Information processing method and information processing device
By generating groups based on point cloud data and setting height, arrangement and deviation conditions, the problem of mistakenly identifying curbs as mobile objects when the sensor scanning density is insufficient, achieving a more accurate identification effect.
Patent Information
- Application Number
- CN202280094468.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-08
- Publication Date
- 2024-11-15
AI Technical Summary
In the prior art, when the density of the ranging point obtained by sensor scanning is insufficient, it is easy to mistakenly identify static structures such as curbs as mobile objects.
By generating a group based on point cloud data, the movement direction of the ranging point in the group is detected, and the height, arrangement and deviation conditions are determined whether the group is a curb, including setting the height of the ranging point in the group as The position projected on the road surface is arranged in the moving direction, and the distance difference is set to be below the specified value, and is identified as a curb when the main condition is met.
Even when the distance measurement point density is insufficient, the possibility of erroneously identifying static structures such as curbs as mobile objects can be effectively reduced.
Smart Images

Figure CN118973883A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an information processing method and an information processing device. Background Art
[0002] In the past, a technology has been proposed that processes distance data (distance and direction) obtained by a scanning laser radar and determines whether a moving object is a pedestrian based on the size or speed of the moving object identified based on the distance data (see Patent Document 1).
[0003] Prior art literature
[0004] Patent Literature
[0005] Patent Document 1: (Japanese) Patent Publication No. 2006-160116 Summary of the invention
[0006] Problems to be solved by the invention
[0007] According to the technology described in Patent Document 1, since objects are identified only by their size or speed, if the density of distance measurement points around the vehicle obtained by scanning using sensors is insufficient, stationary structures such as curbs may be mistakenly identified as moving objects.
[0008] The present invention is made in view of the above problems and aims to provide an information processing method and an information processing device that can reduce the possibility of misidentifying a stationary structure such as a curb as a moving object even when the density of distance measurement points around a vehicle obtained by scanning using a sensor is insufficient.
[0009] Technical solutions to solve problems
[0010] In order to solve the above-mentioned problems, one embodiment of the present invention provides an information processing method and an information processing device, which generate a group consisting of distance measuring points whose distances to each other are within a specified distance based on point cloud data, and detect the moving direction of the distance measuring points included in the group from the first timing to the second timing. In addition, the height of the distance measuring points included in the group from the road surface for vehicle travel is set as a height condition that the height of the distance measuring points included in the group is below the specified height at least at a certain time in the first timing or the second timing, the position of the projection of the distance measuring points included in the group on the road surface is arranged along the moving direction at least at a certain time as an arrangement condition, and the difference between the first distance to the group in the first timing and the second distance to the group in the second timing is below a specified value as a deviation condition. When it is determined that all the main conditions consisting of the height condition, the arrangement condition, and the deviation condition are satisfied, the group is identified as a curb on the road surface.
[0011] Effects of the Invention
[0012] According to the present invention, even when the density of distance measurement points around a vehicle obtained by scanning using a sensor is insufficient, the possibility of erroneously recognizing a stationary structure such as a curb as a moving object can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 It is a block diagram showing the structure of the information processing device 1 according to one embodiment of the present invention.
[0014] Figure 2 This is a flowchart showing the processing of the information processing device 1 according to one embodiment of the present invention.
[0015] Figure 3A 1 is a schematic diagram showing the positional relationship between the distance measuring sensor 10 and the distance measuring point on the surface of the curb.
[0016] Figure 3B It is a schematic diagram showing the relationship between the distance measurement points and the groups on the surface of the curb.
[0017] Figure 4A 1 is a first plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 .
[0018] Figure 4B It is a second plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 .
[0019] Figure 4C 1 is a third plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 . DETAILED DESCRIPTION
[0020] Next, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description, the same elements are denoted by the same reference numerals and repeated descriptions are omitted.
[0021] [Structure of information processing device]
[0022] Reference Figure 1 A configuration example of the information processing device 1 will be described. Figure 1 is a block diagram showing the structure of the information processing device 1 of this embodiment. Figure 1 As shown, the information processing device 1 includes a distance measuring sensor 10 (sensor) and a controller 20 .
