point P b1 and match the point P d2 Point P b2 and match the point P d3 Point P b3 and match the point P d4 Point P b4 and match the point P d5 Point P b5 and point P d6 Point P b6 Then, the detection unit 260 may match the point P d1 Point P b1 The position error e'1 in the map space for point P d2 Point P b2 The position error e'2 in the map space for point P d3 Point P b3 The position error e'3 in the map space for point P d4 Point Pb4 The position error e'4 in the map space for point P d5 Point P b5 The position error e'5 in the map space for point P d6 Point P b6 The sum of the position errors e'6 in the map space for total If =e'1+e'2+e'3+e'4+e'5+e'6 is smaller than the error threshold, it may be determined that the positional relationship between the detected 3D map and the background 3D map satisfies the termination condition.

[0114] 6 is an explanatory diagram for explaining an example in which the information processing device 200 detects a detection target in normal mode. Here, the information processing device 200 executes the DBSCAN algorithm to detect a plurality of points P t An example of detecting a detection target from the image will be mainly described. Note that the "□" in Fig. 6 is assumed to be a target point.

[0115] 6A is an explanatory diagram illustrating an example in which the detection unit 260 detects another target point whose distance to the first target point in the map space is shorter than ε. t1 Let us suppose that another target point whose distance to point P is shorter than ε in the map space is detected. t1 is a plurality of points P t The explanation will continue assuming that this is the starting point of the classification process.

[0116] In the example shown in FIG. 6A, the detection unit 260 detects a point P t1 As another target point whose distance to the map space is shorter than ε, point P t2 , point P t3 and point P t4 After that, the detection unit 260 detects the point P t1 The number of other target points corresponding to c In the example shown in FIG. c = 2 and the explanation will continue.

[0117] In the example shown in FIG. 6A, point P t1 The number of other target points corresponding to point P t2 , point P t3 and point P t4 A total of 3>N c Therefore, the detection unit 260 detects the point P t1 the core point P c1 Then, the detection unit 260 classifies the core points P c1 It is determined that belongs to cluster 1.

[0118] 6B is an explanatory diagram for explaining another example in which the detection unit 260 detects another target point whose distance to the one target point in the map space is shorter than ε. Here, the detection unit 260 detects a point P t2 other target points whose distance in the map space to point P is shorter than ε t4 It is assumed that the distance to the target point .epsilon. is shorter than .epsilon. in the map space.

[0119] In the example shown in FIG. 6B, the detection unit 260 detects a point P t2 As another target point whose distance to the map space is shorter than ε, point P t1 , point P t3 and point P t5 After that, the detection unit 260 detects the point P t2 The number of other target points corresponding to c In the example shown in FIG. 6B, the point P t2 The number of other target points corresponding to point P t1 , point P t3 and point P t5 A total of 3>N c Therefore, the detection unit 260 detects the point P t2 the core point P c2 Then, the detection unit 260 classifies the core points P c2 It is determined that belongs to cluster 1.

[0120] In the example shown in FIG. 6B, the detection unit 260 detects the point P t4As another target point whose distance to the map space is shorter than ε, point P t1 and point P t6 After that, the detection unit 260 detects the point P t4 The number of other target points corresponding to c In the example shown in FIG. 6B, the point P t4 The number of other target points corresponding to point P t1 and point P t6 Total of 2 = N c and the core point P c1 is point P t4 Since the point P is included in the other target points corresponding to the point P t4 Let P be the boundary point e4 Then, the detection unit 260 classifies the boundary points P e4 It is determined that belongs to cluster 1.

[0121] 6C is an explanatory diagram illustrating another example in which the detection unit 260 detects another target point whose distance to the first target point in the map space is shorter than ε. Here, the detection unit 260 detects a point P t6 other target points whose distance in the map space to point P is shorter than ε t7 It is assumed that the distance to the target point .epsilon. is shorter than .epsilon. in the map space.

[0122] In the example shown in FIG. 6C, the detection unit 260 detects the point P t6 As another target point whose distance to the map space is shorter than ε, point P t4 After that, the detection unit 260 detects the point P t6 The number of other target points corresponding to c In the example shown in FIG. 6C, the point P t6 The number of other target points corresponding to point P t4 A total of 1 <N c and the core point is point P t6 Since the point P is not included in the other target points corresponding to the point P t6 At the noise point P n6Then, the detection unit 260 classifies the noise points P n6 Remove from the detected 3D map.

[0123] In the example shown in FIG. 6C, the detection unit 260 detects the point P t7 Since there is no other target point whose distance in the map space to t7 At the noise point P n7 Then, the detection unit 260 classifies the noise points P n7 is deleted from the detected 3D map. If the number of other target points whose distance to a target point in the map space is shorter than ε is 0, the number of such other target points is c This may be an example of a case where the core point is smaller and is not included in other target points.

[0124] The detection unit 260 detects the point P t The classification process may be performed until there are no more points P t 6, the detection unit 260 detects the detection target based on the clustering result of the points P t The number of t If the number is greater than the number of clusters, it is determined that the detection target exists in the area corresponding to cluster 1.