[0023] The information processing device 1 can be mounted on a vehicle with an automatic driving function or a vehicle without an automatic driving function. In addition, the information processing device 1 can also be mounted on a vehicle that can switch between automatic driving and manual driving. In addition, the automatic driving function can also be a driving assistance function that automatically controls only part of the vehicle control functions such as steering control, braking force control, and driving force control to assist the driver in driving. In this embodiment, it is assumed that the information processing device 1 is mounted on a vehicle with an automatic driving function for description.
[0024] It should be noted that in Figure 1 Although omitted in FIG. 1 , the information processing device 1 can also control various actuators such as the steering actuator, the accelerator pedal actuator, and the brake actuator based on the recognition result (the position, shape, posture, etc. of the object) realized by the attribute information setting unit 24. In this way, high-precision autonomous driving can be realized.
[0025] The ranging sensor 10 mainly includes a sensor that emits electromagnetic waves from a transmitting point relative to the surroundings of the vehicle, and detects the position of a reflection point based on a reflected wave relative to the emitted electromagnetic waves, thereby measuring the distance and direction to objects around the vehicle. As an example, such a sensor is a laser radar (LIDAR: Laser Imaging Detection and Ranging). A laser radar refers to a sensor that emits light (laser) from a transmitting point relative to a specified range around the vehicle, and detects the position of a ranging point as a reflection point based on a reflected wave, and generates point cloud data related to the ranging point. The laser radar measures the distance and direction to an object or identifies the shape of an object by measuring the time from the emission of light until the light (reflected wave) irradiates the object and reflects. In addition, the laser radar can also obtain the positional relationship of objects in three dimensions. It should be noted that mapping can also be performed using the intensity of the reflected wave.
[0026] For example, the laser radar changes the irradiation direction of light to scan the surroundings of the vehicle in the main scanning direction and the sub-scanning direction. Thus, light is sequentially irradiated to a plurality of ranging points existing around the vehicle. The irradiation of light to a circle of all ranging points existing around the vehicle is repeated at a predetermined time interval. The laser radar generates information (ranging point information) of each ranging point obtained by irradiation of light for each ranging point. Furthermore, the laser radar outputs point cloud data consisting of a plurality of ranging point information to the controller 20.
[0027] The ranging point information includes the position information of the ranging point. The position information is information indicating the position coordinates of the ranging point. In the position coordinates, a polar coordinate system represented by the direction from the laser radar toward the ranging point (roll angle, pitch angle) and the distance (depth) from the laser radar to the ranging point may also be used. In the position coordinates, a three-dimensional coordinate system represented by x-coordinates, y-coordinates and z-coordinates with the setting position of the laser radar as the origin may also be used. In addition, the ranging point information may also include the time information of the ranging point. The time information is information indicating the time when the position information of the ranging point is generated (the reflected wave of the electromagnetic wave is received). In addition, the ranging point information may also include information on the intensity of the reflected wave from the ranging point (intensity information).
[0028] The controller 20 is a general-purpose microcomputer having a CPU (central processing unit), a memory, and an input / output unit. A computer program for functioning as the information processing device 1 is installed in the microcomputer. By executing the computer program, the microcomputer functions as a plurality of information processing circuits provided in the information processing device 1. The controller 20 processes data acquired from the distance measuring sensor 10.
[0029] It should be noted that, although an example is shown here in which the multiple information processing circuits provided in the information processing device 1 are implemented by software, it is also possible to prepare dedicated hardware for executing each information processing as shown below to constitute the information processing circuit. In addition, the multiple information processing circuits may also be constituted by separate hardware.
[0030] As an example of a plurality of information processing circuits (information processing functions), the controller 20 includes a point cloud acquisition unit 21, a distance measurement point extraction unit 23, a clustering unit 25, a group tracking unit 27, a speed calculation unit 29, a vehicle information acquisition unit 31, and a determination unit 33. It should be noted that the controller 20 may also be expressed as an ECU (Electronic Control Unit).
[0031] The point cloud acquisition unit 21 acquires point cloud data from the distance measuring sensor 10 .
[0032] The distance measurement point extraction unit 23 extracts distance measurement points of three-dimensional objects existing around the vehicle, in addition to the distance measurement points on the road surface on which the vehicle travels, based on the point cloud data.
[0033] The clustering unit 25 classifies (clusters) a plurality of ranging points associated with a three-dimensional object into a plurality of groups based on the distances between each point. More specifically, the clustering unit 25 performs a process of classifying a set of ranging points whose distances to adjacent ranging points are less than a specified value into a group of ranging points associated with an object. Therefore, each group is composed of ranging points whose distances to each other are within a specified distance. It should be noted that the specified distance can be set in advance or appropriately set based on the conditions around the vehicle or the speed of the vehicle.
[0034] Furthermore, the clustering unit 25 may calculate the size of each group based on the information of the distance measurement points in the group, and if the calculated size of the group is within a range preset corresponding to the pre-registered object, the clustering unit 25 may set the registered object as a candidate for the group.
[0035] use Figure 3A and Figure 3B The clustering performed by the clustering unit 25 will be described. Figure 3A 1 is a schematic diagram showing the positional relationship between the distance measuring sensor 10 and the distance measuring point on the surface of the curb. Figure 3B It is a schematic diagram showing the relationship between the distance measurement points and the groups on the surface of the curb.
[0036] exist Figure 3A In FIG. 1 , the area through which the electromagnetic waves emitted from the emission point of the distance measuring sensor 10 pass is represented as a cone BL. The emission point of the distance measuring sensor 10 is located at the vertex of the cone BL, and the emitted electromagnetic waves pass through the surface of the cone BL. In addition, a plurality of distance measuring points P located at the intersection of the cone BL and the surface of the curb LS are represented by black dots.
[0037] exist Figure 3B In FIG. 1 , the cones BL1 to BL5 representing the area through which the electromagnetic waves emitted from the emission point of the ranging sensor 10 pass and the portion where the plane including the side of the curb LS intersects are represented by solid lines (curves). In addition, the ranging points corresponding to the curb LS are represented by black dots. It should be noted that it is assumed that the side of the curb LS is perpendicular to the road surface on which the vehicle travels.
[0038] The pitch angles (the longitudinal tilt angles based on the horizontal plane) of the electromagnetic waves represented by the cones BL1 to BL5 when emitted from the emission point of the distance measuring sensor 10 are different from each other. The pitch angle of the traveling direction of the electromagnetic waves corresponding to the cone BL1 is the largest, and the pitch angles of the traveling direction of the electromagnetic waves corresponding to the cones decrease in the order of the cones BL2, BL3, BL4, and BL5.
[0039] exist Figure 3BIn the example, the ranging points belonging to cones BL1 and BL2 are classified into group CL1, and the ranging points belonging to cone BL3 are classified into group CL2 which is different from group CL1. Since both the ranging points belonging to group CL1 and the ranging points belonging to group CL2 are ranging points corresponding to the curb LS, the ranging points belonging to group CL1 and the ranging points belonging to group CL1 should be classified into the same group. However, when the curb LS is located far from the transmitting point of the ranging sensor 10 and the density of the ranging points at the position of the curb LS is insufficient, as shown in FIG. Figure 3B As shown, there may be a problem that the distance measurement points for the same object are classified into different groups.
[0040] in addition, Figure 3B The groups CL1 and CL2 shown in the figure move along the curb LS together with the movement of the vehicle, and therefore appear to have similar movements to pedestrians or small animals. Therefore, if one attempts to identify the object corresponding to the group only by the size or speed of the group, the groups CL1 and CL2 may be mistakenly identified as moving objects. Therefore, the group tracking unit 27 and the determination unit 33 described later perform processing to reduce the possibility of mistakenly identifying the groups CL1 and CL2 as moving objects.
[0041] The group tracking unit 27 determines whether the groups at two consecutive time points (the first timing and the second timing) are groups of the same object based on the clustering results (position, shape, etc. of the group) for the distance measurement points at the two consecutive time points. For example, the group tracking unit 27 obtains the moving direction of the distance measurement points included in the group from the first timing to the second timing.