[0125] The number of other target points whose distance to one target point in the map space is shorter than ε is N. c If so, the detection unit 260 detects the target point as a core point P c The process of not classifying the target point as a target point is performed by dividing the number of other target points whose distance to the target point in the map space is shorter than ε by N c If so, the detection unit 260 detects the target point as a core point P c This may be replaced with a process of classifying the

[0126] 7 is an explanatory diagram for explaining an example of detecting a detection target in the dense mode by the information processing device 200. Here, the information processing device 200 executes a grid occupation algorithm to detect a plurality of points P t The following mainly describes an example of detecting the detection target from the point P. t It is assumed that:

[0127] 7, the map space is represented by an XYZ coordinate system. Here, the description will be continued assuming that the dividing unit 258 divides the XY plane of Z=0 in the map space of the detection 3D map into a plurality of grid cells whose grid cell size is determined based on the size of the detection target.

[0128] The detection unit 260 detects the detection target based on the plurality of grid cells divided by the division unit 258. For example, the detection unit 260 detects a point P that exists in the Z-axis direction in the map space among the plurality of grid cells divided by the division unit 258. t The number of g It is determined that the detection target exists in an area corresponding to a larger number of grid cells.

[0129] In the example shown in FIG. 7, the detection unit 260 detects a point P t The number of g 7, the detection unit 260 determines that the detection target exists in the area corresponding to grid cell 1. On the other hand, in the example shown in FIG. 7, the detection unit 260 determines that the detection target exists in the area corresponding to grid cell 2 at point P t The number of g Since the number of pixels is smaller than the number of pixels in the grid cell 2, it is determined that the detection target does not exist in the area corresponding to the grid cell 2. In this case, the detection unit 260 detects the point P t is regarded as noise, and the point P t may be deleted.

[0130] 8 is an explanatory diagram for explaining an example of the processing flow of the system 10. Here, an example of the processing flow when the information processing device 200 executes initial settings for detecting a detection target will be mainly described.

[0131] In step (step may be abbreviated as S) 102, the acquisition unit 252 acquires measurement results measured by the rotary LiDAR 100 from the rotary LiDAR 100 via the network 20. The generation unit 254 generates a background 3D map based on the measurement results acquired by the acquisition unit 252.

[0132] In S104, the zone setting unit 256 sets a plurality of zones for the background 3D map generated in S102 by the generation unit 254. In S106, the generation unit 254 stores the background 3D map generated in S102 in the storage unit 250, and the zone setting unit 256 stores zone information indicating the plurality of zones set in S104 in the storage unit 250.

[0133] In S108, the display control unit 264 controls the display of the display unit 270 so as to display the background 3D map generated by the generation unit 254 in S102 in a state in which the multiple zones set by the zone setting unit 256 in S104 are superimposed. The display unit 270 displays the background 3D map in a state in which the multiple zones are superimposed, in accordance with the control of the display control unit 264.

[0134] 9 is an explanatory diagram for explaining another example of the processing flow of the system 10. Here, an example of the processing flow when the information processing device 200 detects a detection target in normal mode will be mainly described.

[0135] In S202, the acquisition unit 252 acquires measurement results measured by the rotating LiDAR 100 from the rotating LiDAR 100 via the network 20. The generation unit 254 generates a detected 3D map based on the measurement results acquired by the acquisition unit 252. The detection unit 260 filters the detected 3D map by comparing the background 3D map stored in the storage unit 250 with the detected 3D map generated by the generation unit 254.

[0136] In S204, the detection unit 260 executes a clustering algorithm on the detection 3D map filtered in S202 to detect detection targets present in areas corresponding to each zone. In S206, the detection unit 260 stores the detection results, including the number of detection targets present in the areas corresponding to each zone, in the storage unit 250.

[0137] In S208, the display control unit 264 controls the display of the display unit 270 so as to display the detected 3D map generated by the generation unit 254 in S202 in a state in which a bounding box encompassing the occupation area of ​​the detection target detected by the detection unit 260 in S204 is superimposed. The display unit 270 displays the detected 3D map in a state in which the bounding box is superimposed, in accordance with the control of the display control unit 264.

[0138] 10 is an explanatory diagram for explaining another example of the processing flow of the system 10. Here, an example of the processing flow when the information processing device 200 detects a detection target in the dense mode will be mainly described.

[0139] In S302, the acquisition unit 252 acquires measurement results measured by the rotating LiDAR 100 from the rotating LiDAR 100 via the network 20. The generation unit 254 generates a detected 3D map based on the measurement results acquired by the acquisition unit 252. The detection unit 260 filters the detected 3D map by comparing the background 3D map stored in the storage unit 250 with the detected 3D map generated by the generation unit 254.

[0140] In S304, the detection unit 260 executes a grid occupancy algorithm on the detection 3D map filtered in S202 to detect detection targets present in areas corresponding to each zone. In S306, the detection unit 260 stores the detection results, including the number of detection targets present in areas corresponding to each zone, in the storage unit 250.