[0042] In addition, the group tracking unit 27 obtains the heights of the distance measuring points included in the group. The group tracking unit 27 may also obtain a representative value (e.g., an average value) of the heights of the distance measuring points based on a number of distance measuring points greater than a predetermined ratio among the distance measuring points included in the group, and obtain it as the height of the group.
[0043] In addition, the group tracking unit 27 obtains the arrangement direction of the distance measuring points included in the group. More specifically, the group tracking unit 27 calculates the positions of the distance measuring points included in the group projected on the road surface, and obtains the arrangement direction on a two-dimensional plane parallel to the road surface for the multiple positions obtained by projecting the multiple distance measuring points. The group tracking unit 27 may also obtain the arrangement direction based on the number of distance measuring points greater than a predetermined ratio among the distance measuring points included in the group.
[0044] The group tracking unit 27 acquires the height of the distance measuring point and the arrangement direction of the distance measuring point at least one of the first timing and the second timing.
[0045] The group tracking unit 27 acquires the distance from the emitting point emitting electromagnetic waves to the distance measuring point to the group. Here, the group tracking unit 27 acquires the distance from the emitting point to the group at the first timing as the first distance, and acquires the distance from the emitting point to the group at the second timing as the second distance.
[0046] The group tracking unit 27 acquires the height of the group, the arrangement direction of the distance measurement points in the group, and the distance from the transmission point to the group for each group.
[0047] The vehicle information acquisition unit 31 acquires the position, speed, and moving direction of the vehicle. For example, the vehicle information acquisition unit 31 may acquire the position of the vehicle through a GPS receiver or a GNSS receiver (not shown), or may acquire the state of the vehicle using a speed sensor, an acceleration sensor, a steering angle sensor, a gyro sensor, a brake fluid pressure sensor, an accelerator opening sensor, and the like.
[0048] The speed calculation unit 29 calculates, for each group, a moving speed that is assumed when the group is a group consisting of distance measurement points corresponding to curbstones. The magnitude W of the assumed moving speed of the group is calculated by the following formula (1).
[0049] [Mathematical formula 1]
[0050] W=V cosθ+V sinθtan(θ+φ) (1)
[0051] Here, V is the magnitude of the moving speed of the ranging sensor 10, θ is the angle formed by the moving direction of the ranging sensor 10 and the arrangement direction of the ranging points included in the group, and φ is the yaw angle (azimuth) of the group relative to the ranging sensor 10. It should be noted that the moving speed of the ranging sensor 10 is calculated based on the speed and steering angle of the vehicle. In addition, the yaw angle of the group is, for example, the average value of the yaw angles of the ranging points included in the group, or the yaw angle of a representative point of the group calculated based on the ranging points included in the group.
[0052] use Figure 4A , Figure 4B , Figure 4C The reason why the magnitude of the moving speed of the group consisting of distance measurement points corresponding to the curb is expressed by the above-mentioned equation (1) is described below. Figure 4A 1 is a first plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 . Figure 4B It is a second plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 . Figure 4C 1 is a third plan view showing an example of the positional relationship between the curb and the distance measuring sensor 10 .
[0053] exist Figure 4AIn the figure, the distance that the distance measuring sensor 10 advances during the unit time Δt is represented by "VΔt", and the distance that the group moves during the unit time Δt is represented by "WΔt". In addition, the angle formed by the moving direction of the distance measuring sensor 10 and the arrangement direction of the distance measuring points included in the group is represented by "θ", and the yaw angle of the group relative to the distance measuring sensor 10 is represented by "φ". In addition, the distance from the distance measuring sensor 10 to the group (to be precise, the distance on the surface parallel to the road surface) is represented by "r". Circle C1 and circle C2 are circles with a radius of r, which means that the emission point of the distance measuring sensor 10 located at the center of circle C1 is located at the center of circle C2 after the unit time Δt has passed.
[0054] “WΔt” is measured by “W x Δt” and “W y Δt”. Here, “W x Δt" is the distance "V" that the distance measuring sensor 10 moves in a direction parallel to the curb LS during the unit time Δt. x The moving distance of the group generated by "Δt". In addition, "W y Δt" is the distance "V" that the distance measuring sensor 10 moves in the direction perpendicular to the curb LS during the unit time Δt. y The moving distance of the group generated by "Δt".
[0055] exist Figure 4B , the distance measuring sensor 10 is shown to be moving in a direction parallel to the curb LS. Figure 4B The positional relationship between the circle C1 and the circle C2 shown in FIG. x Δt” and “V x Δt”, the following formula (2) holds.
[0056] [Mathematical formula 2]
[0057] W x △t=V x △t=V△t cosθ (2)
[0058] exist Figure 4C , the distance measuring sensor 10 is shown to be moving in a direction perpendicular to the curb LS. Figure 4C In the equation, “α” satisfies “α+θ+φ=π / 2”. Figure 4C The positional relationship between the circle C1 and the circle C2 shown in FIG. y Δt” and “V y Δt”, the following formula (3) holds.
[0059] [Mathematical formula 3]
[0060]
[0061] It should be noted that when deriving the formula (3), "α+θ+φ=π / 2" and "r" being sufficiently larger than "VΔt" were used.
[0062] Therefore, by the "W" shown in formula (2) x Δt” and “W y The sum of "Δt" is divided by "Δt" to obtain "W" shown in formula (1).
[0063] Therefore, the magnitude of the moving speed of the group consisting of the ranging points corresponding to the curb is shown as the above formula (1). The moving speed assumed for the group actually obtained from the point cloud data is calculated based on formula (1). When the assumed moving speed is close to the actual moving speed, it can be determined that the group is likely to correspond to the curb.
[0064] The determination unit 33 determines whether the condition indicating "like a curb" is satisfied for each group. Here, the following conditions can be cited as the condition indicating "like a curb".
[0065] [A. Height conditions]
[0066] The height condition is that the height of the distance measurement points included in the group from the road surface on which the vehicle travels is below a predetermined height at least at a certain time in the first timing or the second timing. Most of the curbstones on the road surface are below the predetermined height. Therefore, the group for which the height condition is satisfied is likely to correspond to the curbstone.
[0067] [B. Arrangement conditions]
[0068] The positions of the projections of the distance measuring points included in the group on the road surface are arranged along the moving direction of the group at least at one time in the first timing or the second timing as an arrangement condition. The arrangement direction of the positions of the projections of the distance measuring points included in the group corresponding to the curb is consistent with the moving direction of the group. Therefore, the group for which the arrangement condition is satisfied is highly likely to correspond to the curb.
[0069] [C. Deviation conditions]
[0070] The difference between the first distance from the transmitting point to the group at the first timing and the second distance from the transmitting point to the group at the second timing is less than a predetermined value as a deviation condition. The distance from the transmitting point to the group corresponding to the curb does not change significantly. Therefore, the group for which the deviation condition is satisfied is likely to correspond to the curb.
[0071] [D.Continuation conditions]
[0072] The arrangement direction of the positions of the projections of the distance measuring points included in the first timing group on the road surface and the arrangement direction of the positions of the projections of the distance measuring points included in the second timing group on the road surface are the same as the continuation condition. The arrangement direction of the distance measuring points included in the group corresponding to the curb does not change significantly. Therefore, the group for which the continuation condition is satisfied is highly likely to correspond to the curb.
[0073] It should be noted that the height of the distance measuring points included in the group at the first timing and the height of the distance measuring points included in the group at the second timing can also be used as another continuation condition. The height of the distance measuring points included in the group corresponding to the curb does not change significantly. Therefore, the group for which the continuation condition is satisfied is likely to correspond to the curb.
[0074] [E. Speed condition]
[0075] The speed condition is that the difference between the assumed moving speed of the group actually obtained from the point cloud data based on formula (1) and the actual moving speed of the group is less than a specified threshold (that is, the two moving speeds are equal or slightly different). As described above, the moving speed of the group corresponding to the curb can be evaluated by formula (1). Therefore, the group for which the speed condition is satisfied is likely to correspond to the curb.
[0076] [F. Other conditions]
[0077] Furthermore, when one or more of the above conditions are satisfied at two or more timings, it can be said that the group is likely to be a curb. In particular, when one or more of the above conditions are satisfied at different vehicle speeds after acceleration or deceleration of the vehicle, it can be said that the group is likely to be a curb.