[0141] In S308, the display control unit 264 controls the display of the display unit 270 so as to display the detection 3D map generated by the generation unit 254 in S302 in a state in which a bounding box encompassing the occupation area of ​​the detection target detected by the detection unit 260 in S304 is superimposed. The display unit 270 displays the detection 3D map in a state in which the bounding box is superimposed, in accordance with the control of the display control unit 264.

[0142] 11 schematically shows an example of a hardware configuration of a computer 1200 functioning as the rotating LiDAR 100 or the information processing device 200. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the above embodiment, or can cause the computer 1200 to execute operations associated with the device according to the above embodiment or one or more "parts," and / or can cause the computer 1200 to execute a process according to the above embodiment or steps of the process. Such a program can be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0143] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communications interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard 1242, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0144] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller itself, and causes the image data to be displayed on the display device 1218.

[0145] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0146] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0147] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and causes cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

[0148] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, the DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0149] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive 1226 (DVD-ROM 1227), an IC card, etc. to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0150] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0151] The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0152] The blocks in the flowcharts and block diagrams in the present embodiments may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, including integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0153] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, etc.

[0154] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0155] Computer-readable instructions may be provided locally or over a wide area network (WAN) such as a local area network (LAN), the Internet, etc. to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or programmable circuitry, such that the processor or programmable circuitry executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0156] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0157] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0158] 10 system, 20 network, 100 rotating LiDAR, 102 control unit, 104 acquisition unit, 106 generation unit, 108 communication unit, 110 LiDAR, 115 output unit, 120 mounting unit, 130 motor, 150 housing, 200 information processing device, 250 memory unit, 252 acquisition unit, 254 generation unit, 256 zone setting unit, 257 detection mode setting unit, 258 division unit, 260 detection unit, 262 monitoring unit, 264 display control unit, 270 display unit, 300 sensor, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphics controller, 1218 display device, 1220 input / output controller, 1222 communication interface, 1224 storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 I / O chip, 1242 keyboard

Claims

1. A mounting unit that mounts a LiDAR (Light Detection and Ranging) device; a motor that rotates the mounting portion; an acquisition unit that acquires measurement results measured by the LiDAR while rotating the mounting unit using the motor to generate a 3D map; a generation unit that generates the 3D map based on the measurement results; a detection unit that detects the detection target by aligning the 3D map generated by the generation unit with a 3D map in a state in which a predetermined detection target is not included, thereby associating each of a plurality of first points in the 3D map generated by the generation unit with each of a plurality of second points in the 3D map in a state in which the detection target is not included, and detecting a target point whose distance in map space from a first point of the plurality of first points to a second point associated with the first point is longer than a predetermined first distance threshold; A system comprising:

2. 2. The system according to claim 1, wherein the detection unit classifies, for each of the detected multiple target points, a single target point as a core point if the number of other target points whose distances to the single target point in the map space are shorter than a predetermined second distance threshold is greater than a predetermined first target point number threshold, classifies the single target point as a boundary point if the number of the other target points is less than the first target point number threshold and the core point is included among the other target points, and classifies the single target point as a noise point if the number of the other target points is less than the first target point number threshold and the core point is not included among the other target points, clusters the detected multiple target points, and determines that the detection target is present in an area corresponding to the one cluster if the number of target points clustered to belong to the one cluster as a result of the clustering is greater than a predetermined second target point number threshold.

3. The system according to claim 2 , wherein the detection unit determines whether the detection target exists in the area corresponding to the one cluster based further on the shape and size of the one cluster.

4. a division unit that divides a horizontal plane in the map space of the 3D map generated by the generation unit into a plurality of grid cells, the grid cell size of which is determined based on the size of the detection target; Furthermore, the detection unit determines that the detection target exists in an area corresponding to a grid cell among the plurality of grid cells in which the number of the target points existing in the vertical direction in the map space is greater than a predetermined third target point number threshold; The system of claim 1 .

5. The system according to claim 1 , further comprising a zone setting unit that sets zones specified by a user of the system for the 3D map generated by the generation unit.

6. a detection unit that detects, based on the 3D map generated by the generation unit, that a predetermined detection target is present in an area corresponding to the zone set by the zone setting unit; a monitoring unit that monitors the area corresponding to the zone set by the zone setting unit based on the detection result by the detection unit; The system of claim 5 further comprising:

7. The system of claim 1 , further comprising the LiDAR.

8. 1. A computer-implemented method comprising: An acquisition step of acquiring measurement results measured by the LiDAR while rotating a mounting unit on which the LiDAR is mounted using a motor that rotates the mounting unit to generate a 3D map; generating the 3D map based on the measurement results; a detection step of detecting the detection target by aligning the 3D map generated in the generation step with a 3D map in a state in which a predetermined detection target is not included, thereby associating each of a plurality of first points in the 3D map generated in the generation step with each of a plurality of second points in the 3D map in a state in which the detection target is not included, and detecting a target point whose distance in map space from a first point of the plurality of first points to a second point associated with the first point is longer than a predetermined distance threshold; A method comprising:

Images