[0078] Furthermore, when one or more of the above conditions are satisfied for a plurality of groups adjacent to the group of interest, there is a high possibility that the group of interest and the plurality of adjacent groups are groups corresponding to the same curb.
[0079] The determination unit 33 determines for each group whether the above-mentioned condition indicating "like a curb" is satisfied. More specifically, the determination unit 33 determines whether all the main conditions consisting of the height condition, the arrangement condition, and the deviation condition are satisfied. If it is determined that all the main conditions are satisfied, the determination unit 33 identifies the group as a curb on the road surface.
[0080] Furthermore, when the determination unit 33 determines that the continuation condition is satisfied in addition to all the conditions of the main condition, the group may be identified as a curb on the road surface. Furthermore, when the determination unit 33 determines that the speed condition is satisfied in addition to all the conditions of the main condition, the group may be identified as a curb on the road surface. Furthermore, when the determination unit 33 determines that other conditions are satisfied in addition to all the conditions of the main condition, the group may be identified as a curb on the road surface.
[0081] [Processing steps of information processing device]
[0082] Next, refer to Figure 2 The flowchart of FIG. 1 illustrates the processing procedure of the information processing device 1 of the present embodiment. Figure 2 This is a flowchart showing the processing of the information processing device 1 according to the present embodiment. Figure 2 The processing of the information processing device 1 shown may be repeatedly executed in a predetermined cycle.
[0083] First, in step S101 , the point cloud acquisition unit 21 acquires point cloud data from the distance measuring sensor 10 .
[0084] In step S103 , the distance measurement point extraction unit 23 extracts distance measurement points of three-dimensional objects existing around the vehicle, in addition to the distance measurement points on the road surface on which the vehicle travels, based on the point cloud data.
[0085] In step S105, the clustering unit 25 classifies (clusters) a plurality of distance measurement points related to the three-dimensional object into a plurality of groups based on the distances between the points. In addition, the group tracking unit 27 acquires various information related to the group and the distance measurement points included in the group.
[0086] In step S107 , the determination unit 33 selects an unprocessed group from the groups obtained by the clustering unit 25 .
[0087] In steps S109 , S111 , and S113 , the determination unit 33 determines whether the condition indicating “like a curb” is satisfied for each group.
[0088] For example, in step S109, the determination unit 33 determines whether the height condition is satisfied. In step S111, the determination unit 33 determines whether the arrangement condition is satisfied. In step S113, the determination unit 33 determines whether the deviation condition is satisfied. The determination unit 33 may also determine whether the continuation condition, speed condition, or other conditions are satisfied.
[0089] When it is determined in steps S109, S111, and S113 that the condition indicating "like a curb" is not satisfied (NO in any of steps S109, S111, and S113), in step S117, the determination unit 33 identifies the selected group as a group corresponding to something other than a curb.
[0090] On the other hand, when it is determined in steps S109, S111, and S113 that the condition indicating "like a curb" is met (when the answer is YES in all steps S109, S111, and S113), in step S115, the determination unit 33 identifies the selected group as a group corresponding to a curb.
[0091] In step S119, it is determined whether the determination process by the determination unit 33 has been completed for all groups. If it is determined that the process has not been completed for all groups (NO in step S119), the process returns to step S107.
[0092] On the other hand, when it is determined that all groups have completed the processing (in the case of YES in step S119), in step S121, the recognition result of the determination unit 33 is output from the input and output unit of the controller 20. Then, the process ends. Figure 2 Flowchart of the process.
[0093] [Effects of Embodiment]
[0094] As described in detail above, the information processing method and information processing device of the present embodiment generate a group based on point cloud data, the point cloud data being generated by emitting electromagnetic waves from a transmitting point for a specified range around a vehicle and detecting the position of a ranging point as a reflection point based on a reflected wave, and the group is composed of ranging points whose distances from each other are within a specified distance. Furthermore, the moving direction of the ranging points included in the group from the first timing to the second timing is detected. The height of the ranging points included in the group from the road surface for the vehicle to travel is set to be below a specified height at least at a certain time in the first timing or the second timing as a height condition. The positions of the projections of the ranging points included in the group on the road surface are arranged along the moving direction at least at a certain time in the first timing or the second timing as an arrangement condition. The difference between the first distance from the transmitting point to the group at the first timing and the second distance from the transmitting point to the group at the second timing is set to be below a specified value as a deviation condition. Furthermore, it is determined whether the main conditions consisting of the height condition, the arrangement condition, and the deviation condition are all satisfied, and if it is determined that all the main conditions are satisfied, the group is identified as a curb on the road surface.
[0095] Thus, even when the density of the distance measuring points around the vehicle obtained by scanning using the sensor is insufficient, the possibility of erroneously identifying a stationary structure such as a curb as a moving object can be reduced. In particular, since it is determined whether a group is a curb based on the height of the distance measuring points constituting the group, the movement direction of the group and the similarity of the arrangement direction of the distance measuring points within the group, and the time change of the distance from the emission point of the sensor, the possibility of erroneously detecting a curb as a moving object can be reduced.
[0096] In addition, the information processing method and information processing device of this embodiment can also identify the group as a curb on the road surface when it is determined that all the above main conditions are met and the arrangement direction of the first timed position is the same as the arrangement direction of the second timed position. As for the arrangement direction of the distance measurement points contained in the group corresponding to the curb, if they are in the same place, they do not change in time, and they change slowly in space. Therefore, by adding arrangement conditions for judgment, the possibility of mistakenly judging the moving object as a curb can be reduced.
[0097] Furthermore, the information processing method and the information processing device of this embodiment can also identify the group as a curb on the road surface when it is determined that all the above main conditions are met and the height of the distance measurement point included in the first timing group is the same as the height of the distance measurement point included in the second timing group. The height of the group corresponding to the curb does not change in time if it is at the same location, and changes slowly in space. Therefore, by adding this condition for judgment, the possibility of mistakenly judging the moving object as a curb can be reduced.
[0098] In addition, the information processing method and the information processing device of the present embodiment may also determine that all the above main conditions are met, and V is set as the magnitude of the moving speed of the sensor, θ is set as the angle formed by the direction of sensor movement and the arrangement direction of the position, φ is set as the azimuth angle of the group relative to the sensor, and the magnitude of the moving speed W of the group is
[0099] [Formula 4]
[0100] When W=V cosθ+Vsinθtan(θ+φ), the group is identified as a curb on the road surface. The moving speed of the group corresponding to the curb is calculated by the above calculation formula based on the moving speed of the sensor, the angle of the curb relative to the moving direction of the sensor, and the azimuth of the ranging point included in the group. Therefore, by adding the speed condition for judgment, the possibility of mistakenly judging the moving object as a curb can be reduced.
[0101] Furthermore, the information processing method and the information processing device of the present embodiment may also identify the group as a curb on the road surface when it is determined that all the above main conditions are satisfied and it is determined that all the main conditions are satisfied after the acceleration or deceleration of the vehicle. When the moving speed of the group satisfies the above conditions at multiple time points with different vehicle speeds, the possibility that the group corresponds to a curb is high. Therefore, by determining the above conditions even after the acceleration or deceleration of the vehicle, the possibility of mistakenly determining the moving object as a curb can be reduced.
[0102] In addition, the information processing method and information processing device of this embodiment can also identify multiple groups as curbs on the road surface when it is determined that all the above main conditions are met with respect to the above multiple groups. In the case of spatially continuous curbs, the possibility that the above conditions are met in multiple groups is high. Therefore, by determining that the above conditions are met in multiple groups, the possibility of mistakenly judging a moving object as a curb can be reduced.
[0103] Each function described in the above embodiments may be implemented by one or more processing circuits, including a programmed processor or circuit, a device such as an application-specific integrated circuit (ASIC), or a circuit component configured to perform the described functions.
[0104] The content of the present invention has been described above according to the embodiments, but the present invention is not limited to these descriptions, and various modifications and improvements can be made to those skilled in the art. It should not be understood that the discussion and drawings forming part of this disclosure limit the present invention. Based on this disclosure, those skilled in the art will clearly understand various alternative embodiments, examples, and application technologies.
[0105] The present invention naturally includes various embodiments not described here, etc. Therefore, the technical scope of the present invention is to be determined only by the invention-specific matters of the appropriate claims based on the above description.
[0106] Description of Reference Numerals
[0107] 1 information processing device; 10 ranging sensor; 20 controller; 21 point cloud acquisition unit; 23 ranging point extraction unit; 25 clustering unit; 27 group tracking unit; 29 speed calculation unit; 31 vehicle information acquisition unit; 33 determination unit.
Claims
1. An information processing method, which is an information processing method of an information processing device, wherein the information processing device comprises: a sensor that emits electromagnetic waves from a transmitting point for a prescribed range around the vehicle and detects the position of a ranging point as a reflection point based on a reflected wave, and generates point cloud data related to the ranging point; A controller that processes data acquired from the sensor, wherein the information processing method is characterized in that: Through the controller, Based on the point cloud data, a group consisting of the distance measurement points whose distances to each other are within a predetermined distance is generated, detecting a moving direction of the distance measuring point included in the group from a first timing to a second timing, The height condition is that the height of the distance measuring points included in the group from the road surface on which the vehicle is traveling is equal to or lower than a predetermined height at at least one of the first timing or the second timing, The positions of the projections of the distance measuring points included in the group onto the road surface are arranged along the moving direction at at least one of the first timing or the second timing as an arrangement condition, The difference between a first distance from the transmission point to the group at the first timing and a second distance from the transmission point to the group at the second timing is equal to or less than a predetermined value as a deviation condition, Determine whether all the main conditions consisting of the height condition, the arrangement condition, and the deviation condition are satisfied, When it is determined that all the main conditions are satisfied, the group is identified as a curb on the road surface.
2. The information processing method according to claim 1, characterized in that: Through the controller, When it is determined that all the main conditions are satisfied and the arrangement direction of the positions at the first timing is the same as the arrangement direction of the positions at the second timing, the group is recognized as a curb on the road surface.
3. The information processing method according to claim 1 or 2, characterized in that: Through the controller, When it is determined that all the main conditions are satisfied and the height of the distance measuring points included in the group at the first timing is the same as the height of the distance measuring points included in the group at the second timing, the group is identified as a curb on the road surface.
4. The information processing method according to any one of claims 1 to 3, characterized in that: Through the controller, When it is determined that all the main conditions are met, And V is set to the magnitude of the moving speed of the sensor, Let θ be the angle between the direction of movement of the sensor and the direction of arrangement of the positions, Let φ be the azimuth angle of the group relative to the sensor, The moving speed W of the group is [Formula 1] When W=Vcosθ+Vsinθtan(θ+φ), the group is recognized as a curbstone on the road surface.
5. The information processing method according to any one of claims 1 to 4, characterized in that: When it is determined that all the main conditions are satisfied, and when it is determined that all the main conditions are satisfied after the acceleration or deceleration of the vehicle, the group is recognized as a curb on the road surface.
6. The information processing method according to any one of claims 1 to 5, characterized in that: When it is determined that all of the main conditions are satisfied for two or more groups, the groups are recognized as curbstones on the road surface.
7. An information processing device, characterized in that: have: a sensor that emits electromagnetic waves from a transmitting point for a prescribed range around the vehicle and detects the position of a ranging point as a reflection point based on a reflected wave, and generates point cloud data related to the ranging point; a controller that processes the data acquired from the sensor, Through the controller, Based on the point cloud data, a group consisting of the distance measurement points whose distances to each other are within a predetermined distance is generated, detecting a moving direction of the distance measuring point included in the group from a first timing to a second timing, The height condition is that the height of the distance measuring points included in the group from the road surface on which the vehicle travels is equal to or lower than a predetermined height at at least one of the first timing or the second timing. The projection positions of the distance measuring points included in the group on the road surface are arranged along the moving direction at at least one of the first timing or the second timing as an arrangement condition, The difference between a first distance from the transmission point to the group at the first timing and a second distance from the transmission point to the group at the second timing is equal to or less than a predetermined value as a deviation condition, Determine whether all the main conditions consisting of the height condition, the arrangement condition, and the deviation condition are satisfied, When it is determined that all the main conditions are satisfied, the group is identified as a curb on the road surface.
